Objective:To explore the application value of a machine learning-based prediction model in assessing the prognosis of septic children in the pediatric intensive care unit(PICU)and provide data support for clinical dec...Objective:To explore the application value of a machine learning-based prediction model in assessing the prognosis of septic children in the pediatric intensive care unit(PICU)and provide data support for clinical decision-making.Methods:A total of 180 septic children admitted to the PICU of a tertiary hospital from January 2020 to December 2024 were selected.They were divided into a control group(90 cases,using traditional scoring methods to predict prognosis)and an observation group(90 cases,using a multivariable model based on machine learning algorithms to predict prognosis)according to the random number table method.General information,laboratory indicators,and clinical interventions were collected.Various models such as Random Forest(RF),Support Vector Machine(SVM),and Logistic Regression(LR)were established.The model performance was evaluated using ROC curve,AUC value,accuracy,sensitivity,and specificity.Results:The machine learning models performed better than traditional scoring methods in predicting the 28-day mortality rate of septic children.Among them,the RF model achieved an AUC value of 0.921,a sensitivity of 85.6%,and a specificity of 88.1%,which were significantly higher than the PIM3 score(AUC 0.762).The prediction accuracy and timeliness of clinical intervention in the observation group were significantly improved,leading to a shortened hospital stay and reduced mortality rate(p<0.05).Conclusion:The prediction model based on machine learning can more accurately assess the prognostic risk of septic children in PICU,showing good clinical application prospects and providing references for individualized treatment and optimal resource allocation.展开更多
Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investiga...Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%-52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.展开更多
BACKGROUND Colorectal cancer(CRC)is characterized by high heterogeneity,aggressiveness,and high morbidity and mortality rates.With machine learning(ML)algorithms,patient,tumor,and treatment features can be used to dev...BACKGROUND Colorectal cancer(CRC)is characterized by high heterogeneity,aggressiveness,and high morbidity and mortality rates.With machine learning(ML)algorithms,patient,tumor,and treatment features can be used to develop and validate models for predicting survival.In addition,important variables can be screened and different applications can be provided that could serve as vital references when making clinical decisions and potentially improving patient outcomes in clinical settings.AIM To construct prognostic prediction models and screen important variables for patients with stageⅠtoⅢCRC.METHODS More than 1000 postoperative CRC patients were grouped according to survival time(with cutoff values of 3 years and 5 years)and assigned to training and testing cohorts(7:3).For each 3-category survival time,predictions were made by 4 ML algorithms(all-variable and important variable-only datasets),each of which was validated via 5-fold cross-validation and bootstrap validation.Important variables were screened with multivariable regression methods.Model performance was evaluated and compared before and after variable screening with the area under the curve(AUC).SHapley Additive exPlanations(SHAP)further demonstrated the impact of important variables on model decision-making.Nomograms were constructed for practical model application.RESULTS Our ML models performed well;the model performance before and after important parameter identification was consistent,and variable screening was effective.The highest pre-and postscreening model AUCs 95%confidence intervals in the testing set were 0.87(0.81-0.92)and 0.89(0.84-0.93)for overall survival,0.75(0.69-0.82)and 0.73(0.64-0.81)for disease-free survival,0.95(0.88-1.00)and 0.88(0.75-0.97)for recurrence-free survival,and 0.76(0.47-0.95)and 0.80(0.53-0.94)for distant metastasis-free survival.Repeated cross-validation and bootstrap validation were performed in both the training and testing datasets.The SHAP values of the important variables were consistent with the clinicopathological characteristics of patients with tumors.The nomograms were created.CONCLUSION We constructed a comprehensive,high-accuracy,important variable-based ML architecture for predicting the 3-category survival times.This architecture could serve as a vital reference for managing CRC patients.展开更多
Ovarian cancer has one of the highest mortality rates among gynecological malignancies.This disease has a low early detection rate,a high postoperative recurrence rate,and a 5-year survival rate of only 40%.Hence,ther...Ovarian cancer has one of the highest mortality rates among gynecological malignancies.This disease has a low early detection rate,a high postoperative recurrence rate,and a 5-year survival rate of only 40%.Hence,there is an urgent need to improve the early diagnosis and prognosis of ovarian cancer.Prediction models can effectively estimate the risk of disease occurrence,as well as its prognosis.Recently,many studies have established multiple ovarian cancer prediction models based on different regions and populations.These models can improve the detection rate and optimize the prognosis management to a certain extent.Herein,the construction principle of the ovarian cancer risk prediction model and its validation are summarized;furthermore,comprehensive reviews and comparisons of the different types of these models are made.Therefore,our review may be of great significance for the whole course of ovarian cancer management.展开更多
ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical ...ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical practice.However,existing clinical risk scores and manually derived imaging biomarkers have limited accuracy in predicting post-STEMI outcomes.To address this gap,we developed DeepSTEMI,an end-to-end deep learning system that integrates multi-sequence cardiac magnetic resonance(CMR)images with clinical parameters for predicting 2-year major adverse cardiovascular events(MACE).The system comprised two key algorithmic modules:a U-Net module that automatically segments heart regions from raw CMR images and a Transformer-based module that predicted future cardiovascular events.DeepSTEMI was developed using a multicenter dataset(n=610;20,618 images)from STEMI patients enrolled in the EARLY-MYO-CMR registry(NCT03768453),with external validation performed in 334 patients(9944 images)from three independent cardiac centers.In external validation,DeepSTEMI demonstrated superior predictive performance compared to conventional clinical risk scores and manual CMR parameters(AUC 0.894,95%CI:0.823-0.965;overall accuracy 94.3%).The model identified high-risk patients who exhibited a 20-fold MACE risk compared to low-risk counterparts(HR 20.43,log-rank P<0.001).SHapley Additive exPlanations(SHAP)analysis revealed that DeepSTEMI's predictive power stems from clinical-imaging synergy,enabling it to capture complex pathological patterns.DeepSTEMI achieved consistently superior performance over the Eitel score across all subgroups,with the greatest benefit observed in women(NRI 1.597)and in patients imaged 4-7 d post-STEMI(NRI 1.442).Overall,DeepSTEMI serves as an automated,scalable,and interpretable clinical copilot,which advances postSTEMI risk stratification beyond the limitations of current paradigms.展开更多
