Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying clima...Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying climatic conditions.This study presents a scale separation hybrid statistical model with recurrent neural network(SS-RNN)to predict the summer monthly NEC-PR.The SS-RNN model decomposes the multiple scales of the NEC-PR into several spatiotemporal intrinsic mode functions covering annual to decadal time scales.This strategy provides a way to derive appropriate predictors and establish predictive models for the primary spatial modes of the NEC-PR at various time scales.Our results demonstrate substantial improvements by the SS-RNN model in predicting the summer monthly NEC-PR as compared with dynamic models,particularly in predicting the spatial pattern of the NEC-PR.In this paper we take August,the month of the highest NEC-PR,to assess our model skill.Independent forecasts of the August NEC-PR over the period 2021–24 achieve significant spatial anomaly correlation coefficients,reaching a maximum value of 0.83.Additional verifications by station observations show that the model hits most station anomalies,achieving a mean predictive skill score of 90.展开更多
BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suita...BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suitable for rapid clinical application.METHODS:In this multi-center retrospective cohort study,AAS patient data from three hospitals were analyzed.The modeling cohort included data from the First Affiliated Hospital of Zhengzhou University and the People’s Hospital of Xinjiang Uygur Autonomous Region,with Peking University Third Hospital data serving as the external test set.Four machine learning algorithms—logistic regression(LR),multilayer perceptron(MLP),Gaussian naive Bayes(GNB),and random forest(RF)—were used to develop predictive models based on 34 early-accessible clinical variables.A simplifi ed model was then derived based on fi ve key variables(Stanford type,pericardial eff usion,asymmetric peripheral arterial pulsation,decreased bowel sounds,and dyspnea)via Least Absolute Shrinkage and Selection Operator(LASSO)regression to improve ED applicability.RESULTS:A total of 929 patients were included in the modeling cohort,and 210 were included in the external test set.Four machine learning models based on 34 clinical variables were developed,achieving internal and external validation AUCs of 0.85-0.90 and 0.73-0.85,respectively.The simplifi ed model incorporating fi ve key variables demonstrated internal and external validation AUCs of 0.71-0.86 and 0.75-0.78,respectively.Both models showed robust calibration and predictive stability across datasets.CONCLUSION:Both kinds of models were built based on machine learning tools,and proved to have certain prediction performance and extrapolation.展开更多
Hydrological extremes,such as floods,droughts,and compound events,are extremely dangerous to human societies,ecosystems,and infrastructures,whose frequency and severity are affected by climate change more and more.Eff...Hydrological extremes,such as floods,droughts,and compound events,are extremely dangerous to human societies,ecosystems,and infrastructures,whose frequency and severity are affected by climate change more and more.Effective disaster preparedness,water resource management,and climate adaptation have to do with accurate prediction and extensive risk assessment.This review sums up recent progress in predictive modeling and risk assessment systems in the framework of hydrological extremes in the changing climatic conditions.Statistical and empirical techniques,including extreme value theory and nonstationary frequency analysis,give probabilistic information using historic records,whereas process-based models give an understanding of physical hydrological processes at different climate and land-use conditions.New information-based and hybrid methods that use machine learning and high-resolution data take advantage of the complexity and nonlinearities and enhance the predictive power.Hazard,exposure,vulnerability,and adaptive capacity risk assessment models allow predictive output to be translated into actionable decision support,with socio-economic aspects and analysis of the scenario.Case studies of various regions across the globe show the use of these techniques to address floods,droughts,and compound events,with success and current problems.The review also addresses current trends such as compound hazard,multi-hazard integration,AI-enabled modelling,and cross-sectoral decision support,and outlines research priorities of improving predictive capability and resilience.This review will inform researchers,policymakers,and practitioners by offering a synthesis of all the effects of the hydrological extremes in climate change to formulate sound strategies for alleviating these effects.展开更多
In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method n...In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method named RFR-WOA is developed based on random forest regression(RFR)and whale optimization algorithm(WOA).Firstly,using Pearson and Spearman correlation analysis and Gini coefficient importance ranking on an actual production dataset containing 37,878 samples,22 key variables are selected as model inputs from 112 variables that affect mechanical properties.Subsequently,an RFR-based predictive model for the mechanical properties of cold-rolled strip steel is constructed.Then,with the combination of the coefficient of determination(R^(2))and root mean square error as the optimization objective,the hyperparameters of RFR model are iteratively optimized using WOA,and better predictive effectiveness is obtained.Finally,the mechanical properties prediction model based on RFR-WOA is compared with models established using deep neural networks,convolutional neural networks,and other methods.The test results on 9469 samples of actual production data show that the model developed present has better predictive accuracy and generalization capability.展开更多
To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the stre...To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the strength and elastic modulus of mortar and concrete prepared with mechanism aggregates of the corresponding lithology,and the stress-strain curves of concrete were investigated.In this paper,a coarse aggregate and mortar matrix bonding assumption is proposed,and a prediction model for the elastic modulus of mortar is established by considering the lithology of the mechanism sand and the slurry components.An equivalent coarse aggregate elastic modulus model was established by considering factors such as coarse aggregate particle size,volume fraction,and mortar thickness between coarse aggregates.Based on the elastic modulus of the equivalent coarse aggregate and the remaining mortar,a prediction model for the elastic modulus of the two and three components of concrete in series and then in parallel was established,and the predicted values differed from the measured values within 10%.It is proposed that the coarse aggregate elastic modulus in highstrength concrete is the most critical factor affecting the elastic modulus of concrete,and as the coarse aggregate elastic modulus increases by 27.7%,the concrete elastic modulus increases by 19.5%.展开更多
BACKGROUND Colorectal polyps are precancerous diseases of colorectal cancer.Early detection and resection of colorectal polyps can effectively reduce the mortality of colorectal cancer.Endoscopic mucosal resection(EMR...BACKGROUND Colorectal polyps are precancerous diseases of colorectal cancer.Early detection and resection of colorectal polyps can effectively reduce the mortality of colorectal cancer.Endoscopic mucosal resection(EMR)is a common polypectomy proce-dure in clinical practice,but it has a high postoperative recurrence rate.Currently,there is no predictive model for the recurrence of colorectal polyps after EMR.AIM To construct and validate a machine learning(ML)model for predicting the risk of colorectal polyp recurrence one year after EMR.METHODS This study retrospectively collected data from 1694 patients at three medical centers in Xuzhou.Additionally,a total of 166 patients were collected to form a prospective validation set.Feature variable screening was conducted using uni-variate and multivariate logistic regression analyses,and five ML algorithms were used to construct the predictive models.The optimal models were evaluated based on different performance metrics.Decision curve analysis(DCA)and SHapley Additive exPlanation(SHAP)analysis were performed to assess clinical applicability and predictor importance.RESULTS Multivariate logistic regression analysis identified 8 independent risk factors for colorectal polyp recurrence one year after EMR(P<0.05).Among the models,eXtreme Gradient Boosting(XGBoost)demonstrated the highest area under the curve(AUC)in the training set,internal validation set,and prospective validation set,with AUCs of 0.909(95%CI:0.89-0.92),0.921(95%CI:0.90-0.94),and 0.963(95%CI:0.94-0.99),respectively.DCA indicated favorable clinical utility for the XGBoost model.SHAP analysis identified smoking history,family history,and age as the top three most important predictors in the model.CONCLUSION The XGBoost model has the best predictive performance and can assist clinicians in providing individualized colonoscopy follow-up recommendations.展开更多
