Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are...Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.展开更多
To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.Howeve...To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.However,most of the studies had focused only on colored plastic fragments,ignoring colorless plastic fragments and the effects of different environmental media(backgrounds),thus underestimating their abundance.To address this issue,the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis(PLS-DA),extreme gradient boost,support vector machine and random forest classifier.The effects of polymer color,type,thickness,and background on the plastic fragments classification were evaluated.PLS-DA presented the best and most stable outcome,with higher robustness and lower misclassification rate.All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm.A two-stage modeling method,which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background,was proposed.The method presented an accuracy higher than 99%in different backgrounds.In summary,this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds.展开更多
BACKGROUND Patients with early-stage hepatocellular carcinoma(HCC)generally have good survival rates following surgical resection.However,a subset of these patients experience recurrence within five years post-surgery...BACKGROUND Patients with early-stage hepatocellular carcinoma(HCC)generally have good survival rates following surgical resection.However,a subset of these patients experience recurrence within five years post-surgery.AIM To develop predictive models utilizing machine learning(ML)methods to detect early-stage patients at a high risk of mortality.METHODS Eight hundred and eight patients with HCC at Beijing Ditan Hospital were randomly allocated to training and validation cohorts in a 2:1 ratio.Prognostic models were generated using random survival forests and artificial neural networks(ANNs).These ML models were compared with other classic HCC scoring systems.A decision-tree model was established to validate the contri-bution of immune-inflammatory indicators to the long-term outlook of patients with early-stage HCC.RESULTS Immune-inflammatory markers,albumin-bilirubin scores,alpha-fetoprotein,tumor size,and International Normalized Ratio were closely associated with the 5-year survival rates.Among various predictive models,the ANN model gene-rated using these indicators through ML algorithms exhibited superior perfor-mance,with a 5-year area under the curve(AUC)of 0.85(95%CI:0.82-0.88).In the validation cohort,the 5-year AUC was 0.82(95%CI:0.74-0.85).According to the ANN model,patients were classified into high-risk and low-risk groups,with an overall survival hazard ratio of 7.98(95%CI:5.85-10.93,P<0.0001)between the two cohorts.INTRODUCTION Hepatocellular carcinoma(HCC)is one of the six most prevalent cancers[1]and the third leading cause of cancer-related mortality[2].China has some of the highest incidence and mortality rates for liver cancer,accounting for half of global cases[3,4].The Barcelona Clinic Liver Cancer(BCLC)Staging System is the most widely used framework for diagnosing and treating HCC[5].The optimal candidates for surgical treatment are those with early-stage HCC,classified as BCLC stage 0 or A.Patients with early-stage liver cancer typically have a better prognosis after surgical resection,achieving a 5-year survival rate of 60%-70%[6].However,the high postoperative recurrence rates of HCC remain a major obstacle to long-term efficacy.To improve the prognosis of patients with early-stage HCC,it is necessary to develop models that can identify those with poor prognoses,enabling stratified and personalized treatment and follow-up strategies.Chronic inflammation is linked to the development and advancement of tumors[7].Recently,peripheral blood immune indicators,such as neutrophil-to-lymphocyte ratio(NLR),platelet-to-lymphocyte ratio(PLR),and lymphocyte-to-monocyte ratio(LMR),have garnered extensive attention and have been used to predict survival in various tumors and inflammation-related diseases[8-10].However,the relationship between these combinations of immune markers and the outcomes in patients with early-stage HCC require further investigation.Machine learning(ML)algorithms are capable of handling large and complex datasets,generating more accurate and personalized predictions through unique training algorithms that better manage nonlinear statistical relationships than traditional analytical methods.Commonly used ML models include artificial neural networks(ANNs)and random survival forests(RSFs),which have shown satisfactory accuracy in prognostic predictions across various cancers and other diseases[11-13].ANNs have performed well in identifying the progression from liver cirrhosis to HCC and predicting overall survival(OS)in patients with HCC[14,15].However,no studies have confirmed the ability of ML models to predict post-surgical survival in patients with early-stage HCC.Through ML,a better understanding of the risk factors for early-stage HCC prognosis can be achieved.This aids in surgical decision-making,identifying patients at a high risk of mortality,and selecting subsequent treatment strategies.In this study,we aimed to establish a 5-year prognostic model for patients with early-stage HCC after surgical resection,based on ML and systemic immune-inflammatory indicators.This model seeks to improve the early monitoring of high-risk patients and provide personalized treatment plans.展开更多
Breast cancer is among the leading causes of cancer mortality globally,and its diagnosis through histopathological image analysis is often prone to inter-observer variability and misclassification.Existing machine lea...Breast cancer is among the leading causes of cancer mortality globally,and its diagnosis through histopathological image analysis is often prone to inter-observer variability and misclassification.Existing machine learning(ML)methods struggle with intra-class heterogeneity and inter-class similarity,necessitating more robust classification models.This study presents an ML classifier ensemble hybrid model for deep feature extraction with deep learning(DL)and Bat Swarm Optimization(BSO)hyperparameter optimization to improve breast cancer histopathology(BCH)image classification.A dataset of 804 Hematoxylin and Eosin(H&E)stained images classified as Benign,in situ,Invasive,and Normal categories(ICIAR2018_BACH_Challenge)has been utilized.ResNet50 was utilized for feature extraction,while Support Vector Machines(SVM),Random Forests(RF),XGBoosts(XGB),Decision Trees(DT),and AdaBoosts(ADB)were utilized for classification.BSO was utilized for hyperparameter optimization in a soft voting ensemble approach.Accuracy,precision,recall,specificity,F1-score,Receiver Operating Characteristic(ROC),and Precision-Recall(PR)were utilized for model performance metrics.The model using an ensemble outperformed individual classifiers in terms of having greater accuracy(~90.0%),precision(~86.4%),recall(~86.3%),and specificity(~96.6%).The robustness of the model was verified by both ROC and PR curves,which showed AUC values of 1.00,0.99,and 0.98 for Benign,Invasive,and in situ instances,respectively.This ensemble model delivers a strong and clinically valid methodology for breast cancer classification that enhances precision and minimizes diagnostic errors.Future work should focus on explainable AI,multi-modal fusion,few-shot learning,and edge computing for real-world deployment.展开更多
In this paper,we propose STPLF,which stands for the short-term forecasting of locational marginal price components,including the forecasting of non-conforming hourly net loads.The volatility of transmission-level hour...In this paper,we propose STPLF,which stands for the short-term forecasting of locational marginal price components,including the forecasting of non-conforming hourly net loads.The volatility of transmission-level hourly locational marginal prices(LMPs)is caused by several factors,including weather data,hourly gas prices,historical hourly loads,and market prices.In addition,variations of non-conforming net loads,which are affected by behind-the-meter distributed energy resources(DERs)and retail customer loads,could have a major impact on the volatility of hourly LMPs,as bulk grid operators have limited visibility of such retail-level resources.We propose a fusion forecasting model for the STPLF,which uses machine learning and deep learning methods to forecast non-conforming loads and respective hourly prices.Additionally,data preprocessing and feature extraction are used to increase the accuracy of the STPLF.The proposed STPLF model also includes a post-processing stage for calculating the probability of hourly LMP spikes.We use a practical set of data to analyze the STPLF results and validate the proposed probabilistic method for calculating the LMP spikes.展开更多
Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Int...Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Intelligence(AI)techniques have played an important role in early diagnosis and help physicians make decisions.This study evaluated the performance of Machine Learning(ML)algorithms on the hepatitis data set.The dataset contains missing values that have been processed and outliers removed.The dataset was counterbalanced by the Synthetic Minority Over-sampling Technique(SMOTE).The features of the data set were processed in two ways:first,the application of the Recursive Feature Elimination(RFE)algorithm to arrange the percentage of contribution of each feature to the diagnosis of hepatitis,then selection of important features using the t-distributed Stochastic Neighbor Embedding(t-SNE)and Principal Component Analysis(PCA)algorithms.Second,the SelectKBest function was applied to give scores for each attribute,followed by the t-SNE and PCA algorithms.Finally,the classification algorithms K-Nearest Neighbors(KNN),Support Vector Machine(SVM),Artificial Neural Network(ANN),Decision Tree(DT),and Random Forest(RF)were fed by the dataset after processing the features in different methods are RFE with t-SNE and PCA and SelectKBest with t-SNE and PCA).All algorithms yielded promising results for diagnosing hepatitis data sets.The RF with RFE and PCA methods achieved accuracy,Precision,Recall,and AUC of 97.18%,96.72%,97.29%,and 94.2%,respectively,during the training phase.During the testing phase,it reached accuracy,Precision,Recall,and AUC by 96.31%,95.23%,97.11%,and 92.67%,respectively.展开更多
Introduction Deep learning(DL),as one of the most transformative technologies in artificial intelligence(AI),is undergoing a pivotal transition from laboratory research to industrial deployment.Advancing at an unprece...Introduction Deep learning(DL),as one of the most transformative technologies in artificial intelligence(AI),is undergoing a pivotal transition from laboratory research to industrial deployment.Advancing at an unprecedented pace,DL is transcending theoretical and application boundaries to penetrate emerging realworld scenarios such as industrial automation,urban management,and health monitoring,thereby driving a new wave of intelligent transformation.In August 2023,Goldman Sachs estimated that global AI investment will reach US$200 billion by 2025[1].However,the increasing complexity and dynamic nature of application scenarios expose critical challenges in traditional deep learning,including data heterogeneity,insufficient model generalization,computational resource constraints,and privacy-security trade-offs.The next generation of deep learning methodologies needs to achieve breakthroughs in multimodal fusion,lightweight design,interpretability enhancement,and cross-disciplinary collaborative optimization,in order to develop more efficient,robust,and practically valuable intelligent systems.展开更多
Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex ro...Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex road traffic environment of smart vehicles and other vehicles frequently experiences conflicting start and stop motion.The fine-grained scheduling of autonomous vehicles(AVs)at non-signalized intersections,which is a promising technique for exploring optimal driving paths for both assisted driving nowadays and driverless cars in the near future,has attracted significant attention owing to its high potential for improving road safety and traffic efficiency.Fine-grained scheduling primarily focuses on signalized intersection scenarios,as applying it directly to non-signalized intersections is challenging because each AV can move freely without traffic signal control.This may cause frequent driving collisions and low road traffic efficiency.Therefore,this study proposes a novel algorithm to address this issue.Our work focuses on the fine-grained scheduling of automated vehicles at non-signal intersections via dual reinforced training(FS-DRL).For FS-DRL,we first use a grid to describe the non-signalized intersection and propose a convolutional neural network(CNN)-based fast decision model that can rapidly yield a coarse-grained scheduling decision for each AV in a distributed manner.We then load these coarse-grained scheduling decisions onto a deep Q-learning network(DQN)for further evaluation.We use an adaptive learning rate to maximize the reward function and employ parameterεto tradeoff the fast speed of coarse-grained scheduling in the CNN and optimal fine-grained scheduling in the DQN.In addition,we prove that using this adaptive learning rate leads to a converged loss rate with an extremely small number of training loops.The simulation results show that compared with Dijkstra,RNN,and ant colony-based scheduling,FS-DRL yields a high accuracy of 96.5%on the sample,with improved performance of approximately 61.54%-85.37%in terms of the average conflict and traffic efficiency.展开更多
BACKGROUND Early screening methods for gastric cancer(GC)are lacking;therefore,the disease often progresses to an advanced stage when patients first start to exhibit typical symptoms.Endoscopy and pathological biopsy ...BACKGROUND Early screening methods for gastric cancer(GC)are lacking;therefore,the disease often progresses to an advanced stage when patients first start to exhibit typical symptoms.Endoscopy and pathological biopsy remain the primary diagnostic approaches,but they are invasive and not yet widely applicable for early popu-lation screening.miRNA is a highly conserved type of RNA that exists stably in plasma.Dysfunction of miRNA is linked to tumorigenesis and progression,indicating that individual miRNAs or combinations of multiple miRNAs may serve as potential biomarkers.AIM To identify effective plasma miRNA biomarkers and investigate the clinical value of combining multiple miRNAs for early detection of GC.METHODS Plasma samples from multiple centres were collected.Differentially expressed genes among healthy controls,early-stage GC patients,and advanced-stage GC patients were identified through small RNA sequencing(sRNA-seq)and validated via real-time quantitative reverse transcription polymerase chain reaction(RT-qPCR).A Wilcoxon signed-rank test was used to investigate the differences in miRNAs.Sequencing datasets of GC serum samples were retrieved from the Gene Expression Omnibus(GEO),ArrayExpress,and The Cancer Genome Atlas databases,and a multilayer perceptron-artificial neural network(MLP-ANN)model was constructed for the key risk miRNAs.The pROC package was used to assess the discriminatory efficacy of the model.RESULTS Plasma samples of 107 normal,71 early GC and 97 advanced GC patients were obtained from three centres,and serum samples of 8443 normal and 1583 GC patients were obtained from the GEO database.The sRNA-seq and RT-qPCR experiments revealed that miR-452-5p,miR-5010-5p,miR-27b-5p,miR-5189-5p,miR-552-5p and miR-199b-5p were significantly increased in early GC patients compared with healthy controls and in advanced GC patients compared with early GC patients(P<0.05).An MLP-ANN model was constructed for the six key miRNAs.The area under the curve(AUC)within the training cohort was 0.983[95% confidence interval(CI):0.980–0.986].In the two validation cohorts,the AUCs were 0.995(95%CI:0.987 to nearly 1.000)and 0.979(95%CI:0.972–0.986),respectively.CONCLUSION Potential miRNA biomarkers,including miR-452-5p,miR-5010-5p,miR-27b-5p,miR-5189-5p,miR-552-5p and miR-199b-5p,were identified.A GC classifier based on these miRNAs was developed,benefiting early detection and population screening.展开更多