Importance:Acute kidney injury(AKI)is common in hospitalized children which could rapidly progress into chronic kidney disease if not timely diagnosed.Prognostic prediction models for AKI were established to identify ...Importance:Acute kidney injury(AKI)is common in hospitalized children which could rapidly progress into chronic kidney disease if not timely diagnosed.Prognostic prediction models for AKI were established to identify AKI early and improve children’s prognosis.Objective:To appraise prognostic prediction models for pediatric AKI.Methods:Four English and four Chinese databases were systematically searched from January 1,2010,to June 6,2022.Articles describing prognostic prediction models for pediatric AKI were included.The data extraction was based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies checklist.The risk of bias(ROB)was assessed according to the Prediction model Risk of Bias Assessment Tool guideline.The quantitative synthesis of the models was not performed due to the lack of methods regarding the meta-analysis of prediction models.Results:Eight studies with 16 models were included.There were significant deficiencies in reporting and all models were considered at high ROB.The area under the receiver operating characteristic curve to predict AKI ranged from 0.69 to 0.95.However,only about one-third of models have completed internal or external validation.The calibration was provided only in four models.Three models allowed easy bedside calculation or electronic automation,and two models were evaluated for their impacts on clinical practice.Interpretation:Besides the modeling algorithm,the challenges for developing prediction models for pediatric AKI reflected by the reporting deficiencies included ways of handling baseline serum creatinine and age-dependent blood biochemical indexes.Moreover,few prediction models for pediatric AKI were performed for external validation,let alone the transformation in clinical practice.Further investigation should focus on the combination of prediction models and electronic automatic alerts.展开更多
The estrogen receptor(ER)-negative breast cancer subtype is aggressive with few treatment options available.To identify specific prognostic factors for ER-negative breast cancer,this study included 705,729 and 1034 br...The estrogen receptor(ER)-negative breast cancer subtype is aggressive with few treatment options available.To identify specific prognostic factors for ER-negative breast cancer,this study included 705,729 and 1034 breast invasive cancer patients from the Surveillance,Epidemiology,and End Results(SEER)and The Cancer Genome Atlas(TCGA)databases,respectively.To identify key differential kinase-substrate node and edge biomarkers between ER-negative and ERpositive breast cancer patients,we adopted a network-based method using correlation coefficients between molecular pairs in the kinase regulatory network.Integrated analysis of the clinical and molecular data revealed the significant prognostic power of kinase-substrate node and edge features for both subtypes of breast cancer.Two promising kinase-substrate edge features,CSNK1A1-NFATC3 and SRC-OCLN,were identified for more accurate prognostic prediction in ERnegative breast cancer patients.展开更多
BACKGROUND Liver failure,particularly acute-on-chronic liver failure,is associated with high mortality(50%-90%).The plasma exchange(PE)mode of the artificial liver support system has been shown to improve clinical out...BACKGROUND Liver failure,particularly acute-on-chronic liver failure,is associated with high mortality(50%-90%).The plasma exchange(PE)mode of the artificial liver support system has been shown to improve clinical outcomes,although its efficacy may vary depending on the regenerative capacity of the liver.Alpha-fetoprotein(AFP),an oncofetal glycoprotein,is reactivated during liver regeneration and may serve as a prognostic biomarker.Previous studies have reported significantly higher post-PE AFP levels in survivors than in non-survivors(286.5 ng/mL vs 82.3 ng/mL at day 7).However,the predictive value of baseline AFP stratification and serial AFP kinetics during PE therapy remains unestablished.This study investigated whether serial AFP measurements predict clinical outcomes in liver failure patients receiving PE.AIM To evaluate the predictive value of serial AFP measurements in liver failure patients receiving PE.METHODS This retrospective study included 194 liver failure patients with complete AFP data,excluding those with tumors,bleeding disorders,allergies,or unstable conditions.Patients were stratified by baseline AFP into low-AFP(<100 ng/mL,n=60),medium-AFP(100-200 ng/mL,n=70),and high-AFP(>200 ng/mL,n=64)groups.AFP was measured before PE and on days 1,10,20,and 25.RESULTS Stratification by baseline AFP revealed significant gradients.The high-AFP group required fewer PE sessions than the low-AFP group(2.8±1.0 vs 4.2±1.5)but exhibited greater post-PE AFP elevation(75.1±20.3 ng/mL vs 33.1±10.2 ng/mL;P<0.001).The high-AFP group demonstrated optimal values,including the lowest ammonia,bilirubin,alanine aminotransferase,aspartate aminotransferase,γ-glutamyl transferase,and the highest albumin and prothrombin activity(all post hoc P<0.05 vs low-AFP).The medium-AFP group showed intermediate values except for prothrombin activity(35.2%±8.6%),which was significantly lower than in both other groups(P<0.001).The high-AFP group had a reduced incidence of spontaneous bacterial peritonitis(9.4%vs 25.0%;P=0.003),superior three-month survival(90.6%vs 56.7%;P<0.001),and a higher post-treatment three-month receiver operating characteristic area under the curve(0.8851 vs 0.7051).CONCLUSION AFP dynamics correlate with regenerative capacity and clinical outcomes in liver failure.Serial AFP monitoring may enhance risk stratification and support personalized therapeutic strategies.展开更多
Objective The systemic immune-inflammation index(SII)has recently attracted significant interest as a new biomarker for predicting the prognosis of patients with glioblastoma(GBM).However,the predictive significance o...Objective The systemic immune-inflammation index(SII)has recently attracted significant interest as a new biomarker for predicting the prognosis of patients with glioblastoma(GBM).However,the predictive significance of it is still a subject of debate.This study intended to assess the clinical effectiveness of the SII in GBM and establish a nomogram.Methods Receiver operating characteristic(ROC)curves were utilized to determine the optimal cut-off values of the SII.Kaplan–Meier(KM)survival curves were used to analyze the median overall survival(OS).Cox regression analysis was carried out to evaluate the associations between OS and different clinical factors.Based on the SII and clinical characteristics,a nomogram was constructed,and its value in clinical application was evaluated by means of decision curve analysis.Results The optimal SII cut-off value was 610.13.KM analysis revealed that GBM patients with higher SII values had shorter OS(15.0 vs.34.0 months,P=0.044).Multivariate analysis demonstrated that a high SII was an independent predictor of poor outcome in GBM(HR=1.79,P=0.029).The nomogram incorporating the preoperative SII showed good predictive accuracy for GBM patient prognosis(C-index=0.691).Conclusions The SII is an independent predictive indicator for GBM.Patients with elevated SII levels tend to have a poorer prognosis.A nomogram combining the SII with clinical and molecular pathological features can assist clinicians in assessing the risk of death in GBM patients,providing a basis for individualized treatment decisions.展开更多
Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including ...Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.展开更多
Objective:This study aimed to examine a novel method for prognostic evaluation of patients with oral squamous cell carcinoma(OSCC)based on the expression of heterogeneous nuclear ribonucleoprotein C(HNRNPC),YTH domain...Objective:This study aimed to examine a novel method for prognostic evaluation of patients with oral squamous cell carcinoma(OSCC)based on the expression of heterogeneous nuclear ribonucleoprotein C(HNRNPC),YTH domain-binding protein 2(YTHDF2),and methyltransferase 14(METTL14).Methods:We obtained the RNA sequence and clinical information of OSCC patients from The Cancer Genome Atlas database.An optical method was established by the least absolute shrinkage and selection operator Cox regression algorithm,which was used to calculate the risk score of every sample.In addition,all samples(n=239)were classified into high-risk(n=119)and low-risk(n=120)groups,and the overall survival(OS)time and clinical characteristics were compared between groups.Moreover,bioinformatics analysis was carried out.Gene set enrichment analysis was performed to investigate the signaling pathways of HNRNPC,YTHDF2,and METTL14.Results:The two groups showed significantly different OS time,tumor grades,tumor stages,and pathologic T stages(P<0.05).The receiver operating characteristic analysis identified that our method was effective and it was more accurate than use of age,gender,tumor grade,tumor stage,pathologic T stage,and pathologic N stage in OSCC prognostic prediction.Gene set enrichment analysis revealed that HNRNPC,YTHDF2,and METTL14 were mainly associated with ubiquitin-mediated proteolysis,cell cycle,RNA degradation,and spliceosome signaling pathways.Conclusion:The method based on the expression of HNRNPC,YTHDF2,and METTL14 can predict the prognosis of patients with OSCC independently,and its prognostic value is better than that of clinicopathological characteristic indicators.展开更多
Hepatocellular carcinoma(HCC)is a common immunogenic malignant tumor.Although the new strategies of immunotherapy and targeted therapy have made considerable progress in the treatment of HCC,the 5-year survival rate o...Hepatocellular carcinoma(HCC)is a common immunogenic malignant tumor.Although the new strategies of immunotherapy and targeted therapy have made considerable progress in the treatment of HCC,the 5-year survival rate of patients is still very low.The identification of new prognostic signatures and the exploration of the immune microenvironment are crucial to the optimization and improvement of molecular therapy strategies.We studied the potential clinical benefits of the inflammation regulator miR-93-3p and mined its target genes.Weighted gene coexpression network analysis(WGCNA),univariate and multivariate COX regression and the LASSO COX algorithm are employed to identify prognostic-related genes and construct multi-gene signature-based risk model and nomogram for survival prediction.Support vector machine(SVM)based Cibersort’s deconvolution algorithm and gene set enrichment analysis(GSEA)is used to evaluate the changes in tumor immune microenvironment and pathway differences.The study found the favorable prognostic performance of miR-93-3p and identified 389 prognostic-related target genes.The risk model based on a novel 5-gene signature(cct5,cdk4,cenpa,dtnbp1 and flvcr1)was developed and has prominent prognostic significance in the training cohort(P<0.0001)and validation cohort(P=0.0016).The nomogram constructed by combining the gene signature and the AJCC stage further improves the survival prediction ability of the gene signature.The infiltration level of multiple immune cells(especially T cells,B cells and macrophages)were positively correlated with the expression of prognostic signature.In addition,we found that gene markers of T cells and B cells is monitored and regulated by prognostic signature.Meanwhile,several GSEA pathways related to the immune system are enriched in the high-risk group.In general,we integrated the WGCNA,LASSO COX and SVM algorithms to develop and verify 5-gene signatures and nomograms related to immune infiltration to improve the survival prediction of patients.展开更多
BACKGROUND The novel coronavirus disease 2019(COVID-19)pandemic is a global threat caused by the severe acute respiratory syndrome coronavirus-2.AIM To develop and validate a risk stratification tool for the early pre...BACKGROUND The novel coronavirus disease 2019(COVID-19)pandemic is a global threat caused by the severe acute respiratory syndrome coronavirus-2.AIM To develop and validate a risk stratification tool for the early prediction of intensive care unit(ICU)admission among COVID-19 patients at hospital admission.METHODS The training cohort included COVID-19 patients admitted to the Wuhan Third Hospital.We selected 13 of 65 baseline laboratory results to assess ICU admission risk,which were used to develop a risk prediction model with the random forest(RF)algorithm.A nomogram for the logistic regression model was built based on six selected variables.The predicted models were carefully calibrated,and the predictive performance was evaluated and compared with two previously published models.RESULTS There were 681 and 296 patients in the training and validation cohorts,respectively.The patients in the training cohort were older than those in the validation cohort(median age:63.0 vs 49.0 years,P<0.001),and the percentages of male gender were similar(49.6%vs 49.3%,P=0.958).The top predictors selected in the RF model were neutrophil-to-lymphocyte ratio,age,lactate dehydrogenase,C-reactive protein,creatinine,D-dimer,albumin,procalcitonin,glucose,platelet,total bilirubin,lactate and creatine kinase.The accuracy,sensitivity and specificity for the RF model were 91%,88%and 93%,respectively,higher than those for the logistic regression model.The area under the receiver operating characteristic curve of our model was much better than those of two other published methods(0.90 vs 0.82 and 0.75).Model A underestimated risk of ICU admission in patients with a predicted risk less than 30%,whereas the RF risk score demonstrated excellent ability to categorize patients into different risk strata.Our predictive model provided a larger standardized net benefit across the major high-risk range compared with model A.CONCLUSION Our model can identify ICU admission risk in COVID-19 patients at admission,who can then receive prompt care,thus improving medical resource allocation.展开更多