BACKGROUND Patients harboring gene mutations like KRAS,NRAS,and BRAF demonstrate highly variable responses to chemotherapy,posing challenges for treatment optimization.Multiparametric magnetic resonance imaging(MRI),w...BACKGROUND Patients harboring gene mutations like KRAS,NRAS,and BRAF demonstrate highly variable responses to chemotherapy,posing challenges for treatment optimization.Multiparametric magnetic resonance imaging(MRI),with its noninvasive capability to assess tumor characteristics in detail,has shown promise in evaluating treatment response and predicting therapeutic outcomes.This technology holds potential for guiding personalized treatment strategies tailored to individual patient profiles,enhancing the precision and effectiveness of colorectal cancer care.AIM To create a multiparametric MRI-based predictive model for assessing chemotherapy efficacy in colorectal cancer patients with gene mutations.METHODS This retrospective study was conducted in a tertiary hospital,analyzing 157 colorectal cancer patients with gene mutations treated between August 2022 and December 2023.Based on chemotherapy outcomes,the patients were categorized into favorable(n=60)and unfavorable(n=50)response groups.Univariate and multivariate logistic regression analyses were performed to identify independent predictors of chemotherapy efficacy.A predictive nomogram was constructed using significant variables,and its performance was assessed using the area under the receiver operating characteristic curve(AUC)in both training and validation sets.RESULTS Univariate analysis identified that tumor differentiation,T2 signal intensity ratio,tumor-to-anal margin distance,and MRI-detected lymph node metastasis as significantly associated with chemotherapy response(P<0.05).Multivariate Logistics regression confirmed these four parameters as independent predictors.The predictive model demonstrated strong discrimination,with an AUC of 0.938(sensitivity:86%;specificity:92%)in the training set,and 0.942(sensitivity:100%;specificity:83%)in the validation set.CONCLUSION We established and validated a multiparametric MRI-based model for predicting chemotherapy response in colorectal cancer patients with gene mutations.This model holds promise for guiding individualized treatment strategies.展开更多
Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and sub...Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and subsurface damage depth(SDD)are crucial indicators for evaluating the surface quality of these materials after grinding.Existing prediction models lack general applicability and do not accurately account for the complex material behavior under grinding conditions.This paper introduces novel models for predicting both surface roughness and SDD in hard and brittle semiconductor materials.The surface roughness model uniquely incorporates the material’s elastic recovery properties,revealing the significant impact of these properties on prediction accuracy.The SDD model is distinguished by its analysis of the interactions between abrasive grits and the workpiece,as well as the mechanisms governing stress-induced damage evolution.The surface roughness model and SDD model both establish a stable relationship with the grit depth of cut(GDC).Additionally,we have developed an analytical relationship between the GDC and grinding process parameters.This,in turn,enables the establishment of an analytical framework for predicting surface roughness and SDD based on grinding process parameters,which cannot be achieved by previous models.The models were validated through systematic experiments on three different semiconductor materials,demonstrating excellent agreement with experimental data,with prediction errors of 6.3%for surface roughness and6.9%for SDD.Additionally,this study identifies variations in elastic recovery and material plasticity as critical factors influencing surface roughness and SDD across different materials.These findings significantly advance the accuracy of predictive models and broaden their applicability for grinding hard and brittle semiconductor materials.展开更多
Testicular torsion is a urological emergency that requires prompt diagnosis and treatment,accounting for 10%-15%of cases of acute scrotum.[1]It occurs most frequently during the perinatal period and adolescence and ca...Testicular torsion is a urological emergency that requires prompt diagnosis and treatment,accounting for 10%-15%of cases of acute scrotum.[1]It occurs most frequently during the perinatal period and adolescence and can occur at any age.[2]The incidence of testicular torsion is 1/4,000 in males under 25 years of age and 1/160 in males over 25 years of age.[3]Unilateral torsion is relatively common,with a higher incidence on the left side.Testicular torsion is typically managed through surgical exploration.Necrotic testes,identified by a black appearance,require orchiectomy.[4]展开更多
Malaria remains a major public health challenge necessitating accurate predictive models to inform effective intervention strategies in Sierra Leone. This study compares the performance of Holt-Winters’ Exponential S...Malaria remains a major public health challenge necessitating accurate predictive models to inform effective intervention strategies in Sierra Leone. This study compares the performance of Holt-Winters’ Exponential Smoothing, Harmonic, and Artificial Neural Network (ANN) models using data from January 2018 to December 2023, incorporating both historical case records from Sierra Leone’s Health Management Information System (HMIS) and meteorological variables including humidity, precipitation, and temperature. The ANN model demonstrated superior performance, achieving a Mean Absolute Percentage Error (MAPE) of 4.74% before including climatic variables. This was further reduced to 3.9% with the inclusion of climatic variables, outperforming traditional models like Holt-Winters and Harmonic, which yielded MAPEs of 22.53% and 17.90% respectively. The ANN’s success is attributed to its ability to capture complex, non-linear relationships in the data, particularly when enhanced with relevant climatic variables. Using the optimized ANN model, we forecasted malaria cases for the next 24 months, predicting a steady increase from January 2024 to December 2025, with seasonal peaks. This study underscores the potential of machine learning approaches, particularly ANNs, in epidemiological modelling and highlights the importance of integrating environmental factors into malaria prediction models, recommending the ANN model for informing more targeted and efficient malaria control strategies to improve public health outcomes in Sierra Leone and similar settings.展开更多
Understanding and predicting droplet breakup is essential in droplet-based microfluidic systems,as it enables precise control over droplet manipulation for various applications.In this study,droplet breakup behavior i...Understanding and predicting droplet breakup is essential in droplet-based microfluidic systems,as it enables precise control over droplet manipulation for various applications.In this study,droplet breakup behavior in a T-junction microchannel is investigated under the influence of microchannel geometry using three-dimensional numerical simulations.A theoretical model is developed based on the balance between surface tension and viscous drag forces acting on the droplet,incorporating the effects of geometric parameters on droplet length.This model predicts the critical Capillary number required for breakup to occur.The theoretical predictions are validated using both previous research data and the present numerical simulations.The results show that the model accurately predicts the transition between breakup and non-breakup regimes.Specifically,an increase in sidearm length ratio inhibits droplet breakup and leads to an asymmetric breakup regime.Furthermore,increasing the outlet-to-inlet width ratio also reduces the likelihood of droplet breakup.These findings provide a predictive framework for understanding and controlling droplet dynamics in microfluidic T-junctions,with potential applications in lab-on-a-chip technologies.展开更多