BACKGROUND Hepatocellular carcinoma(HCC)is the most common primary liver malignancy.Ablation therapy is one of the first-line treatments for early HCC.Accurately predicting early recurrence(ER)is crucial for making pr...BACKGROUND Hepatocellular carcinoma(HCC)is the most common primary liver malignancy.Ablation therapy is one of the first-line treatments for early HCC.Accurately predicting early recurrence(ER)is crucial for making precise treatment plans and improving patient prognosis.AIM To establish an intratumoral and peritumoral model for predicting ER in HCC patients following curative ablation.METHODS This study included a total of 288 patients from three Centers.The patients were divided into a primary cohort(n=222)and an external cohort(n=66).Radiomics and deep learning methods were combined for feature extraction,and models were constructed following a three-step feature selection process.Model performance was evaluated using the area under the receiver operating characteristic curve(AUC),while calibration curves and decision curve analysis(DCA)were used to assess calibration and clinical utility.Finally,Kaplan-Meier(K-M)analysis was used to stratify patients according to progression-free survival(PFS)and overall survival(OS).RESULTS The combined model,which utilizes the light gradient boosting machine learning algorithm and incorporates both intratumoral and peritumoral regions(5 mm and 10 mm),demonstrated the best predictive performance for ER following HCC ablation,achieving AUCs of 0.924 in the training set,0.899 in the internal validation set,and 0.839 in the external validation set.Calibration and DCA curves confirmed strong calibration and clinical utility,whereas K-M curves provided risk stratification for PFS and OS in HCC patients.CONCLUSION The most efficient model integrated the tumor region with the peritumoral 5 mm and 10 mm regions.This model provides a noninvasive,effective,and reliable method for predicting ER after curative ablation of HCC.展开更多
BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early pre...BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.展开更多
Interlayer is an important factor affecting the distribution of remaining oil.Accurate identification of interlayer distribution is of great significance in guiding oilfield production and development.However,the trad...Interlayer is an important factor affecting the distribution of remaining oil.Accurate identification of interlayer distribution is of great significance in guiding oilfield production and development.However,the traditional method of identifying interlayers has some limitations:(1)Due to the existence of overlaps in the cross plot for different categories of interlayers,it is difficult to establish a determined model to classify the type of interlayer;(2)Traditional identification methods only use two or three logging curves to identify the types of interlayers,making it difficult to fully utilize the information of the logging curves,the recognition accuracy will be greatly reduced;(3)For a large number of complex logging data,interlayer identification is time-consuming and laborintensive.Based on the existing well area data such as logging data and core data,this paper uses machine learning method to quantitatively identify the interlayers in the single well layer of CIII sandstone group in the M oilfield.Through the comparison of various classifiers,it is found that the decision tree method has the best applicability and the highest accuracy in the study area.Based on single well identification of interlayers,the continuity of well interval interlayers in the study area is analyzed according to the horizontal well.Finally,the influence of the continuity of interlayers on the distribution of remaining oil is verified by the spatial distribution characteristics of interlayers combined with the production situation of the M oilfield.展开更多
Soil fugitive dust(SFD)is characterized by a variety of sources and considerable spatialtemporal variability,exerting a significant impact on environmental air quality and ecological systems in cities across northern ...Soil fugitive dust(SFD)is characterized by a variety of sources and considerable spatialtemporal variability,exerting a significant impact on environmental air quality and ecological systems in cities across northern China.Multiple factors can shape SFD emission.Nevertheless,the current comprehension of its critical impact factors and quantitative methodologies remains constrained.This study utilizes interpretable machine learning techniques to identify the principal impact factors of SFD and their interactions while delineating their action thresholds.The findings reveal seasonal variations in impact factors and emphasize the substantial effect of bare soil source strength on SFD,including parameters such as bare soil area and soil moisture.Consequently,the Wind Erosion Equation model is optimized following these findings to localize its parameters and improve its capability to calculate hourly SFD emissions.The case application is validated using observational data,demonstrating the reliability and precision of the optimized methodology.This study provides insights and solutions for the local optimization of SFD parameterization schemes and further supports the formulation of precise prevention and control policies for SFD.展开更多
Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA metho...Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA method based on deep reinforcement learning which is trained without subjective scores,named DRL-IQA.Inspired by the human visual perception process,our model is formulated as a quality reinforced agent,which consists of the dynamic distortion generation part and the quality perception part.By considering the image distortion degradation process as a sequential decision-making process,the dynamic distortion generation part can develop a strategy to add as many different distortions as possible to an image,which enriches the distortion space to alleviate overfitting.A reward function calculated from quality degradation after adding distortion is utilized to continuously optimize the strategy.Furthermore,the quality perception part can extract rich quality features from the quality degradation process without using subjective scores,and accurately predict the state values that represent the image quality.Experimental results reveal that our method achieves competitive quality prediction performance compared to other state-of-the-art BIQA methods.展开更多
Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surge...Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surgery.This study aimed to develop and validate a computed tomography(CT)-based radiomics and deep learning(DL)fusion model for predicting non-invasive OLNM.Methods:Patients with radiologically node-negative lung adenocarcinoma from two centers were retrospectively analyzed.We developed clinical,radiomics,and radiomics-clinical models using logistic regression.A DL model was established using a three-dimensional squeeze-and-excitation residual network-34(3D SE-ResNet34)and a fusion model was created by integrating seleted clinical,radiomics features and DL features.Model performance was assessed using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve,calibration curves,and decision curve analysis(DCA).Five predictive models were compared;SHapley Additive exPlanations(SHAP)and Gradient-weighted Class Activation Mapping(Grad-CAM)were employed for visualization and interpretation.Results:Overall,358 patients were included:186 in the training cohort,48 in the internal validation cohort,and 124 in the external testing cohort.The DL fusion model incorporating 3D SE-Resnet34 achieved the highest AUC of 0.947 in the training dataset,with strong performance in internal and external cohorts(AUCs of 0.903 and 0.907,respectively),outperforming single-modal DL models,clinical models,radiomics models,and radiomicsclinical combined models(DeLong test:P<0.05).DCA confirmed its clinical utility,and calibration curves demonstrated excellent agreement between predicted and observed OLNM probabilities.Features interpretation highlighted the importance of textural characteristics and the surrounding tumor regions in stratifying OLNM risk.Conclusions:The DL fusion model reliably and accurately predicts OLNM in early-stage lung adenocarcinoma,offering a non-invasive tool to refine staging and guide personalized treatment decisions.These results may aid clinicians in optimizing surgical and radiotherapy strategies.展开更多
Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral method...Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.展开更多
The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicti...The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.展开更多
The lower Yarlung Tsangpo River basin of the Qinghai-Tibet Plateau frequently experiences geo-hazardous occurrences such as landslides,ice/rock avalanches and debris flows,causing loss of human lives and damage to inf...The lower Yarlung Tsangpo River basin of the Qinghai-Tibet Plateau frequently experiences geo-hazardous occurrences such as landslides,ice/rock avalanches and debris flows,causing loss of human lives and damage to infrastructure.However,a comprehensive inventory map of geohazards is lacking for this region,due to the extreme challenges of the geomorphological and environmental conditions(i.e.,steep terrain,dense vegetation cover,and the presence of ice and snow).To this end,we propose a novel approach for mapping active geohazards in complex mountainous regions through InSAR phase gradient measurements based on a deep learning algorithm,which is then applied to the lower Yarlung Tsangpo River basin for the first time,in order to prepare an inventory map of active geohazards using ascending and descending Sentinel-1 SAR images acquired between March 2017 and July 2023.First,the InSAR phase gradient stacking method was introduced to estimate ground deformation,which offers significant advantages in minimizing the influence of InSAR decorrelation and effectively suppressing topographic residuals and atmospheric delays.InSAR phase gradient rates effectively retrieve patterns of localized ground deformation associated with geohazard activity.Then,a DeepLabv3 deep learning model was established and trained with phase gradient rate maps of manually labeled geohazards,in order to achieve the automatic identification of active geohazards.Our results show that there are 277 active geohazards within the lower Yarlung Tsangpo River basin,encompassing an area of~25600 km^(2).The DeepLabv3 model achieved good precision,recall rate and F1 scores at 92,86 and 90%,respectively.The distribution of detected geohazards is closely correlated with the topographic factors,faults and river system.Compared to the results derived from Small Baseline Subset InSAR(SBAS-InSAR)and optical images,the proposed approach can obtain high density pixels of InSAR measurement in low-coherence scenarios,thus enabling high-accuracy mapping of active geohazards in complex mountainous areas.展开更多
PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a l...PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a lack of data,high acquisition costs,andmultiple uncertainties.These limitations hinder the acquisition of comprehensive information on PM_(2.5)chemical composition and effectively implement refined air pollution protection and control strategies.In this study,we developed an optimal deep learning model to acquire hourly mass concentrations of key PM_(2.5)chemical components without complex chemical analysis.The model was trained using a randomly partitioned multivariate dataset arranged in chronological order,including atmospheric state indicators,which previous studies did not consider.Our results showed that the correlation coefficients of key chemical components were no less than 0.96,and the root mean square errors ranged from 0.20 to 2.11μg/m^(3)for the entire process(training and testing combined).The model accurately captured the temporal characteristics of key chemical components,outperforming typical machine-learning models,previous studies,and global reanalysis datasets(such asModern-Era Retrospective analysis for Research and Applications,Version 2(MERRA-2)and Copernicus Atmosphere Monitoring Service ReAnalysis(CAMSRA)).We also quantified the feature importance using the random forest model,which showed that PM_(2.5),PM_(1),visibility,and temperature were the most influential variables for key chemical components.In conclusion,this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data,improved air pollution monitoring and source identification.This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.展开更多
Objective:As an age-related neurodegenerative disease,the prevalence of mild cognitive impairment(MCI)increases with age.Within the framework of traditional Chinese medicine,spleen-kidney deficiency syndrome(SKDS)is r...Objective:As an age-related neurodegenerative disease,the prevalence of mild cognitive impairment(MCI)increases with age.Within the framework of traditional Chinese medicine,spleen-kidney deficiency syndrome(SKDS)is recognized as the most frequent MCI subtype.Due to the covert and gradual onset of MCI,in community settings it poses a significant challenge for patients and their families to discern between typical aging and pathological changes.There exists an urgent need to devise a preliminary diagnostic tool designed for community-residing older adults with MCI attributed to SKDS(MCI-SKDS).Methods:This investigation enrolled 312 elderly individuals diagnosed with MCI,who were randomly distributed into training and test datasets at a 3:1 ratio.Five machine learning methods,including logistic regression(LR),decision tree(DT),naive Bayes(NB),support vector machine(SVM),and gradient boosting(GB),were used to build a diagnostic prediction model for MCI-SKDS.Accuracy,sensitivity,specificity,precision,F1 score,and area under the curve were used to evaluate model performance.Furthermore,the clinical applicability of the model was evaluated through decision curve analysis(DCA).Results:The accuracy,precision,specificity and F1 score of the DT model performed best in the training set(test set),with scores of 0.904(0.845),0.875(0.795),0.973(0.875)and 0.973(0.875).The sensitivity of the training set(test set)of the SVM model performed best among the five models with a score of 0.865(0.821).The area under the curve of all five models was greater than 0.9 for the training dataset and greater than 0.8 for the test dataset.The DCA of all models showed good clinical application value.The study identified ten indicators that were significant predictors of MCI-SKDS.Conclusion:The risk prediction index derived from machine learning for the MCI-SKDS prediction model is simple and practical;the model demonstrates good predictive value and clinical applicability,and the DT model had the best performance.展开更多
基金supported by the Ministry of Science and Technology of China,No.2020AAA0109605(to XL)Meizhou Major Scientific and Technological Innovation PlatformsProjects of Guangdong Provincial Science & Technology Plan Projects,No.2019A0102005(to HW).
文摘Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.
基金supported by the National Natural Science Foundation of China(No.22276139)the Shanghai’s Municipal State-owned Assets Supervision and Administration Commission(No.2022028).
文摘To better understand the migration behavior of plastic fragments in the environment,development of rapid non-destructive methods for in-situ identification and characterization of plastic fragments is necessary.However,most of the studies had focused only on colored plastic fragments,ignoring colorless plastic fragments and the effects of different environmental media(backgrounds),thus underestimating their abundance.To address this issue,the present study used near-infrared spectroscopy to compare the identification of colored and colorless plastic fragments based on partial least squares-discriminant analysis(PLS-DA),extreme gradient boost,support vector machine and random forest classifier.The effects of polymer color,type,thickness,and background on the plastic fragments classification were evaluated.PLS-DA presented the best and most stable outcome,with higher robustness and lower misclassification rate.All models frequently misinterpreted colorless plastic fragments and its background when the fragment thickness was less than 0.1mm.A two-stage modeling method,which first distinguishes the plastic types and then identifies colorless plastic fragments that had been misclassified as background,was proposed.The method presented an accuracy higher than 99%in different backgrounds.In summary,this study developed a novel method for rapid and synchronous identification of colored and colorless plastic fragments under complex environmental backgrounds.