Intrahepatic cholangiocarcinoma(ICC)is a primary liver malignancy with increasing global incidence and mortality rates.The 5-year overall survival rate for patients with ICC is approximately 9%.Surgical resection curr...Intrahepatic cholangiocarcinoma(ICC)is a primary liver malignancy with increasing global incidence and mortality rates.The 5-year overall survival rate for patients with ICC is approximately 9%.Surgical resection currently represents the only curative treatment option.However,due to the high aggressiveness,insidious onset,and atypical clinical presentation of ICC,many patients either miss the optimal surgical window or experience early postoperative recurrence and metastasis.This poses significant challenges for hepatobiliary surgeons worldwide.Artificial intelligence(AI),as a prominent driver of technological advancement,offers promising new avenues for managing ICC.By leveraging powerful machine learning and deep learning algorithms,AI has demonstrated promising outcomes in ICC diagnosis,particularly in differentiating it from hepatocellular carcinoma,and in predicting critical prognostic factors such as early recurrence,lymph node metastasis,and microvascular invasion.These innovations can support clinical decision-making and ultimately improve patient outcomes.Future efforts should prioritize robust clinical studies evaluating the effectiveness of AI in ICC management.展开更多
Background:As a major histopathological subtype of gastric cancer(GC),stomach adenocarcinoma(STAD)is an important malignant tumor in the digestive system.Increasing evidence also indicates that endoplasmic reticulum(E...Background:As a major histopathological subtype of gastric cancer(GC),stomach adenocarcinoma(STAD)is an important malignant tumor in the digestive system.Increasing evidence also indicates that endoplasmic reticulum(ER)stress plays a pivotal role in the pathogenesis and progression of GC.Therefore,this study aims to screen and identify vital ER stress-related genes that could contribute to the malignant development and poor prognosis for STAD.Methods:A novel ER stress-related risk score signature was developed employingmachine learning techniques.Then,a prognostic prediction nomogram was also built based on the clinicopathological characteristics and the risk score signature.The tumor immune microenvironment characteristics and pathway enrichment analysis in different risk groups were also explored.Furthermore,through the single-cell RNA sequencing(scRNA-seq)analysis,the study highlightedCytochrome P450 Family 19 SubfamilyAMember 1(CYP19A1)as the pivotal research target and detected its effect on cell proliferation by 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazoliumbromide(MTT)and the expression of ER stress-related genes by RT-qPCR in STAD.Results:Based on the evaluation of five screened key ER stressrelated genes(AKR1B1,SERPINE1,ADCYAP1,MATN3,CYP19A1),our ER stress-related risk score signature offers a novel approach for assessing STAD prognosis hazards.The novel prognostic prediction nomogram based on the signature also accurately predicted the survival outcomes of patients with STAD.Furthermore,the expression of CYP19A1 is significantly higher in STAD tissues than in normal tissues.High expression of CYP19A1 was related to a poor survival outcome for patients with STAD.Besides,compared to normal gastric epithelial cells,the expression of CYP19A1 was significantly higher in STAD cell lines.Silencing the expression of CYP19A1 significantly inhibited the cell proliferation ability and decreased the expression of ER stress-related genes,including ATF4,DDIT3 and XBP1 in STAD.Conclusions:In conclusion,our study developed a novel prognosis prediction signature and identified the novel diagnostic and therapeutic target CYP19A1 for patients with STAD.展开更多
Multiple system atrophy is a sporadic,progressive,adult-onset,neurodegenerative disorder characte rized by autonomic dysfunction symptoms,parkinsonian features,and cerebellar signs in va rious combinations.An early di...Multiple system atrophy is a sporadic,progressive,adult-onset,neurodegenerative disorder characte rized by autonomic dysfunction symptoms,parkinsonian features,and cerebellar signs in va rious combinations.An early diagnosis of multiple system atrophy is of utmost impo rtance for the proper prevention and management of its potentially fatal complications leading to the poor prognosis of these patients.The current diagnostic criteria incorporate several clinical red flags and magnetic resonance imaging marke rs supporting diagnosis of multiple system atrophy.Nonetheless,especially in the early disease stage,it can be challenging to differentiate multiple system atrophy from mimic disorders,in particular Parkinson’s disease.Electromyography of the external anal sphincter represents a useful neurophysiological tool for diffe rential diagnosis since it can provide indirect evidence of Onuf’s nucleus degeneration,which is a pathological hallmark of multiple system atrophy.However,the diagnostic value of external anal sphincter electromyography has been a matter of debate for three decades due to controve rsial reports in the literature.In this review,after a brief ove rview of the electrophysiological methodology,we first aimed to critically analyze the available knowledge on the diagnostic role of external anal sphincter electromyography.We discussed the conflicting evidence on the clinical correlations of neurogenic abnormalities found at external anal sphincter electro myography.Finally,we repo rted recent prognostic findings of a novel classification of electromyography patterns of the external anal sphincter that could pave the way toward the implementation of this neurophysiological technique for survival prediction in patients with multiple system atrophy.展开更多
Solid pseudopapillary tumor of the pancreas(SPTP)is a rare neoplasm predom-inantly observed in young females.Pathologically,CTNNB1 mutations,β-catenin nuclear accumulation,and subsequent Wnt-signaling pathway activat...Solid pseudopapillary tumor of the pancreas(SPTP)is a rare neoplasm predom-inantly observed in young females.Pathologically,CTNNB1 mutations,β-catenin nuclear accumulation,and subsequent Wnt-signaling pathway activation are the leading molecular features.Accurate preoperative diagnosis often relies on imaging techniques and endoscopic biopsies.Surgical resection remains the mainstay treatment.Risk models,such as the Fudan Prognostic Index,show promise as predictive tools for assessing the prognosis of SPTP.Establishing three types of metachronous liver metastasis can be beneficial in tailoring individu-alized treatment and follow-up strategies.Despite advancements,challenges persist in understanding its etiology,establishing standardized treatments for unresectable or metastatic diseases,and developing a widely recognized grading system.This comprehensive review aims to elucidate the enigma by consolidating current knowledge on the epidemiology,clinical presentation,pathology,molecular characteristics,diagnostic methods,treatment options,and prognostic factors.展开更多