BACKGROUND Stomal complications though small in early postoperative period,but poses significant morbidity,therapeutic challenge,delay in adjuvant treatment and sometimes even leads to mortality.Predictive model for e...BACKGROUND Stomal complications though small in early postoperative period,but poses significant morbidity,therapeutic challenge,delay in adjuvant treatment and sometimes even leads to mortality.Predictive model for early detection of stomal complications is important to improve the outcome.A model including patients and disease related factors,intraoperative surgical techniques and biochemical markers would be a better determinant to anticipate early stomal complications.Incorporation of emerging tools and technology such as artificial intelligence(AI),will further improve the prediction.AIM To identify various risk factors and models for prediction of early post operative stomal complications in colorectal cancer(CRC)surgery.METHODS Published literatures on early postoperative stomal complications in CRC surgery were systematically reviewed between 1995 and 2024 from online search engines PubMed and MEDLINE.RESULTS Twenty-four observational studies focused on identifying various risk factors for early post operative stomal complications in CRC surgery were analyzed.Stomal complications in CRC are influenced by several factors such as disease factors,patient-specific characteristics,and surgical techniques.There are some biomarkers and tools loke AI which may play significant roles in early detection.CONCLUSION Careful analysis of these factors,changes in biochemical parameters,and application of AI,a predictive model for stomal complications can be generated,to help in early detection,prompt action to achieve better outcomes.展开更多
BACKGROUND Low rectal cancer poses a significant surgical challenge because of its close proximity to the anal sphincter,often requiring radical resection with permanent colostomy to achieve oncological safety.Revisit...BACKGROUND Low rectal cancer poses a significant surgical challenge because of its close proximity to the anal sphincter,often requiring radical resection with permanent colostomy to achieve oncological safety.Revisited rectal anatomy,advances in surgical techniques and neoadjuvant therapies have enabled the possibility of sphincter-preserving procedures,however,it is uniformly not applicable.Selecting appropriate candidates for sphincter preservation is crucial,as an illadvised approach may compromise oncological outcome or lead to poor functional outcomes.Currently there is no consensus-which clinical,anatomical,or molecular factors most accurately predict the feasibility of sphincter-preserving surgery(SPS)in this subset of patients.By identifying these predictors,the study seeks to support improved patient selection,enhance surgical planning,and ultimately contribute to better functional and oncological outcomes in patients with low rectal cancer.AIM To identify predictive factors that determine the feasibility of SPS in patients with low rectal cancer.METHODS A comprehensive literature search was conducted using PubMed/MEDLINE databases.The search focused on various factors influencing the feasibility of SPS in low rectal cancer.These included patient-related factors,anatomical considerations,findings from different imaging modalities,advancements in diagnostic tools and techniques,and the role of neoadjuvant chemoradiotherapy.The relevance of each factor in predicting the potential for sphincter preservation was critically analyzed and presented based on the current evidence RESULTS Multiple studies have identified a range of predictive factors influencing the feasibility of SPS in low rectal cancer.Patient-related factors include age,sex,preoperative continence status,comorbidities,and body mass index.Anatomical considerations,such as tumor distance from the anal verge,involvement of the external anal sphincter,and levator ani muscles,also play a critical role.Additionally,a favourable response to neoadjuvant chemoradiotherapy has been associated with improved suitability for sphincter preservation.Several biomarkers,such as inflammatory markers like interleukins and C-reactive protein,as well as tumor markers like carcinoembryonic antigen,are important.Molecular markers,including BRAF and KRAS mutations and microsatellite instability status,have been linked to prognosis and may further guide decision-making regarding sphincter-preserving approaches.Artificial intelligence(AI)can further add in to select an ideal patient for sphincter preservation.CONCLUSION SPS is feasible in low rectal cancer and depends on patient factors,tumor anatomy and biology,preoperative treatment response,and biomarkers.In addition,tools and technology including AI can further help in selecting an ideal patient for long term optimal outcome.展开更多
BACKGROUND The trend of risk prediction models for diabetic peripheral neuropathy(DPN)is increasing,but few studies focus on the quality of the model and its practical application.AIM To conduct a comprehensive system...BACKGROUND The trend of risk prediction models for diabetic peripheral neuropathy(DPN)is increasing,but few studies focus on the quality of the model and its practical application.AIM To conduct a comprehensive systematic review and rigorous evaluation of prediction models for DPN.METHODS A meticulous search was conducted in PubMed,EMBASE,Cochrane,CNKI,Wang Fang DATA,and VIP Database to identify studies published until October 2023.The included and excluded criteria were applied by the researchers to screen the literature.Two investigators independently extracted data and assessed the quality using a data extraction form and a bias risk assessment tool.Disagreements were resolved through consultation with a third investigator.Data from the included studies were extracted utilizing the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies.Additionally,the bias risk and applicability of the models were evaluated by the Prediction Model Risk of Bias Assessment Tool.RESULTS The systematic review included 14 studies with a total of 26 models.The area under the receiver operating characteristic curve of the 26 models was 0.629-0.938.All studies had high risks of bias,mainly due to participants,outcomes,and analysis.The most common predictors included glycated hemoglobin,age,duration of diabetes,lipid abnormalities,and fasting blood glucose.CONCLUSION The predictor model presented good differentiation,calibration,but there were significant methodological flaws and high risk of bias.Future studies should focus on improving the study design and study report,updating the model and verifying its adaptability and feasibility in clinical practice.展开更多
Accurate prediction of coal reservoir permeability is crucial for engineering applications,including coal mining,coalbed methane(CBM)extraction,and carbon storage in deep unmineable coal seams.Owing to the inherent he...Accurate prediction of coal reservoir permeability is crucial for engineering applications,including coal mining,coalbed methane(CBM)extraction,and carbon storage in deep unmineable coal seams.Owing to the inherent heterogeneity and complex internal structure of coal,a well-established method for predicting permeability based on microscopic fracture structures remains elusive.This paper presents a novel integrated approach that leverages the intrinsic relationship between microscopic fracture structure and permeability to construct a predictive model for coal permeability.The proposed framework encompasses data generation through the integration of three-dimensional(3D)digital core analysis and numerical simulations,followed by data-driven modeling via machine learning(ML)techniques.Key data-driven strategies,including feature selection and hyperparameter tuning,are employed to improve model performance.We propose and evaluate twelve data-driven models,including multilayer perceptron(MLP),random forest(RF),and hybrid methods.The results demonstrate that the ML model based on the RF algorithm achieves the highest accuracy and best generalization capability in predicting permeability.This method enables rapid estimation of coal permeability by inputting two-dimensional(2D)computed tomography images or parameters of the microscopic fracture structure,thereby providing an accurate and efficient means of permeability prediction.展开更多
BACKGROUND Patients with chronic obstructive pulmonary disease(COPD)frequently experience exacerbations requiring multiple hospitalizations over prolonged disease courses,which predispose them to generalized anxiety d...BACKGROUND Patients with chronic obstructive pulmonary disease(COPD)frequently experience exacerbations requiring multiple hospitalizations over prolonged disease courses,which predispose them to generalized anxiety disorder(GAD).This comorbidity exacerbates breathing difficulties,activity limitations,and social isolation.While previous studies predominantly employed the GAD 7-item scale for screening,this approach is somewhat subjective.The current literature on predictive models for GAD risk in patients with COPD is limited.AIM To construct and validate a GAD risk prediction model to aid healthcare professionals in preventing the onset of GAD.METHODS This retrospective analysis encompassed patients with COPD treated at our institution from July 2021 to February 2024.The patients were categorized into a modeling(MO)group and a validation(VA)group in a 7:3 ratio on the basis of the occurrence of GAD.Univariate and multivariate logistic regression analyses were utilized to construct the risk prediction model,which was visualized using forest plots.The model’s performance was evaluated using Hosmer-Lemeshow(H-L)goodness-of-fit test and receiver operating characteristic(ROC)curve analysis.RESULTS A total of 271 subjects were included,with 190 in the MO group and 81 in the VA group.GAD was identified in 67 patients with COPD,resulting in a prevalence rate of 24.72%(67/271),with 49 cases(18.08%)in the MO group