基金Supported by High-Level Chinese Medicine Key Discipline Construction Project,No.zyyzdxk-2023005Capital Health Development Research Project,No.2024-1-2173the National Natural Science Foundation of China,No.82474426 and No.82474419。
文摘BACKGROUND Patients with early-stage hepatocellular carcinoma(HCC)generally have good survival rates following surgical resection.However,a subset of these patients experience recurrence within five years post-surgery.AIM To develop predictive models utilizing machine learning(ML)methods to detect early-stage patients at a high risk of mortality.METHODS Eight hundred and eight patients with HCC at Beijing Ditan Hospital were randomly allocated to training and validation cohorts in a 2:1 ratio.Prognostic models were generated using random survival forests and artificial neural networks(ANNs).These ML models were compared with other classic HCC scoring systems.A decision-tree model was established to validate the contri-bution of immune-inflammatory indicators to the long-term outlook of patients with early-stage HCC.RESULTS Immune-inflammatory markers,albumin-bilirubin scores,alpha-fetoprotein,tumor size,and International Normalized Ratio were closely associated with the 5-year survival rates.Among various predictive models,the ANN model gene-rated using these indicators through ML algorithms exhibited superior perfor-mance,with a 5-year area under the curve(AUC)of 0.85(95%CI:0.82-0.88).In the validation cohort,the 5-year AUC was 0.82(95%CI:0.74-0.85).According to the ANN model,patients were classified into high-risk and low-risk groups,with an overall survival hazard ratio of 7.98(95%CI:5.85-10.93,P<0.0001)between the two cohorts.INTRODUCTION Hepatocellular carcinoma(HCC)is one of the six most prevalent cancers[1]and the third leading cause of cancer-related mortality[2].China has some of the highest incidence and mortality rates for liver cancer,accounting for half of global cases[3,4].The Barcelona Clinic Liver Cancer(BCLC)Staging System is the most widely used framework for diagnosing and treating HCC[5].The optimal candidates for surgical treatment are those with early-stage HCC,classified as BCLC stage 0 or A.Patients with early-stage liver cancer typically have a better prognosis after surgical resection,achieving a 5-year survival rate of 60%-70%[6].However,the high postoperative recurrence rates of HCC remain a major obstacle to long-term efficacy.To improve the prognosis of patients with early-stage HCC,it is necessary to develop models that can identify those with poor prognoses,enabling stratified and personalized treatment and follow-up strategies.Chronic inflammation is linked to the development and advancement of tumors[7].Recently,peripheral blood immune indicators,such as neutrophil-to-lymphocyte ratio(NLR),platelet-to-lymphocyte ratio(PLR),and lymphocyte-to-monocyte ratio(LMR),have garnered extensive attention and have been used to predict survival in various tumors and inflammation-related diseases[8-10].However,the relationship between these combinations of immune markers and the outcomes in patients with early-stage HCC require further investigation.Machine learning(ML)algorithms are capable of handling large and complex datasets,generating more accurate and personalized predictions through unique training algorithms that better manage nonlinear statistical relationships than traditional analytical methods.Commonly used ML models include artificial neural networks(ANNs)and random survival forests(RSFs),which have shown satisfactory accuracy in prognostic predictions across various cancers and other diseases[11-13].ANNs have performed well in identifying the progression from liver cirrhosis to HCC and predicting overall survival(OS)in patients with HCC[14,15].However,no studies have confirmed the ability of ML models to predict post-surgical survival in patients with early-stage HCC.Through ML,a better understanding of the risk factors for early-stage HCC prognosis can be achieved.This aids in surgical decision-making,identifying patients at a high risk of mortality,and selecting subsequent treatment strategies.In this study,we aimed to establish a 5-year prognostic model for patients with early-stage HCC after surgical resection,based on ML and systemic immune-inflammatory indicators.This model seeks to improve the early monitoring of high-risk patients and provide personalized treatment plans.
文摘Breast cancer is among the leading causes of cancer mortality globally,and its diagnosis through histopathological image analysis is often prone to inter-observer variability and misclassification.Existing machine learning(ML)methods struggle with intra-class heterogeneity and inter-class similarity,necessitating more robust classification models.This study presents an ML classifier ensemble hybrid model for deep feature extraction with deep learning(DL)and Bat Swarm Optimization(BSO)hyperparameter optimization to improve breast cancer histopathology(BCH)image classification.A dataset of 804 Hematoxylin and Eosin(H&E)stained images classified as Benign,in situ,Invasive,and Normal categories(ICIAR2018_BACH_Challenge)has been utilized.ResNet50 was utilized for feature extraction,while Support Vector Machines(SVM),Random Forests(RF),XGBoosts(XGB),Decision Trees(DT),and AdaBoosts(ADB)were utilized for classification.BSO was utilized for hyperparameter optimization in a soft voting ensemble approach.Accuracy,precision,recall,specificity,F1-score,Receiver Operating Characteristic(ROC),and Precision-Recall(PR)were utilized for model performance metrics.The model using an ensemble outperformed individual classifiers in terms of having greater accuracy(~90.0%),precision(~86.4%),recall(~86.3%),and specificity(~96.6%).The robustness of the model was verified by both ROC and PR curves,which showed AUC values of 1.00,0.99,and 0.98 for Benign,Invasive,and in situ instances,respectively.This ensemble model delivers a strong and clinically valid methodology for breast cancer classification that enhances precision and minimizes diagnostic errors.Future work should focus on explainable AI,multi-modal fusion,few-shot learning,and edge computing for real-world deployment.
基金funded in part by Grant No.DF-091-135-1441 from the Deanship of Scientific Research(DSR)at King Abdulaziz University in Saudi Arabia.
文摘In this paper,we propose STPLF,which stands for the short-term forecasting of locational marginal price components,including the forecasting of non-conforming hourly net loads.The volatility of transmission-level hourly locational marginal prices(LMPs)is caused by several factors,including weather data,hourly gas prices,historical hourly loads,and market prices.In addition,variations of non-conforming net loads,which are affected by behind-the-meter distributed energy resources(DERs)and retail customer loads,could have a major impact on the volatility of hourly LMPs,as bulk grid operators have limited visibility of such retail-level resources.We propose a fusion forecasting model for the STPLF,which uses machine learning and deep learning methods to forecast non-conforming loads and respective hourly prices.Additionally,data preprocessing and feature extraction are used to increase the accuracy of the STPLF.The proposed STPLF model also includes a post-processing stage for calculating the probability of hourly LMP spikes.We use a practical set of data to analyze the STPLF results and validate the proposed probabilistic method for calculating the LMP spikes.
基金funded by Scientific Research Deanship at University of Ha’il,Saudi Arabia,through project number GR-24009.
文摘Hepatitis is an infection that affects the liver through contaminated foods or blood transfusions,and it has many types,from normal to serious.Hepatitis is diagnosed through many blood tests and factors;Artificial Intelligence(AI)techniques have played an important role in early diagnosis and help physicians make decisions.This study evaluated the performance of Machine Learning(ML)algorithms on the hepatitis data set.The dataset contains missing values that have been processed and outliers removed.The dataset was counterbalanced by the Synthetic Minority Over-sampling Technique(SMOTE).The features of the data set were processed in two ways:first,the application of the Recursive Feature Elimination(RFE)algorithm to arrange the percentage of contribution of each feature to the diagnosis of hepatitis,then selection of important features using the t-distributed Stochastic Neighbor Embedding(t-SNE)and Principal Component Analysis(PCA)algorithms.Second,the SelectKBest function was applied to give scores for each attribute,followed by the t-SNE and PCA algorithms.Finally,the classification algorithms K-Nearest Neighbors(KNN),Support Vector Machine(SVM),Artificial Neural Network(ANN),Decision Tree(DT),and Random Forest(RF)were fed by the dataset after processing the features in different methods are RFE with t-SNE and PCA and SelectKBest with t-SNE and PCA).All algorithms yielded promising results for diagnosing hepatitis data sets.The RF with RFE and PCA methods achieved accuracy,Precision,Recall,and AUC of 97.18%,96.72%,97.29%,and 94.2%,respectively,during the training phase.During the testing phase,it reached accuracy,Precision,Recall,and AUC by 96.31%,95.23%,97.11%,and 92.67%,respectively.
基金supported in part by Guangdong Basic and Applied Basic Research Foundation under Grant 2024A1515012485in part by Shenzhen Fundamental Research Program under Grant JCYJ20220810112354002+4 种基金in part by Shenzhen Science and Technology Program under Grant KJZD20230923114111021in part by the Fund for Academic Innovation Teams and Research Platform of South-Central Minzu University under Grant XTZ24003 and Grant PTZ24001in part by the Knowledge Innovation Program of Wuhan-Basic Research through Project 2023010201010151in part by the Research Start-up Funds of South-Central Minzu University under Grant YZZ18006in part by the Spring Sunshine Program of Ministry of Education of the People’s Republic of China under Grant HZKY20220331.