Background:Tumor heterogeneity is closely related to the occurrence,progression and recurrence of renal clear cell carcinoma(ccRCC),making early diagnosis and effective treatment difficult.DNA methylation is an import...Background:Tumor heterogeneity is closely related to the occurrence,progression and recurrence of renal clear cell carcinoma(ccRCC),making early diagnosis and effective treatment difficult.DNA methylation is an important regulator of gene expression and can affect tumor heterogeneity.Methods:In this study,we investigated the prognostic value of subtypes based on DNA methylation status in 506 ccRCC samples with paired clinical data from the TCGA database.Differences in DNA methylation levels were associated with differences in T,N and M categories,age,stage and prognosis.Finally,the samples were divided into the training group and the testing group according to 450K and 27K.Univariate and multivariate Cox regression analysis was used to construct the prediction model in the training group,and the model was verified and evaluated in the testing group.Results:By univariate Cox regression analysis,21,122 methylation sites and 6,775 CpG sites were identified as potential DNA methylation biomarkers for overall survival of ccRCC patients(P<0.05).3,050 CpG sites independently associated with prognosis were identified with T,N,M,stage and age as covariables.Consensus cluster of 3,050 potential prognostic methylation sites was used to identify different DNA methylation subsets of ccRCC for prognostic purposes.We performed functional enrichment analysis on these 3,640 genes and identified 75 significantly enriched pathways(P<0.05).We then researched the expression of methylated genes in subgroups.Verifing with the training set,suggesting that DNA methylation levels generally reflect the expression of these genes.Conclusion:Based on TCGA database and a series of bioinformatics methods,We identified prognostic specific methylation sites and established prognostic prediction models for ccRCC patients.This model helps to identify novel biomarkers,precision drug targets and disease molecular subtypes in patients with ccRCC.Therefore,this model may be useful in predicting the prognosis,clinical diagnosis and management of patients with different epigenetic subtypes of ccRCC.展开更多
Background:Cholangiocarcinoma(CCA)is highly malignant and has a poor prognosis has a high malignant degree and poor prognosis.The purpose of this study is to develop a new prognostic model based on genes related to th...Background:Cholangiocarcinoma(CCA)is highly malignant and has a poor prognosis has a high malignant degree and poor prognosis.The purpose of this study is to develop a new prognostic model based on genes related to the tumor microenvironment(TME).Methods:Derived from the discerned differentially expressed genes within The Cancer Genome Atlas(TCGA)dataset,this investigation employed the methodology of weighted gene co-expression network analysis(WGCNA)to ascertain gene co-expressed modules intricately linked to the Tumor Microenvironment(TME)among Cholangiocarcinoma(CCA)patients.The genes associated with prognosis,as identified through Cox regression analysis,were employed in the formulation of a predictive model.This model underwent validation,leading to the development of a risk score formula and nomogram.Concurrently,we validated the model’s reliability using data from CCA patients in the Gene Expression Omnibus(GEO)database(accession:GSE107943).Results:6139 DEGs were divided into 10 co-expressed gene modules using WGCNA.Among these,two modules(blue module with 832 genes and brown module with 1379 genes)showed high correlation with the TME.Five prognostic genes(BNIP3,COL4A3,SPRED3,CEBPB,PLOD2)were identified through Cox regression analysis,and a prognostic model and risk score formula were developed based on these genes.Risk score formula:Risk score=BNIP3×1.70520-COL4A3×2.39815+SPRED3×1.17936+CEBPB×0.40456+PLOD2×0.24785.Kaplan-Meier survival analysis revealed that the survival probabilities of the low-risk group were significantly higher than those of the high-risk group.Furthermore,the related evaluation indexes suggested that the model exhibited strong predictive ability.Conclusion:The prognostic model,based on five TME-related genes(BNIP3,COL4A3,SPRED3,CEBPB,PLOD2),could accurately assess the prognosis of CCA patients to aid in guiding clinical decisions.展开更多
Epigenetics is the main mechanism that controls transcription of specific genes with no changes in the underlying DNA sequences. Epigenetic alterations lead to abnormal gene expression patterns that contribute to carc...Epigenetics is the main mechanism that controls transcription of specific genes with no changes in the underlying DNA sequences. Epigenetic alterations lead to abnormal gene expression patterns that contribute to carcinogenesis and persist throughout disease progression. Because of the reversible nature, epigenetic modifications emerge as promising anticancer drug targets. Several compounds have been developed to reverse the aberrant activities of enzymes involved in epigenetic regulation, and some of them show encouraging results in both preclinical and clinical studies. In this article, we comprehensively review the up-to-date roles of epigenetics in the development and progression of prostate cancer. We especially focus on three epigenetic mechanisms: DNA methylation, histone modifications, and noncoding RNAs. We elaborate on current models/theories that explain the necessity of these epigenetic programs in driving the malignant phenotypes of prostate cancer cells. In particular, we elucidate how certain epigenetic regulators crosstalk with critical biological pathways, such as androgen receptor (AR) signaling, and how the cooperation dynamically controls cancer-oriented transcriptional profiles. Restoration of a “normal” epigenetic landscape holds promise as a cure for prostate cancer, so we concluded by highlighting particular epigenetic modifications as diagnostic and prognostic biomarkers or new therapeutic targets for treatment of the disease.展开更多
文摘Objective:To explore the application value of a machine learning-based prediction model in assessing the prognosis of septic children in the pediatric intensive care unit(PICU)and provide data support for clinical decision-making.Methods:A total of 180 septic children admitted to the PICU of a tertiary hospital from January 2020 to December 2024 were selected.They were divided into a control group(90 cases,using traditional scoring methods to predict prognosis)and an observation group(90 cases,using a multivariable model based on machine learning algorithms to predict prognosis)according to the random number table method.General information,laboratory indicators,and clinical interventions were collected.Various models such as Random Forest(RF),Support Vector Machine(SVM),and Logistic Regression(LR)were established.The model performance was evaluated using ROC curve,AUC value,accuracy,sensitivity,and specificity.Results:The machine learning models performed better than traditional scoring methods in predicting the 28-day mortality rate of septic children.Among them,the RF model achieved an AUC value of 0.921,a sensitivity of 85.6%,and a specificity of 88.1%,which were significantly higher than the PIM3 score(AUC 0.762).The prediction accuracy and timeliness of clinical intervention in the observation group were significantly improved,leading to a shortened hospital stay and reduced mortality rate(p<0.05).Conclusion:The prediction model based on machine learning can more accurately assess the prognostic risk of septic children in PICU,showing good clinical application prospects and providing references for individualized treatment and optimal resource allocation.