and 18 cases(22.22%)in the VA group.Significant differences were observed between patients with and without GAD in terms of educational level,average household income,smoking history,smoking index,number of exacerbations in the past year,cardiovascular comorbidities,disease knowledge,and personality traits(P<0.05).Multivariate logistic regression analysis revealed that lower education levels,household income<3000 China yuan,smoking history,smoking index≥400 cigarettes/year,≥two exacerbations in the past year,cardiovascular comorbidities,complete lack of disease information,and introverted personality were significant risk factors for GAD in the MO group(P<0.05).ROC analysis indicated that the area under the curve for predicting GAD in the MO and VA groups was 0.978 and 0.960.The H-L test yieldedχ^(2) values of 6.511 and 5.179,with P=0.275 and 0.274.Calibration curves demonstrated good agreement between predicted and actual GAD occurrence risks.CONCLUSION The developed predictive model includes eight independent risk factors:Educational level,household income,smoking history,smoking index,number of exacerbations in the past year,presence of cardiovascular comorbidities,level of disease knowledge,and personality traits.This model effectively predicts the onset of GAD in patients with COPD,enabling early identification of high-risk individuals and providing a basis for early preventive interventions by nursing staff.展开更多
Through systematic analysis of risk factors associated with postoperative delayed discharge following retrograde intrarenal surgery(RIRS)with flexible ureteroscopic holmium laser lithotripsy under ambulatory surgery p...Through systematic analysis of risk factors associated with postoperative delayed discharge following retrograde intrarenal surgery(RIRS)with flexible ureteroscopic holmium laser lithotripsy under ambulatory surgery protocols,this study aims to develop and validate a risk prediction model for discharge delay.The ultimate objectives include establishing evidence-based clinical guidelines for urolithiasis management,enabling proactive intervention strategies,and optimizing physician-patient communication efficiency.METHODS:This retrospective cohort study analyzed clinical data from 253 patients undergoing ambulatory retrograde intrarenal surgery(RIRS)with flexible ureteroscopic holmium laser lithotripsy at the Day Surgery Unit and Urology Department of Hunan Provincial People's Hospital between January 2023 and December 2024.To identify predictors of discharge delay,Lasso-regularized logistic regression analysis was implemented for variable selection,followed by multivariable logistic regression modeling via R statistical software(version 4.3.1).A clinical prediction nomogram was developed to visualize risk stratification,with model performance evaluated through receiver operating characteristic(ROC)curve analysis,calibration plots,and decision curve analysis(DCA).Internal validation was conducted using 1,000-cycle bootstrap resampling to ensure model generalizability.展开更多
BACKGROUND Difficulty of colonoscopy insertion(DCI)significantly affects colonoscopy effectiveness and serves as a key quality indicator.Predicting and evaluating DCI risk preoperatively is crucial for optimizing intr...BACKGROUND Difficulty of colonoscopy insertion(DCI)significantly affects colonoscopy effectiveness and serves as a key quality indicator.Predicting and evaluating DCI risk preoperatively is crucial for optimizing intraoperative strategies.AIM To evaluate the predictive performance of machine learning(ML)algorithms for DCI by comparing three modeling approaches,identify factors influencing DCI,and develop a preoperative prediction model using ML algorithms to enhance colonoscopy quality and efficiency.METHODS This cross-sectional study enrolled 712 patients who underwent colonoscopy at a tertiary hospital between June 2020 and May 2021.Demographic data,past medical history,medication use,and psychological status were collected.The endoscopist assessed DCI using the visual analogue scale.After univariate screening,predictive models were developed using multivariable logistic regression,least absolute shrinkage and selection operator(LASSO)regression,and random forest(RF)algorithms.Model performance was evaluated based on discrimination,calibration,and decision curve analysis(DCA),and results were visualized using nomograms.RESULTS A total of 712 patients(53.8%male;mean age 54.5 years±12.9 years)were included.Logistic regression analysis identified constipation[odds ratio(OR)=2.254,95%confidence interval(CI):1.289-3.931],abdominal circumference(AC)(77.5–91.9 cm,OR=1.895,95%CI:1.065-3.350;AC≥92 cm,OR=1.271,95%CI:0.730-2.188),and anxiety(OR=1.071,95%CI:1.044-1.100)as predictive factors for DCI,validated by LASSO and RF methods.Model performance revealed training/validation sensitivities of 0.826/0.925,0.924/0.868,and 1.000/0.981;specificities of 0.602/0.511,0.510/0.562,and 0.977/0.526;and corresponding area under the receiver operating characteristic curves(AUCs)of 0.780(0.737-0.823)/0.726(0.654-0.799),0.754(0.710-0.798)/0.723(0.656-0.791),and 1.000(1.000-1.000)/0.754(0.688-0.820),respectively.DCA indicated optimal net benefit within probability thresholds of 0-0.9 and 0.05-0.37.The RF model demonstrated superior diagnostic accuracy,reflected by perfect training sensitivity(1.000)and highest validation AUC(0.754),outperforming other methods in clinical applicability.CONCLUSION The RF-based model exhibited superior predictive accuracy for DCI compared to multivariable logistic and LASSO regression models.This approach supports individualized preoperative optimization,enhancing colonoscopy quality through targeted risk stratification.展开更多
BACKGROUND:Intracranial hemorrhage (ICH),a severe complication among adults receiving extracorporeal membrane oxygenation (ECMO),is often related to poor outcomes.This study aimed to establish a predictive model for I...BACKGROUND:Intracranial hemorrhage (ICH),a severe complication among adults receiving extracorporeal membrane oxygenation (ECMO),is often related to poor outcomes.This study aimed to establish a predictive model for ICH in adults receiving ECMO treatment.METHODS:Adults who received ECMO between January 2017 and June 2022 were the subjects of a single-center retrospective study.Patients under the age of 18 years old,with acute ICH before ECMO,with less than 24 h of ECMO support,and with incomplete data were excluded.ICH was diagnosed by a head computed tomography scan.The outcomes included the incidence of ICH,in-hosptial mortality and 28-day mortality.Multivariate logistic regression analysis was used to identify relevant risk factors of ICH,and a predictive model of ICH with a nomogram was constructed.RESULTS:Among the 227 patients included,22 developed ICH during ECMO.Patients with ICH had higher in-hospital mortality (90.9%vs.47.8%,P=0.001) and higher 28-day mortality (81.8%vs.47.3%,P=0.001) than patients with non-ICH.ICH was associated with decreased grey-white-matter ratio (GWR)(OR=0.894,95%CI:0.841–0.951,P<0.001),stroke history (OR=4.265,95%CI:1.052–17.291,P=0.042),fresh frozen plasma (FFP) transfusion (OR=1.208,95%CI:1.037–1.408,P=0.015)and minimum platelet (PLT) count during ECMO support (OR=0.977,95%CI:0.958–0.996,P=0.019).The area under the receiver operating characteristic curve of the ICH predictive model was 0.843 (95%CI:0.762–0.924,P<0.001).CONCLUSION:ECMO-treated patients with ICH had a higher risk of death.GWR,stroke history,FFP transfusion,and the minimum PLT count were independently associated with ICH,and the ICH predictive model showed that these parameters performed well as diagnostic tools.展开更多
基金supported by the National Key Research and Development Program of China(Grant No.2022YFC3002803)the National Key Research and Development Program of China(Grant No.2024YFF0808402)the National Natural Science Foundation of China(Grant No.42375169)。
文摘Northeast China serves as an important crop production region.Accurately forecasting summer precipitation in Northeast China(NEC-PR)has been a challenge due to its wide range of time scales influenced by varying climatic conditions.This study presents a scale separation hybrid statistical model with recurrent neural network(SS-RNN)to predict the summer monthly NEC-PR.The SS-RNN model decomposes the multiple scales of the NEC-PR into several spatiotemporal intrinsic mode functions covering annual to decadal time scales.This strategy provides a way to derive appropriate predictors and establish predictive models for the primary spatial modes of the NEC-PR at various time scales.Our results demonstrate substantial improvements by the SS-RNN model in predicting the summer monthly NEC-PR as compared with dynamic models,particularly in predicting the spatial pattern of the NEC-PR.In this paper we take August,the month of the highest NEC-PR,to assess our model skill.Independent forecasts of the August NEC-PR over the period 2021–24 achieve significant spatial anomaly correlation coefficients,reaching a maximum value of 0.83.Additional verifications by station observations show that the model hits most station anomalies,achieving a mean predictive skill score of 90.