文摘Introduction Deep learning(DL),as one of the most transformative technologies in artificial intelligence(AI),is undergoing a pivotal transition from laboratory research to industrial deployment.Advancing at an unprecedented pace,DL is transcending theoretical and application boundaries to penetrate emerging realworld scenarios such as industrial automation,urban management,and health monitoring,thereby driving a new wave of intelligent transformation.In August 2023,Goldman Sachs estimated that global AI investment will reach US$200 billion by 2025[1].However,the increasing complexity and dynamic nature of application scenarios expose critical challenges in traditional deep learning,including data heterogeneity,insufficient model generalization,computational resource constraints,and privacy-security trade-offs.The next generation of deep learning methodologies needs to achieve breakthroughs in multimodal fusion,lightweight design,interpretability enhancement,and cross-disciplinary collaborative optimization,in order to develop more efficient,robust,and practically valuable intelligent systems.
基金Supported by National Natural Science Foundation of China(Grant No.61803206)Jiangsu Provincial Natural Science Foundation(Grant No.222300420468)Jiangsu Provincial key R&D Program(Grant No.BE2017008-2).
文摘Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents,reducing the traffic efficiency of intelligent vehicles.The complex road traffic environment of smart vehicles and other vehicles frequently experiences conflicting start and stop motion.The fine-grained scheduling of autonomous vehicles(AVs)at non-signalized intersections,which is a promising technique for exploring optimal driving paths for both assisted driving nowadays and driverless cars in the near future,has attracted significant attention owing to its high potential for improving road safety and traffic efficiency.Fine-grained scheduling primarily focuses on signalized intersection scenarios,as applying it directly to non-signalized intersections is challenging because each AV can move freely without traffic signal control.This may cause frequent driving collisions and low road traffic efficiency.Therefore,this study proposes a novel algorithm to address this issue.Our work focuses on the fine-grained scheduling of automated vehicles at non-signal intersections via dual reinforced training(FS-DRL).For FS-DRL,we first use a grid to describe the non-signalized intersection and propose a convolutional neural network(CNN)-based fast decision model that can rapidly yield a coarse-grained scheduling decision for each AV in a distributed manner.We then load these coarse-grained scheduling decisions onto a deep Q-learning network(DQN)for further evaluation.We use an adaptive learning rate to maximize the reward function and employ parameterεto tradeoff the fast speed of coarse-grained scheduling in the CNN and optimal fine-grained scheduling in the DQN.In addition,we prove that using this adaptive learning rate leads to a converged loss rate with an extremely small number of training loops.The simulation results show that compared with Dijkstra,RNN,and ant colony-based scheduling,FS-DRL yields a high accuracy of 96.5%on the sample,with improved performance of approximately 61.54%-85.37%in terms of the average conflict and traffic efficiency.
基金Supported by the Guangxi Zhuang Autonomous Region Health Commission Scientific Research Project,No.Z-A20220465Guangxi Key R and D Plan,No.AB20297021+2 种基金Guangxi Medical and Health Appropriate Technology Development and Promotion Application Project,No.S2022107China Undergraduate Innovation and Entrepreneurship Training Program,No.S202310598074Future Academic Star of Guangxi Medical University,No.WLXSZX23109.
文摘BACKGROUND Early screening methods for gastric cancer(GC)are lacking;therefore,the disease often progresses to an advanced stage when patients first start to exhibit typical symptoms.Endoscopy and pathological biopsy remain the primary diagnostic approaches,but they are invasive and not yet widely applicable for early popu-lation screening.miRNA is a highly conserved type of RNA that exists stably in plasma.Dysfunction of miRNA is linked to tumorigenesis and progression,indicating that individual miRNAs or combinations of multiple miRNAs may serve as potential biomarkers.AIM To identify effective plasma miRNA biomarkers and investigate the clinical value of combining multiple miRNAs for early detection of GC.METHODS Plasma samples from multiple centres were collected.Differentially expressed genes among healthy controls,early-stage GC patients,and advanced-stage GC patients were identified through small RNA sequencing(sRNA-seq)and validated via real-time quantitative reverse transcription polymerase chain reaction(RT-qPCR).A Wilcoxon signed-rank test was used to investigate the differences in miRNAs.Sequencing datasets of GC serum samples were retrieved from the Gene Expression Omnibus(GEO),ArrayExpress,and The Cancer Genome Atlas databases,and a multilayer perceptron-artificial neural network(MLP-ANN)model was constructed for the key risk miRNAs.The pROC package was used to assess the discriminatory efficacy of the model.RESULTS Plasma samples of 107 normal,71 early GC and 97 advanced GC patients were obtained from three centres,and serum samples of 8443 normal and 1583 GC patients were obtained from the GEO database.The sRNA-seq and RT-qPCR experiments revealed that miR-452-5p,miR-5010-5p,miR-27b-5p,miR-5189-5p,miR-552-5p and miR-199b-5p were significantly increased in early GC patients compared with healthy controls and in advanced GC patients compared with early GC patients(P<0.05).An MLP-ANN model was constructed for the six key miRNAs.The area under the curve(AUC)within the training cohort was 0.983[95% confidence interval(CI):0.980–0.986].In the two validation cohorts,the AUCs were 0.995(95%CI:0.987 to nearly 1.000)and 0.979(95%CI:0.972–0.986),respectively.CONCLUSION Potential miRNA biomarkers,including miR-452-5p,miR-5010-5p,miR-27b-5p,miR-5189-5p,miR-552-5p and miR-199b-5p,were identified.A GC classifier based on these miRNAs was developed,benefiting early detection and population screening.
基金Supported by Anhui Provincial Key Research and Development Plan,No.202104j07020048.
文摘BACKGROUND Hepatocellular carcinoma(HCC)is the most common primary liver malignancy.Ablation therapy is one of the first-line treatments for early HCC.Accurately predicting early recurrence(ER)is crucial for making precise treatment plans and improving patient prognosis.AIM To establish an intratumoral and peritumoral model for predicting ER in HCC patients following curative ablation.METHODS This study included a total of 288 patients from three Centers.The patients were divided into a primary cohort(n=222)and an external cohort(n=66).Radiomics and deep learning methods were combined for feature extraction,and models were constructed following a three-step feature selection process.Model performance was evaluated using the area under the receiver operating characteristic curve(AUC),while calibration curves and decision curve analysis(DCA)were used to assess calibration and clinical utility.Finally,Kaplan-Meier(K-M)analysis was used to stratify patients according to progression-free survival(PFS)and overall survival(OS).RESULTS The combined model,which utilizes the light gradient boosting machine learning algorithm and incorporates both intratumoral and peritumoral regions(5 mm and 10 mm),demonstrated the best predictive performance for ER following HCC ablation,achieving AUCs of 0.924 in the training set,0.899 in the internal validation set,and 0.839 in the external validation set.Calibration and DCA curves confirmed strong calibration and clinical utility,whereas K-M curves provided risk stratification for PFS and OS in HCC patients.CONCLUSION The most efficient model integrated the tumor region with the peritumoral 5 mm and 10 mm regions.This model provides a noninvasive,effective,and reliable method for predicting ER after curative ablation of HCC.