基金the Natural Science Foundation of Hainan Province,No.821MS125the National Key R&D Program of China,No.2023YFC2415200+6 种基金the Key R&D projects in Hainan Province,No.ZDYF-2021SHFZ239the Natural Science Research Project“open competition mechanism”of Hainan Medical College,Nos.JBGS202113 and JBGS202107Strategic Priority Research Program of the Chinese Academy of Sciences,No.XDB 38040200National Natural Science Foundation of China,Nos.82372053,82302296,81871346,81971602,82022036,91959130,81971776,81771924,62027901,81930053Beijing Natural Science Foundation,No.L182061 and Z20J00105Chinese Academy of Sciences,Nos.GJJSTD20170004 and QYZDJ-SSW-JSC005and Youth Innovation Promotion Association CAS,No.2017175.
文摘Although prognostic prediction of nasopharyngeal carcinoma (NPC) remains a pivotal research area, the role of dynamic contrast-enhanced magnetic resonance (DCE-MR) has been less explored. This study aimed to investigate the role of DCR-MR in predicting progression-free survival (PFS) in patients with NPC using magnetic resonance (MR)- and DCE-MR-based radiomic models. A total of 434 patients with two MR scanning sequences were included. The MR- and DCE-MR-based radiomics models were developed based on 289 patients with only MR scanning sequences and 145 patients with four additional pharmacokinetic parameters (volume fraction of extravascular extracellular space (ve), volume fraction of plasma space (vp), volume transfer constant (Ktrans), and reverse reflux rate constant (kep) of DCE-MR. A combined model integrating MR and DCE-MR was constructed. Utilizing methods such as correlation analysis, least absolute shrinkage and selection operator regression, and multivariate Cox proportional hazards regression, we built the radiomics models. Finally, we calculated the net reclassification index and C-index to evaluate and compare the prognostic performance of the radiomics models. Kaplan-Meier survival curve analysis was performed to investigate the model’s ability to stratify risk in patients with NPC. The integration of MR and DCE-MR radiomic features significantly enhanced prognostic prediction performance compared to MR- and DCE-MR-based models, evidenced by a test set C-index of 0.808 vs 0.729 and 0.731, respectively. The combined radiomics model improved net reclassification by 22.9%-52.6% and could significantly stratify the risk levels of patients with NPC (p = 0.036). Furthermore, the MR-based radiomic feature maps achieved similar results to the DCE-MR pharmacokinetic parameters in terms of reflecting the underlying angiogenesis information in NPC. Compared to conventional MR-based radiomics models, the combined radiomics model integrating MR and DCE-MR showed promising results in delivering more accurate prognostic predictions and provided more clinical benefits in quantifying and monitoring phenotypic changes associated with NPC prognosis.
基金Supported by National Natural Science Foundation of China,No.81802777.
文摘BACKGROUND Colorectal cancer(CRC)is characterized by high heterogeneity,aggressiveness,and high morbidity and mortality rates.With machine learning(ML)algorithms,patient,tumor,and treatment features can be used to develop and validate models for predicting survival.In addition,important variables can be screened and different applications can be provided that could serve as vital references when making clinical decisions and potentially improving patient outcomes in clinical settings.AIM To construct prognostic prediction models and screen important variables for patients with stageⅠtoⅢCRC.METHODS More than 1000 postoperative CRC patients were grouped according to survival time(with cutoff values of 3 years and 5 years)and assigned to training and testing cohorts(7:3).For each 3-category survival time,predictions were made by 4 ML algorithms(all-variable and important variable-only datasets),each of which was validated via 5-fold cross-validation and bootstrap validation.Important variables were screened with multivariable regression methods.Model performance was evaluated and compared before and after variable screening with the area under the curve(AUC).SHapley Additive exPlanations(SHAP)further demonstrated the impact of important variables on model decision-making.Nomograms were constructed for practical model application.RESULTS Our ML models performed well;the model performance before and after important parameter identification was consistent,and variable screening was effective.The highest pre-and postscreening model AUCs 95%confidence intervals in the testing set were 0.87(0.81-0.92)and 0.89(0.84-0.93)for overall survival,0.75(0.69-0.82)and 0.73(0.64-0.81)for disease-free survival,0.95(0.88-1.00)and 0.88(0.75-0.97)for recurrence-free survival,and 0.76(0.47-0.95)and 0.80(0.53-0.94)for distant metastasis-free survival.Repeated cross-validation and bootstrap validation were performed in both the training and testing datasets.The SHAP values of the important variables were consistent with the clinicopathological characteristics of patients with tumors.The nomograms were created.CONCLUSION We constructed a comprehensive,high-accuracy,important variable-based ML architecture for predicting the 3-category survival times.This architecture could serve as a vital reference for managing CRC patients.