基金supported by the special fund of the National Clinical Key Specialty Construction Program[(2022)301-2305].
文摘BACKGROUND:This study aims to develop and validate a machine learning-based in-hospital mortality predictive model for acute aortic syndrome(AAS)in the emergency department(ED)and to derive a simplifi ed version suitable for rapid clinical application.METHODS:In this multi-center retrospective cohort study,AAS patient data from three hospitals were analyzed.The modeling cohort included data from the First Affiliated Hospital of Zhengzhou University and the People’s Hospital of Xinjiang Uygur Autonomous Region,with Peking University Third Hospital data serving as the external test set.Four machine learning algorithms—logistic regression(LR),multilayer perceptron(MLP),Gaussian naive Bayes(GNB),and random forest(RF)—were used to develop predictive models based on 34 early-accessible clinical variables.A simplifi ed model was then derived based on fi ve key variables(Stanford type,pericardial eff usion,asymmetric peripheral arterial pulsation,decreased bowel sounds,and dyspnea)via Least Absolute Shrinkage and Selection Operator(LASSO)regression to improve ED applicability.RESULTS:A total of 929 patients were included in the modeling cohort,and 210 were included in the external test set.Four machine learning models based on 34 clinical variables were developed,achieving internal and external validation AUCs of 0.85-0.90 and 0.73-0.85,respectively.The simplifi ed model incorporating fi ve key variables demonstrated internal and external validation AUCs of 0.71-0.86 and 0.75-0.78,respectively.Both models showed robust calibration and predictive stability across datasets.CONCLUSION:Both kinds of models were built based on machine learning tools,and proved to have certain prediction performance and extrapolation.
文摘Hydrological extremes,such as floods,droughts,and compound events,are extremely dangerous to human societies,ecosystems,and infrastructures,whose frequency and severity are affected by climate change more and more.Effective disaster preparedness,water resource management,and climate adaptation have to do with accurate prediction and extensive risk assessment.This review sums up recent progress in predictive modeling and risk assessment systems in the framework of hydrological extremes in the changing climatic conditions.Statistical and empirical techniques,including extreme value theory and nonstationary frequency analysis,give probabilistic information using historic records,whereas process-based models give an understanding of physical hydrological processes at different climate and land-use conditions.New information-based and hybrid methods that use machine learning and high-resolution data take advantage of the complexity and nonlinearities and enhance the predictive power.Hazard,exposure,vulnerability,and adaptive capacity risk assessment models allow predictive output to be translated into actionable decision support,with socio-economic aspects and analysis of the scenario.Case studies of various regions across the globe show the use of these techniques to address floods,droughts,and compound events,with success and current problems.The review also addresses current trends such as compound hazard,multi-hazard integration,AI-enabled modelling,and cross-sectoral decision support,and outlines research priorities of improving predictive capability and resilience.This review will inform researchers,policymakers,and practitioners by offering a synthesis of all the effects of the hydrological extremes in climate change to formulate sound strategies for alleviating these effects.
基金supported by National Natural Science Foundation of China(Grant 62573375)the Natural Science Foundation of Hebei Province(Grant F2024203038)+2 种基金the Science and Technology Research and Development Plan Project of Qinhuangdao City(Grant 202302B048)the Provincial Key Laboratory Performance Subsidy Project(Grant 22567612H)the Shandong Provincial Natural Science Foundation Youth Project(ZR2023QF044)。
文摘In response to the challenges of inadequate predictive accuracy and limited generalization capability in data-driven modeling for the mechanical properties of the cold-rolled strip steel,a predictive modeling method named RFR-WOA is developed based on random forest regression(RFR)and whale optimization algorithm(WOA).Firstly,using Pearson and Spearman correlation analysis and Gini coefficient importance ranking on an actual production dataset containing 37,878 samples,22 key variables are selected as model inputs from 112 variables that affect mechanical properties.Subsequently,an RFR-based predictive model for the mechanical properties of cold-rolled strip steel is constructed.Then,with the combination of the coefficient of determination(R^(2))and root mean square error as the optimization objective,the hyperparameters of RFR model are iteratively optimized using WOA,and better predictive effectiveness is obtained.Finally,the mechanical properties prediction model based on RFR-WOA is compared with models established using deep neural networks,convolutional neural networks,and other methods.The test results on 9469 samples of actual production data show that the model developed present has better predictive accuracy and generalization capability.
基金Funded by State Railway Administration Research Project(No.2023JS007)National Natural Science Foundation of China(No.52438002)+1 种基金Research and Development Programs for Science and Technology of China Railways Corporation(No.J2023G003)New Cornerstone Science Foundation through the XPLORER PRIZE。
文摘To investigate the influence of coarse aggregate parent rock properties on the elastic modulus of concrete,the mineralogical properties and stress-strain curves of granite and dolomite parent rocks,as well as the strength and elastic modulus of mortar and concrete prepared with mechanism aggregates of the corresponding lithology,and the stress-strain curves of concrete were investigated.In this paper,a coarse aggregate and mortar matrix bonding assumption is proposed,and a prediction model for the elastic modulus of mortar is established by considering the lithology of the mechanism sand and the slurry components.An equivalent coarse aggregate elastic modulus model was established by considering factors such as coarse aggregate particle size,volume fraction,and mortar thickness between coarse aggregates.Based on the elastic modulus of the equivalent coarse aggregate and the remaining mortar,a prediction model for the elastic modulus of the two and three components of concrete in series and then in parallel was established,and the predicted values differed from the measured values within 10%.It is proposed that the coarse aggregate elastic modulus in highstrength concrete is the most critical factor affecting the elastic modulus of concrete,and as the coarse aggregate elastic modulus increases by 27.7%,the concrete elastic modulus increases by 19.5%.