基金Applicable Funding Source University of Science and Technology of China(to YLL)National Natural Science Foundation of China(12126604)(to MPZ)+1 种基金R&D project of Pazhou Lab(Huangpu)(2023K0609)(to MPZ)Anhui Provincial Natural Science(grant number 2208085MH235)(to KJ)。
文摘BACKGROUND:Rapid and accurate identification of high-risk patients in the emergency departments(EDs)is crucial for optimizing resource allocation and improving patient outcomes.This study aimed to develop an early prediction model for identifying high-risk patients in EDs using initial vital sign measurements.METHODS:This retrospective cohort study analyzed initial vital signs from the Chinese Emergency Triage,Assessment,and Treatment(CETAT)database,which was collected between January 1^(st),2020,and June 25^(th),2023.The primary outcome was the identification of high-risk patients needing immediate treatment.Various machine learning methods,including a deep-learningbased multilayer perceptron(MLP)classifier were evaluated.Model performance was assessed using the area under the receiver operating characteristic curve(AUC-ROC).AUC-ROC values were reported for three scenarios:a default case,a scenario requiring sensitivity greater than 0.8(Scenario I),and a scenario requiring specificity greater than 0.8(Scenario II).SHAP values were calculated to determine the importance of each predictor within the MLP model.RESULTS:A total of 38,797 patients were analyzed,of whom 18.2%were identified as high-risk.Comparative analysis of the predictive models for high-risk patients showed AUC-ROC values ranging from 0.717 to 0.738,with the MLP model outperforming logistic regression(LR),Gaussian Naive Bayes(GNB),and the National Early Warning Score(NEWS).SHAP value analysis identified coma state,peripheral capillary oxygen saturation(SpO_(2)),and systolic blood pressure as the top three predictive factors in the MLP model,with coma state exerting the most contribution.CONCLUSION:Compared with other methods,the MLP model with initial vital signs demonstrated optimal prediction accuracy,highlighting its potential to enhance clinical decision-making in triage in the EDs.
基金supported by the Natural Science Basic Research Program of Shaanxi(2024JC-YBMS-202).
文摘Interlayer is an important factor affecting the distribution of remaining oil.Accurate identification of interlayer distribution is of great significance in guiding oilfield production and development.However,the traditional method of identifying interlayers has some limitations:(1)Due to the existence of overlaps in the cross plot for different categories of interlayers,it is difficult to establish a determined model to classify the type of interlayer;(2)Traditional identification methods only use two or three logging curves to identify the types of interlayers,making it difficult to fully utilize the information of the logging curves,the recognition accuracy will be greatly reduced;(3)For a large number of complex logging data,interlayer identification is time-consuming and laborintensive.Based on the existing well area data such as logging data and core data,this paper uses machine learning method to quantitatively identify the interlayers in the single well layer of CIII sandstone group in the M oilfield.Through the comparison of various classifiers,it is found that the decision tree method has the best applicability and the highest accuracy in the study area.Based on single well identification of interlayers,the continuity of well interval interlayers in the study area is analyzed according to the horizontal well.Finally,the influence of the continuity of interlayers on the distribution of remaining oil is verified by the spatial distribution characteristics of interlayers combined with the production situation of the M oilfield.
基金supported by the General Program of National Natural Science Foundation of China(No.42275190)。
文摘Soil fugitive dust(SFD)is characterized by a variety of sources and considerable spatialtemporal variability,exerting a significant impact on environmental air quality and ecological systems in cities across northern China.Multiple factors can shape SFD emission.Nevertheless,the current comprehension of its critical impact factors and quantitative methodologies remains constrained.This study utilizes interpretable machine learning techniques to identify the principal impact factors of SFD and their interactions while delineating their action thresholds.The findings reveal seasonal variations in impact factors and emphasize the substantial effect of bare soil source strength on SFD,including parameters such as bare soil area and soil moisture.Consequently,the Wind Erosion Equation model is optimized following these findings to localize its parameters and improve its capability to calculate hourly SFD emissions.The case application is validated using observational data,demonstrating the reliability and precision of the optimized methodology.This study provides insights and solutions for the local optimization of SFD parameterization schemes and further supports the formulation of precise prevention and control policies for SFD.
基金supported by the Fundamental Research Funds for the Central Universities.
文摘Most blind image quality assessment(BIQA)methods require a large amount of time to collect human opinion scores as training labels,which limits their usability in practice.Thus,we present an opinion-unaware BIQA method based on deep reinforcement learning which is trained without subjective scores,named DRL-IQA.Inspired by the human visual perception process,our model is formulated as a quality reinforced agent,which consists of the dynamic distortion generation part and the quality perception part.By considering the image distortion degradation process as a sequential decision-making process,the dynamic distortion generation part can develop a strategy to add as many different distortions as possible to an image,which enriches the distortion space to alleviate overfitting.A reward function calculated from quality degradation after adding distortion is utilized to continuously optimize the strategy.Furthermore,the quality perception part can extract rich quality features from the quality degradation process without using subjective scores,and accurately predict the state values that represent the image quality.Experimental results reveal that our method achieves competitive quality prediction performance compared to other state-of-the-art BIQA methods.
基金supported by the National Natural Science Foundation of China(No.82272845)the Natural Science Foundation of Shandong(No.ZR2023ZD26).
文摘Objective:The neglect of occult lymph nodes metastasis(OLNM)is one of the pivotal causes of early non-small cell lung cancer(NSCLC)recurrence after local treatments such as stereotactic body radiotherapy(SBRT)or surgery.This study aimed to develop and validate a computed tomography(CT)-based radiomics and deep learning(DL)fusion model for predicting non-invasive OLNM.Methods:Patients with radiologically node-negative lung adenocarcinoma from two centers were retrospectively analyzed.We developed clinical,radiomics,and radiomics-clinical models using logistic regression.A DL model was established using a three-dimensional squeeze-and-excitation residual network-34(3D SE-ResNet34)and a fusion model was created by integrating seleted clinical,radiomics features and DL features.Model performance was assessed using the area under the curve(AUC)of the receiver operating characteristic(ROC)curve,calibration curves,and decision curve analysis(DCA).Five predictive models were compared;SHapley Additive exPlanations(SHAP)and Gradient-weighted Class Activation Mapping(Grad-CAM)were employed for visualization and interpretation.Results:Overall,358 patients were included:186 in the training cohort,48 in the internal validation cohort,and 124 in the external testing cohort.The DL fusion model incorporating 3D SE-Resnet34 achieved the highest AUC of 0.947 in the training dataset,with strong performance in internal and external cohorts(AUCs of 0.903 and 0.907,respectively),outperforming single-modal DL models,clinical models,radiomics models,and radiomicsclinical combined models(DeLong test:P<0.05).DCA confirmed its clinical utility,and calibration curves demonstrated excellent agreement between predicted and observed OLNM probabilities.Features interpretation highlighted the importance of textural characteristics and the surrounding tumor regions in stratifying OLNM risk.Conclusions:The DL fusion model reliably and accurately predicts OLNM in early-stage lung adenocarcinoma,offering a non-invasive tool to refine staging and guide personalized treatment decisions.These results may aid clinicians in optimizing surgical and radiotherapy strategies.
基金supported by grants from the National Key Research and Development Program of China(2023YFF0724902)the China Postdoctoral Science Foundation(2020?M670027,2023TQ0183)the Local Standards Research of BeiJing Laboratory Tree Shrew(CHYX-2023-DGB001)。
文摘Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.