基金the Shanghai Municipal Key Clinical Specialty Program(No.shslczdzk06302)。
文摘Ovarian cancer has one of the highest mortality rates among gynecological malignancies.This disease has a low early detection rate,a high postoperative recurrence rate,and a 5-year survival rate of only 40%.Hence,there is an urgent need to improve the early diagnosis and prognosis of ovarian cancer.Prediction models can effectively estimate the risk of disease occurrence,as well as its prognosis.Recently,many studies have established multiple ovarian cancer prediction models based on different regions and populations.These models can improve the detection rate and optimize the prognosis management to a certain extent.Herein,the construction principle of the ovarian cancer risk prediction model and its validation are summarized;furthermore,comprehensive reviews and comparisons of the different types of these models are made.Therefore,our review may be of great significance for the whole course of ovarian cancer management.
基金supported by the Innovative Research Group Project of China’s National Natural Science Foundation(82421001)the National Natural Science Foundation of China(823B2005,824B1015,U21A20341,T2525004,82470394,82230014,82202159,81930007,81971570,and 32100426)+13 种基金the National Key Research and Development Program of China(2021YFC2502300 and 2022YFE0103500)the National Science Fund for Distinguished Young Scholars(81625002)the Shanghai Municipal Health Commission(2022JC013,2023ZZ02021,GWVI11.1-26,and 2022ZZ01008)the Science and Technology Commission of Shanghai Municipality(24DZ2202700,22DZ2292400,22JC1402100,and 20YF1426100)the Program of Shanghai Academic Research Leader(21XD1432100)the Shanghai Municipal Education Commission(SHSMU-ZDCX20210700)the Shanghai Municipal Health Commission(202440156)the Shanghai Institutions of Higher Learning,Innovative Research Team of High-Level Local Universities in Shanghai(SHSMU-ZDCX20210700)(Project 2021-01-07-00-02-E00083)the National High Level Hospital Clinical Research Funding(2022-PUMCH-C-023)the MedicalEngineering Joint Funds of Shanghai Jiao Tong University(YG2022QN107 and 2025ZYB-007)the Shanghai Clinical Cohort Program(Reserve Clinical Cohort)by the Shanghai Hospital Deveopment Center(SHDC2025CCS037)the Shanghai Professional Technical Service Platform for Cardio-Cerebral Disease Biobank and Database(22DZ2292400)the Pudong New District Health Commission(PW2023E-02)support from the innovative research team of high-level local universities in Shanghai。
文摘ST-elevation myocardial infarction(STEMI)remains a leading cause of cardiovascular morbidity and mortality worldwide,and accurate early risk stratification is critical for implementing precision therapies in clinical practice.However,existing clinical risk scores and manually derived imaging biomarkers have limited accuracy in predicting post-STEMI outcomes.To address this gap,we developed DeepSTEMI,an end-to-end deep learning system that integrates multi-sequence cardiac magnetic resonance(CMR)images with clinical parameters for predicting 2-year major adverse cardiovascular events(MACE).The system comprised two key algorithmic modules:a U-Net module that automatically segments heart regions from raw CMR images and a Transformer-based module that predicted future cardiovascular events.DeepSTEMI was developed using a multicenter dataset(n=610;20,618 images)from STEMI patients enrolled in the EARLY-MYO-CMR registry(NCT03768453),with external validation performed in 334 patients(9944 images)from three independent cardiac centers.In external validation,DeepSTEMI demonstrated superior predictive performance compared to conventional clinical risk scores and manual CMR parameters(AUC 0.894,95%CI:0.823-0.965;overall accuracy 94.3%).The model identified high-risk patients who exhibited a 20-fold MACE risk compared to low-risk counterparts(HR 20.43,log-rank P<0.001).SHapley Additive exPlanations(SHAP)analysis revealed that DeepSTEMI's predictive power stems from clinical-imaging synergy,enabling it to capture complex pathological patterns.DeepSTEMI achieved consistently superior performance over the Eitel score across all subgroups,with the greatest benefit observed in women(NRI 1.597)and in patients imaged 4-7 d post-STEMI(NRI 1.442).Overall,DeepSTEMI serves as an automated,scalable,and interpretable clinical copilot,which advances postSTEMI risk stratification beyond the limitations of current paradigms.
基金National Natural Science Foundation of China,Grant/Award Number:72174128High-Level Public Health Technical Talent Training Plan,Grant/Award Number:2022-2-026
文摘Importance:Acute kidney injury(AKI)is common in hospitalized children which could rapidly progress into chronic kidney disease if not timely diagnosed.Prognostic prediction models for AKI were established to identify AKI early and improve children’s prognosis.Objective:To appraise prognostic prediction models for pediatric AKI.Methods:Four English and four Chinese databases were systematically searched from January 1,2010,to June 6,2022.Articles describing prognostic prediction models for pediatric AKI were included.The data extraction was based on the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies checklist.The risk of bias(ROB)was assessed according to the Prediction model Risk of Bias Assessment Tool guideline.The quantitative synthesis of the models was not performed due to the lack of methods regarding the meta-analysis of prediction models.Results:Eight studies with 16 models were included.There were significant deficiencies in reporting and all models were considered at high ROB.The area under the receiver operating characteristic curve to predict AKI ranged from 0.69 to 0.95.However,only about one-third of models have completed internal or external validation.The calibration was provided only in four models.Three models allowed easy bedside calculation or electronic automation,and two models were evaluated for their impacts on clinical practice.Interpretation:Besides the modeling algorithm,the challenges for developing prediction models for pediatric AKI reflected by the reporting deficiencies included ways of handling baseline serum creatinine and age-dependent blood biochemical indexes.Moreover,few prediction models for pediatric AKI were performed for external validation,let alone the transformation in clinical practice.Further investigation should focus on the combination of prediction models and electronic automatic alerts.