文摘BACKGROUND Colorectal polyps are precancerous diseases of colorectal cancer.Early detection and resection of colorectal polyps can effectively reduce the mortality of colorectal cancer.Endoscopic mucosal resection(EMR)is a common polypectomy proce-dure in clinical practice,but it has a high postoperative recurrence rate.Currently,there is no predictive model for the recurrence of colorectal polyps after EMR.AIM To construct and validate a machine learning(ML)model for predicting the risk of colorectal polyp recurrence one year after EMR.METHODS This study retrospectively collected data from 1694 patients at three medical centers in Xuzhou.Additionally,a total of 166 patients were collected to form a prospective validation set.Feature variable screening was conducted using uni-variate and multivariate logistic regression analyses,and five ML algorithms were used to construct the predictive models.The optimal models were evaluated based on different performance metrics.Decision curve analysis(DCA)and SHapley Additive exPlanation(SHAP)analysis were performed to assess clinical applicability and predictor importance.RESULTS Multivariate logistic regression analysis identified 8 independent risk factors for colorectal polyp recurrence one year after EMR(P<0.05).Among the models,eXtreme Gradient Boosting(XGBoost)demonstrated the highest area under the curve(AUC)in the training set,internal validation set,and prospective validation set,with AUCs of 0.909(95%CI:0.89-0.92),0.921(95%CI:0.90-0.94),and 0.963(95%CI:0.94-0.99),respectively.DCA indicated favorable clinical utility for the XGBoost model.SHAP analysis identified smoking history,family history,and age as the top three most important predictors in the model.CONCLUSION The XGBoost model has the best predictive performance and can assist clinicians in providing individualized colonoscopy follow-up recommendations.
基金Supported by Shenzhen High-level Hospital Construction Fund.
文摘BACKGROUND Patients harboring gene mutations like KRAS,NRAS,and BRAF demonstrate highly variable responses to chemotherapy,posing challenges for treatment optimization.Multiparametric magnetic resonance imaging(MRI),with its noninvasive capability to assess tumor characteristics in detail,has shown promise in evaluating treatment response and predicting therapeutic outcomes.This technology holds potential for guiding personalized treatment strategies tailored to individual patient profiles,enhancing the precision and effectiveness of colorectal cancer care.AIM To create a multiparametric MRI-based predictive model for assessing chemotherapy efficacy in colorectal cancer patients with gene mutations.METHODS This retrospective study was conducted in a tertiary hospital,analyzing 157 colorectal cancer patients with gene mutations treated between August 2022 and December 2023.Based on chemotherapy outcomes,the patients were categorized into favorable(n=60)and unfavorable(n=50)response groups.Univariate and multivariate logistic regression analyses were performed to identify independent predictors of chemotherapy efficacy.A predictive nomogram was constructed using significant variables,and its performance was assessed using the area under the receiver operating characteristic curve(AUC)in both training and validation sets.RESULTS Univariate analysis identified that tumor differentiation,T2 signal intensity ratio,tumor-to-anal margin distance,and MRI-detected lymph node metastasis as significantly associated with chemotherapy response(P<0.05).Multivariate Logistics regression confirmed these four parameters as independent predictors.The predictive model demonstrated strong discrimination,with an AUC of 0.938(sensitivity:86%;specificity:92%)in the training set,and 0.942(sensitivity:100%;specificity:83%)in the validation set.CONCLUSION We established and validated a multiparametric MRI-based model for predicting chemotherapy response in colorectal cancer patients with gene mutations.This model holds promise for guiding individualized treatment strategies.
基金supported by the National Key Research and Development Program of China(2022YFB3605902)the National Natural Science Foundation of China(52375411,52293402)。
文摘Workpiece rotational grinding is widely used in the ultra-precision machining of hard and brittle semiconductor materials,including single-crystal silicon,silicon carbide,and gallium arsenide.Surface roughness and subsurface damage depth(SDD)are crucial indicators for evaluating the surface quality of these materials after grinding.Existing prediction models lack general applicability and do not accurately account for the complex material behavior under grinding conditions.This paper introduces novel models for predicting both surface roughness and SDD in hard and brittle semiconductor materials.The surface roughness model uniquely incorporates the material’s elastic recovery properties,revealing the significant impact of these properties on prediction accuracy.The SDD model is distinguished by its analysis of the interactions between abrasive grits and the workpiece,as well as the mechanisms governing stress-induced damage evolution.The surface roughness model and SDD model both establish a stable relationship with the grit depth of cut(GDC).Additionally,we have developed an analytical relationship between the GDC and grinding process parameters.This,in turn,enables the establishment of an analytical framework for predicting surface roughness and SDD based on grinding process parameters,which cannot be achieved by previous models.The models were validated through systematic experiments on three different semiconductor materials,demonstrating excellent agreement with experimental data,with prediction errors of 6.3%for surface roughness and6.9%for SDD.Additionally,this study identifies variations in elastic recovery and material plasticity as critical factors influencing surface roughness and SDD across different materials.These findings significantly advance the accuracy of predictive models and broaden their applicability for grinding hard and brittle semiconductor materials.
基金supported by the National Natural Science Foundation of China(82371709).
文摘Testicular torsion is a urological emergency that requires prompt diagnosis and treatment,accounting for 10%-15%of cases of acute scrotum.[1]It occurs most frequently during the perinatal period and adolescence and can occur at any age.[2]The incidence of testicular torsion is 1/4,000 in males under 25 years of age and 1/160 in males over 25 years of age.[3]Unilateral torsion is relatively common,with a higher incidence on the left side.Testicular torsion is typically managed through surgical exploration.Necrotic testes,identified by a black appearance,require orchiectomy.[4]
文摘Malaria remains a major public health challenge necessitating accurate predictive models to inform effective intervention strategies in Sierra Leone. This study compares the performance of Holt-Winters’ Exponential Smoothing, Harmonic, and Artificial Neural Network (ANN) models using data from January 2018 to December 2023, incorporating both historical case records from Sierra Leone’s Health Management Information System (HMIS) and meteorological variables including humidity, precipitation, and temperature. The ANN model demonstrated superior performance, achieving a Mean Absolute Percentage Error (MAPE) of 4.74% before including climatic variables. This was further reduced to 3.9% with the inclusion of climatic variables, outperforming traditional models like Holt-Winters and Harmonic, which yielded MAPEs of 22.53% and 17.90% respectively. The ANN’s success is attributed to its ability to capture complex, non-linear relationships in the data, particularly when enhanced with relevant climatic variables. Using the optimized ANN model, we forecasted malaria cases for the next 24 months, predicting a steady increase from January 2024 to December 2025, with seasonal peaks. This study underscores the potential of machine learning approaches, particularly ANNs, in epidemiological modelling and highlights the importance of integrating environmental factors into malaria prediction models, recommending the ANN model for informing more targeted and efficient malaria control strategies to improve public health outcomes in Sierra Leone and similar settings.
基金funded by the Master,Ph D Scholarship Programme of Vingroup Innovation Foundation(VINIF),code VINIF.2023.Th S.118。
文摘Understanding and predicting droplet breakup is essential in droplet-based microfluidic systems,as it enables precise control over droplet manipulation for various applications.In this study,droplet breakup behavior in a T-junction microchannel is investigated under the influence of microchannel geometry using three-dimensional numerical simulations.A theoretical model is developed based on the balance between surface tension and viscous drag forces acting on the droplet,incorporating the effects of geometric parameters on droplet length.This model predicts the critical Capillary number required for breakup to occur.The theoretical predictions are validated using both previous research data and the present numerical simulations.The results show that the model accurately predicts the transition between breakup and non-breakup regimes.Specifically,an increase in sidearm length ratio inhibits droplet breakup and leads to an asymmetric breakup regime.Furthermore,increasing the outlet-to-inlet width ratio also reduces the likelihood of droplet breakup.These findings provide a predictive framework for understanding and controlling droplet dynamics in microfluidic T-junctions,with potential applications in lab-on-a-chip technologies.