基金supported in part by the Science and Technology Department of Sichuan Province(No.2025ZNSFSC0427,No.2024ZDZX0035)the Open Project Fund of Vehicle Measurement,Control and Safety Key Laboratory of Sichuan Province(No.QCCK2024-004)the Industrial and Educational Integration Project of Yibin(No.YB-XHU-20240001)。
文摘The accurate prediction of battery pack capacity in electric vehicles(EVs)is crucial for ensuring safety and optimizing performance.Despite extensive research on predicting cell capacity using laboratory data,predicting the capacity of onboard battery packs from field data remains challenging due to complex operating conditions and irregular EV usage in real-world settings.Most existing methods rely on extracting health feature parameters from raw data for capacity prediction of onboard battery packs,however,selecting specific parameters often results in a loss of critical information,which reduces prediction accuracy.To this end,this paper introduces a novel framework combining deep learning and data compression techniques to accurately predict battery pack capacity onboard.The proposed data compression method converts monthly EV charging data into feature maps,which preserve essential data characteristics while reducing the volume of raw data.To address missing capacity labels in field data,a capacity labeling method is proposed,which calculates monthly battery capacity by transforming the ampere-hour integration formula and applying linear regression.Subsequently,a deep learning model is proposed to build a capacity prediction model,using feature maps from historical months to predict the battery capacity of future months,thus facilitating accurate forecasts.The proposed framework,evaluated using field data from 20 EVs,achieves a mean absolute error of 0.79 Ah,a mean absolute percentage error of 0.65%,and a root mean square error of 1.02 Ah,highlighting its potential for real-world EV applications.
基金financially supported by the Joint Funds of the National Natural Science Foundation of China(Grant No.U2244226)the National Key R&D Program of China(No.2022YFC3004302)+7 种基金Chinese Geological Survey Project(No.DD20230538)the Science Foundation of Gansu Province(No.23JRRA830)the Science and Technology Major Project of Gansu Province(No.23ZDFA007)the Foundation for Innovation Groups of Basic Research in Gansu Province(24JRRA169)Power China Project(No.CD2C20230228)the Lanzhou Youth Science and Technology Talent Innovation Project(No.2024-QN-170)supported by the ESA-MOST China DRAGON-5(Grant No.59339)DRAGON-6 project(Grant No.95355).
文摘The lower Yarlung Tsangpo River basin of the Qinghai-Tibet Plateau frequently experiences geo-hazardous occurrences such as landslides,ice/rock avalanches and debris flows,causing loss of human lives and damage to infrastructure.However,a comprehensive inventory map of geohazards is lacking for this region,due to the extreme challenges of the geomorphological and environmental conditions(i.e.,steep terrain,dense vegetation cover,and the presence of ice and snow).To this end,we propose a novel approach for mapping active geohazards in complex mountainous regions through InSAR phase gradient measurements based on a deep learning algorithm,which is then applied to the lower Yarlung Tsangpo River basin for the first time,in order to prepare an inventory map of active geohazards using ascending and descending Sentinel-1 SAR images acquired between March 2017 and July 2023.First,the InSAR phase gradient stacking method was introduced to estimate ground deformation,which offers significant advantages in minimizing the influence of InSAR decorrelation and effectively suppressing topographic residuals and atmospheric delays.InSAR phase gradient rates effectively retrieve patterns of localized ground deformation associated with geohazard activity.Then,a DeepLabv3 deep learning model was established and trained with phase gradient rate maps of manually labeled geohazards,in order to achieve the automatic identification of active geohazards.Our results show that there are 277 active geohazards within the lower Yarlung Tsangpo River basin,encompassing an area of~25600 km^(2).The DeepLabv3 model achieved good precision,recall rate and F1 scores at 92,86 and 90%,respectively.The distribution of detected geohazards is closely correlated with the topographic factors,faults and river system.Compared to the results derived from Small Baseline Subset InSAR(SBAS-InSAR)and optical images,the proposed approach can obtain high density pixels of InSAR measurement in low-coherence scenarios,thus enabling high-accuracy mapping of active geohazards in complex mountainous areas.
基金supported by the National Key Research and Development Program for Young Scientists of China(No.2022YFC3704000)the National Natural Science Foundation of China(No.42275122)the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab).
文摘PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a lack of data,high acquisition costs,andmultiple uncertainties.These limitations hinder the acquisition of comprehensive information on PM_(2.5)chemical composition and effectively implement refined air pollution protection and control strategies.In this study,we developed an optimal deep learning model to acquire hourly mass concentrations of key PM_(2.5)chemical components without complex chemical analysis.The model was trained using a randomly partitioned multivariate dataset arranged in chronological order,including atmospheric state indicators,which previous studies did not consider.Our results showed that the correlation coefficients of key chemical components were no less than 0.96,and the root mean square errors ranged from 0.20 to 2.11μg/m^(3)for the entire process(training and testing combined).The model accurately captured the temporal characteristics of key chemical components,outperforming typical machine-learning models,previous studies,and global reanalysis datasets(such asModern-Era Retrospective analysis for Research and Applications,Version 2(MERRA-2)and Copernicus Atmosphere Monitoring Service ReAnalysis(CAMSRA)).We also quantified the feature importance using the random forest model,which showed that PM_(2.5),PM_(1),visibility,and temperature were the most influential variables for key chemical components.In conclusion,this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data,improved air pollution monitoring and source identification.This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.
基金funded by the National Natural Science Foundation of China(No.82405530,81973921 and 72374068)the Science and Technology Research Project of Hubei Provincial Department of Education(No.B2023098)。
文摘Objective:As an age-related neurodegenerative disease,the prevalence of mild cognitive impairment(MCI)increases with age.Within the framework of traditional Chinese medicine,spleen-kidney deficiency syndrome(SKDS)is recognized as the most frequent MCI subtype.Due to the covert and gradual onset of MCI,in community settings it poses a significant challenge for patients and their families to discern between typical aging and pathological changes.There exists an urgent need to devise a preliminary diagnostic tool designed for community-residing older adults with MCI attributed to SKDS(MCI-SKDS).Methods:This investigation enrolled 312 elderly individuals diagnosed with MCI,who were randomly distributed into training and test datasets at a 3:1 ratio.Five machine learning methods,including logistic regression(LR),decision tree(DT),naive Bayes(NB),support vector machine(SVM),and gradient boosting(GB),were used to build a diagnostic prediction model for MCI-SKDS.Accuracy,sensitivity,specificity,precision,F1 score,and area under the curve were used to evaluate model performance.Furthermore,the clinical applicability of the model was evaluated through decision curve analysis(DCA).Results:The accuracy,precision,specificity and F1 score of the DT model performed best in the training set(test set),with scores of 0.904(0.845),0.875(0.795),0.973(0.875)and 0.973(0.875).The sensitivity of the training set(test set)of the SVM model performed best among the five models with a score of 0.865(0.821).The area under the curve of all five models was greater than 0.9 for the training dataset and greater than 0.8 for the test dataset.The DCA of all models showed good clinical application value.The study identified ten indicators that were significant predictors of MCI-SKDS.Conclusion:The risk prediction index derived from machine learning for the MCI-SKDS prediction model is simple and practical;the model demonstrates good predictive value and clinical applicability,and the DT model had the best performance.