文摘BACKGROUND Stomal complications though small in early postoperative period,but poses significant morbidity,therapeutic challenge,delay in adjuvant treatment and sometimes even leads to mortality.Predictive model for early detection of stomal complications is important to improve the outcome.A model including patients and disease related factors,intraoperative surgical techniques and biochemical markers would be a better determinant to anticipate early stomal complications.Incorporation of emerging tools and technology such as artificial intelligence(AI),will further improve the prediction.AIM To identify various risk factors and models for prediction of early post operative stomal complications in colorectal cancer(CRC)surgery.METHODS Published literatures on early postoperative stomal complications in CRC surgery were systematically reviewed between 1995 and 2024 from online search engines PubMed and MEDLINE.RESULTS Twenty-four observational studies focused on identifying various risk factors for early post operative stomal complications in CRC surgery were analyzed.Stomal complications in CRC are influenced by several factors such as disease factors,patient-specific characteristics,and surgical techniques.There are some biomarkers and tools loke AI which may play significant roles in early detection.CONCLUSION Careful analysis of these factors,changes in biochemical parameters,and application of AI,a predictive model for stomal complications can be generated,to help in early detection,prompt action to achieve better outcomes.
文摘BACKGROUND Low rectal cancer poses a significant surgical challenge because of its close proximity to the anal sphincter,often requiring radical resection with permanent colostomy to achieve oncological safety.Revisited rectal anatomy,advances in surgical techniques and neoadjuvant therapies have enabled the possibility of sphincter-preserving procedures,however,it is uniformly not applicable.Selecting appropriate candidates for sphincter preservation is crucial,as an illadvised approach may compromise oncological outcome or lead to poor functional outcomes.Currently there is no consensus-which clinical,anatomical,or molecular factors most accurately predict the feasibility of sphincter-preserving surgery(SPS)in this subset of patients.By identifying these predictors,the study seeks to support improved patient selection,enhance surgical planning,and ultimately contribute to better functional and oncological outcomes in patients with low rectal cancer.AIM To identify predictive factors that determine the feasibility of SPS in patients with low rectal cancer.METHODS A comprehensive literature search was conducted using PubMed/MEDLINE databases.The search focused on various factors influencing the feasibility of SPS in low rectal cancer.These included patient-related factors,anatomical considerations,findings from different imaging modalities,advancements in diagnostic tools and techniques,and the role of neoadjuvant chemoradiotherapy.The relevance of each factor in predicting the potential for sphincter preservation was critically analyzed and presented based on the current evidence RESULTS Multiple studies have identified a range of predictive factors influencing the feasibility of SPS in low rectal cancer.Patient-related factors include age,sex,preoperative continence status,comorbidities,and body mass index.Anatomical considerations,such as tumor distance from the anal verge,involvement of the external anal sphincter,and levator ani muscles,also play a critical role.Additionally,a favourable response to neoadjuvant chemoradiotherapy has been associated with improved suitability for sphincter preservation.Several biomarkers,such as inflammatory markers like interleukins and C-reactive protein,as well as tumor markers like carcinoembryonic antigen,are important.Molecular markers,including BRAF and KRAS mutations and microsatellite instability status,have been linked to prognosis and may further guide decision-making regarding sphincter-preserving approaches.Artificial intelligence(AI)can further add in to select an ideal patient for sphincter preservation.CONCLUSION SPS is feasible in low rectal cancer and depends on patient factors,tumor anatomy and biology,preoperative treatment response,and biomarkers.In addition,tools and technology including AI can further help in selecting an ideal patient for long term optimal outcome.
基金Supported by Capital’s Funds for Health Improvement and Research,No.2024-4-4135.
文摘BACKGROUND The trend of risk prediction models for diabetic peripheral neuropathy(DPN)is increasing,but few studies focus on the quality of the model and its practical application.AIM To conduct a comprehensive systematic review and rigorous evaluation of prediction models for DPN.METHODS A meticulous search was conducted in PubMed,EMBASE,Cochrane,CNKI,Wang Fang DATA,and VIP Database to identify studies published until October 2023.The included and excluded criteria were applied by the researchers to screen the literature.Two investigators independently extracted data and assessed the quality using a data extraction form and a bias risk assessment tool.Disagreements were resolved through consultation with a third investigator.Data from the included studies were extracted utilizing the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies.Additionally,the bias risk and applicability of the models were evaluated by the Prediction Model Risk of Bias Assessment Tool.RESULTS The systematic review included 14 studies with a total of 26 models.The area under the receiver operating characteristic curve of the 26 models was 0.629-0.938.All studies had high risks of bias,mainly due to participants,outcomes,and analysis.The most common predictors included glycated hemoglobin,age,duration of diabetes,lipid abnormalities,and fasting blood glucose.CONCLUSION The predictor model presented good differentiation,calibration,but there were significant methodological flaws and high risk of bias.Future studies should focus on improving the study design and study report,updating the model and verifying its adaptability and feasibility in clinical practice.
基金supported by the Zhejiang Provincial Natural Science Foundation of China(Grant No.LY23E040001)Fundamental Research Funding Project of Zhejiang Province,China(Project Category A,Grant No.2022YW06)National Key R&D Program of China(Grant No.2023YFF0614902).
文摘Accurate prediction of coal reservoir permeability is crucial for engineering applications,including coal mining,coalbed methane(CBM)extraction,and carbon storage in deep unmineable coal seams.Owing to the inherent heterogeneity and complex internal structure of coal,a well-established method for predicting permeability based on microscopic fracture structures remains elusive.This paper presents a novel integrated approach that leverages the intrinsic relationship between microscopic fracture structure and permeability to construct a predictive model for coal permeability.The proposed framework encompasses data generation through the integration of three-dimensional(3D)digital core analysis and numerical simulations,followed by data-driven modeling via machine learning(ML)techniques.Key data-driven strategies,including feature selection and hyperparameter tuning,are employed to improve model performance.We propose and evaluate twelve data-driven models,including multilayer perceptron(MLP),random forest(RF),and hybrid methods.The results demonstrate that the ML model based on the RF algorithm achieves the highest accuracy and best generalization capability in predicting permeability.This method enables rapid estimation of coal permeability by inputting two-dimensional(2D)computed tomography images or parameters of the microscopic fracture structure,thereby providing an accurate and efficient means of permeability prediction.
基金Supported by the Henan Provincial Health Commission,No.232102310145.
文摘BACKGROUND Patients with chronic obstructive pulmonary disease(COPD)frequently experience exacerbations requiring multiple hospitalizations over prolonged disease courses,which predispose them to generalized anxiety disorder(GAD).This comorbidity exacerbates breathing difficulties,activity limitations,and social isolation.While previous studies predominantly employed the GAD 7-item scale for screening,this approach is somewhat subjective.The current literature on predictive models for GAD risk in patients with COPD is limited.AIM To construct and validate a GAD risk prediction model to aid healthcare professionals in preventing the onset of GAD.METHODS This retrospective analysis encompassed patients with COPD treated at our institution from July 2021 to February 2024.The patients were categorized into a modeling(MO)group and a validation(VA)group in a 7:3 ratio on the basis of the occurrence of GAD.Univariate and multivariate logistic regression analyses were utilized to construct the risk prediction model,which was visualized using forest plots.The model’s performance was evaluated using Hosmer-Lemeshow(H-L)goodness-of-fit test and receiver operating characteristic(ROC)curve analysis.RESULTS A total of 271 subjects were included,with 190 in the MO group and 81 in the VA group.GAD was identified in 67 patients with COPD,resulting in a prevalence rate of 24.72%(67/271),with 49 cases(18.08%)in the MO group and 18 cases(22.22%)in the VA group.Significant differences were observed between patients with and without GAD in terms of educational level,average household income,smoking history,smoking index,number of exacerbations in the past year,cardiovascular comorbidities,disease knowledge,and personality traits(P<0.05).Multivariate logistic regression analysis revealed that lower education levels,household income<3000 China yuan,smoking history,smoking index≥400 cigarettes/year,≥two exacerbations in the past year,cardiovascular comorbidities,complete lack of disease information,and introverted personality were significant risk factors for GAD in the MO group(P<0.05).ROC analysis indicated that the area under the curve for predicting GAD in the MO and VA groups was 0.978 and 0.960.The H-L test yieldedχ^(2) values of 6.511 and 5.179,with P=0.275 and 0.274.Calibration curves demonstrated good agreement between predicted and actual GAD occurrence risks.CONCLUSION The developed predictive model includes eight independent risk factors:Educational level,household income,smoking history,smoking index,number of exacerbations in the past year,presence of cardiovascular comorbidities,level of disease knowledge,and personality traits.This model effectively predicts the onset of GAD in patients with COPD,enabling early identification of high-risk individuals and providing a basis for early preventive interventions by nursing staff.
文摘Through systematic analysis of risk factors associated with postoperative delayed discharge following retrograde intrarenal surgery(RIRS)with flexible ureteroscopic holmium laser lithotripsy under ambulatory surgery protocols,this study aims to develop and validate a risk prediction model for discharge delay.The ultimate objectives include establishing evidence-based clinical guidelines for urolithiasis management,enabling proactive intervention strategies,and optimizing physician-patient communication efficiency.METHODS:This retrospective cohort study analyzed clinical data from 253 patients undergoing ambulatory retrograde intrarenal surgery(RIRS)with flexible ureteroscopic holmium laser lithotripsy at the Day Surgery Unit and Urology Department of Hunan Provincial People's Hospital between January 2023 and December 2024.To identify predictors of discharge delay,Lasso-regularized logistic regression analysis was implemented for variable selection,followed by multivariable logistic regression modeling via R statistical software(version 4.3.1).A clinical prediction nomogram was developed to visualize risk stratification,with model performance evaluated through receiver operating characteristic(ROC)curve analysis,calibration plots,and decision curve analysis(DCA).Internal validation was conducted using 1,000-cycle bootstrap resampling to ensure model generalizability.
基金the Chinese Clinical Trial Registry(No.ChiCTR2000040109)approved by the Hospital Ethics Committee(No.20210130017).
文摘BACKGROUND Difficulty of colonoscopy insertion(DCI)significantly affects colonoscopy effectiveness and serves as a key quality indicator.Predicting and evaluating DCI risk preoperatively is crucial for optimizing intraoperative strategies.AIM To evaluate the predictive performance of machine learning(ML)algorithms for DCI by comparing three modeling approaches,identify factors influencing DCI,and develop a preoperative prediction model using ML algorithms to enhance colonoscopy quality and efficiency.METHODS This cross-sectional study enrolled 712 patients who underwent colonoscopy at a tertiary hospital between June 2020 and May 2021.Demographic data,past medical history,medication use,and psychological status were collected.The endoscopist assessed DCI using the visual analogue scale.After univariate screening,predictive models were developed using multivariable logistic regression,least absolute shrinkage and selection operator(LASSO)regression,and random forest(RF)algorithms.Model performance was evaluated based on discrimination,calibration,and decision curve analysis(DCA),and results were visualized using nomograms.RESULTS A total of 712 patients(53.8%male;mean age 54.5 years±12.9 years)were included.Logistic regression analysis identified constipation[odds ratio(OR)=2.254,95%confidence interval(CI):1.289-3.931],abdominal circumference(AC)(77.5–91.9 cm,OR=1.895,95%CI:1.065-3.350;AC≥92 cm,OR=1.271,95%CI:0.730-2.188),and anxiety(OR=1.071,95%CI:1.044-1.100)as predictive factors for DCI,validated by LASSO and RF methods.Model performance revealed training/validation sensitivities of 0.826/0.925,0.924/0.868,and 1.000/0.981;specificities of 0.602/0.511,0.510/0.562,and 0.977/0.526;and corresponding area under the receiver operating characteristic curves(AUCs)of 0.780(0.737-0.823)/0.726(0.654-0.799),0.754(0.710-0.798)/0.723(0.656-0.791),and 1.000(1.000-1.000)/0.754(0.688-0.820),respectively.DCA indicated optimal net benefit within probability thresholds of 0-0.9 and 0.05-0.37.The RF model demonstrated superior diagnostic accuracy,reflected by perfect training sensitivity(1.000)and highest validation AUC(0.754),outperforming other methods in clinical applicability.CONCLUSION The RF-based model exhibited superior predictive accuracy for DCI compared to multivariable logistic and LASSO regression models.This approach supports individualized preoperative optimization,enhancing colonoscopy quality through targeted risk stratification.
基金supported by the National Natural Science Foundation of China (82072159)。
文摘BACKGROUND:Intracranial hemorrhage (ICH),a severe complication among adults receiving extracorporeal membrane oxygenation (ECMO),is often related to poor outcomes.This study aimed to establish a predictive model for ICH in adults receiving ECMO treatment.METHODS:Adults who received ECMO between January 2017 and June 2022 were the subjects of a single-center retrospective study.Patients under the age of 18 years old,with acute ICH before ECMO,with less than 24 h of ECMO support,and with incomplete data were excluded.ICH was diagnosed by a head computed tomography scan.The outcomes included the incidence of ICH,in-hosptial mortality and 28-day mortality.Multivariate logistic regression analysis was used to identify relevant risk factors of ICH,and a predictive model of ICH with a nomogram was constructed.RESULTS:Among the 227 patients included,22 developed ICH during ECMO.Patients with ICH had higher in-hospital mortality (90.9%vs.47.8%,P=0.001) and higher 28-day mortality (81.8%vs.47.3%,P=0.001) than patients with non-ICH.ICH was associated with decreased grey-white-matter ratio (GWR)(OR=0.894,95%CI:0.841–0.951,P<0.001),stroke history (OR=4.265,95%CI:1.052–17.291,P=0.042),fresh frozen plasma (FFP) transfusion (OR=1.208,95%CI:1.037–1.408,P=0.015)and minimum platelet (PLT) count during ECMO support (OR=0.977,95%CI:0.958–0.996,P=0.019).The area under the receiver operating characteristic curve of the ICH predictive model was 0.843 (95%CI:0.762–0.924,P<0.001).CONCLUSION:ECMO-treated patients with ICH had a higher risk of death.GWR,stroke history,FFP transfusion,and the minimum PLT count were independently associated with ICH,and the ICH predictive model showed that these parameters performed well as diagnostic tools.