基金supported by the National Key R&D Program of China(Grant No.2017YFA0505500)the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA12010000)+2 种基金the National Program on Key Basic Research Project of China(Grant Nos.2014CBA02000 and 2014CB910500)the National Natural Science Foundation of China(Grant Nos.91029301,30700397,91529303,and 31771476)the support of the SANOFI-SIBS Distinguish Young Scientist Award Scholarship Program。
文摘The estrogen receptor(ER)-negative breast cancer subtype is aggressive with few treatment options available.To identify specific prognostic factors for ER-negative breast cancer,this study included 705,729 and 1034 breast invasive cancer patients from the Surveillance,Epidemiology,and End Results(SEER)and The Cancer Genome Atlas(TCGA)databases,respectively.To identify key differential kinase-substrate node and edge biomarkers between ER-negative and ERpositive breast cancer patients,we adopted a network-based method using correlation coefficients between molecular pairs in the kinase regulatory network.Integrated analysis of the clinical and molecular data revealed the significant prognostic power of kinase-substrate node and edge features for both subtypes of breast cancer.Two promising kinase-substrate edge features,CSNK1A1-NFATC3 and SRC-OCLN,were identified for more accurate prognostic prediction in ERnegative breast cancer patients.
基金Supported by National Natural Science Foundation of China,No.82160106.
文摘BACKGROUND Liver failure,particularly acute-on-chronic liver failure,is associated with high mortality(50%-90%).The plasma exchange(PE)mode of the artificial liver support system has been shown to improve clinical outcomes,although its efficacy may vary depending on the regenerative capacity of the liver.Alpha-fetoprotein(AFP),an oncofetal glycoprotein,is reactivated during liver regeneration and may serve as a prognostic biomarker.Previous studies have reported significantly higher post-PE AFP levels in survivors than in non-survivors(286.5 ng/mL vs 82.3 ng/mL at day 7).However,the predictive value of baseline AFP stratification and serial AFP kinetics during PE therapy remains unestablished.This study investigated whether serial AFP measurements predict clinical outcomes in liver failure patients receiving PE.AIM To evaluate the predictive value of serial AFP measurements in liver failure patients receiving PE.METHODS This retrospective study included 194 liver failure patients with complete AFP data,excluding those with tumors,bleeding disorders,allergies,or unstable conditions.Patients were stratified by baseline AFP into low-AFP(<100 ng/mL,n=60),medium-AFP(100-200 ng/mL,n=70),and high-AFP(>200 ng/mL,n=64)groups.AFP was measured before PE and on days 1,10,20,and 25.RESULTS Stratification by baseline AFP revealed significant gradients.The high-AFP group required fewer PE sessions than the low-AFP group(2.8±1.0 vs 4.2±1.5)but exhibited greater post-PE AFP elevation(75.1±20.3 ng/mL vs 33.1±10.2 ng/mL;P<0.001).The high-AFP group demonstrated optimal values,including the lowest ammonia,bilirubin,alanine aminotransferase,aspartate aminotransferase,γ-glutamyl transferase,and the highest albumin and prothrombin activity(all post hoc P<0.05 vs low-AFP).The medium-AFP group showed intermediate values except for prothrombin activity(35.2%±8.6%),which was significantly lower than in both other groups(P<0.001).The high-AFP group had a reduced incidence of spontaneous bacterial peritonitis(9.4%vs 25.0%;P=0.003),superior three-month survival(90.6%vs 56.7%;P<0.001),and a higher post-treatment three-month receiver operating characteristic area under the curve(0.8851 vs 0.7051).CONCLUSION AFP dynamics correlate with regenerative capacity and clinical outcomes in liver failure.Serial AFP monitoring may enhance risk stratification and support personalized therapeutic strategies.
基金funded by National Natural Science Foundation of China,grant number 82203007.
文摘Objective The systemic immune-inflammation index(SII)has recently attracted significant interest as a new biomarker for predicting the prognosis of patients with glioblastoma(GBM).However,the predictive significance of it is still a subject of debate.This study intended to assess the clinical effectiveness of the SII in GBM and establish a nomogram.Methods Receiver operating characteristic(ROC)curves were utilized to determine the optimal cut-off values of the SII.Kaplan–Meier(KM)survival curves were used to analyze the median overall survival(OS).Cox regression analysis was carried out to evaluate the associations between OS and different clinical factors.Based on the SII and clinical characteristics,a nomogram was constructed,and its value in clinical application was evaluated by means of decision curve analysis.Results The optimal SII cut-off value was 610.13.KM analysis revealed that GBM patients with higher SII values had shorter OS(15.0 vs.34.0 months,P=0.044).Multivariate analysis demonstrated that a high SII was an independent predictor of poor outcome in GBM(HR=1.79,P=0.029).The nomogram incorporating the preoperative SII showed good predictive accuracy for GBM patient prognosis(C-index=0.691).Conclusions The SII is an independent predictive indicator for GBM.Patients with elevated SII levels tend to have a poorer prognosis.A nomogram combining the SII with clinical and molecular pathological features can assist clinicians in assessing the risk of death in GBM patients,providing a basis for individualized treatment decisions.
基金Supported by Xuhui District Health Commission,No.SHXH202214.
文摘Gastrointestinal tumors require personalized treatment strategies due to their heterogeneity and complexity.Multimodal artificial intelligence(AI)addresses this challenge by integrating diverse data sources-including computed tomography(CT),magnetic resonance imaging(MRI),endoscopic imaging,and genomic profiles-to enable intelligent decision-making for individualized therapy.This approach leverages AI algorithms to fuse imaging,endoscopic,and omics data,facilitating comprehensive characterization of tumor biology,prediction of treatment response,and optimization of therapeutic strategies.By combining CT and MRI for structural assessment,endoscopic data for real-time visual inspection,and genomic information for molecular profiling,multimodal AI enhances the accuracy of patient stratification and treatment personalization.The clinical implementation of this technology demonstrates potential for improving patient outcomes,advancing precision oncology,and supporting individualized care in gastrointestinal cancers.Ultimately,multimodal AI serves as a transformative tool in oncology,bridging data integration with clinical application to effectively tailor therapies.
基金supported by the National Natural ScienceFoundation of China(No.81802710).
文摘Objective:This study aimed to examine a novel method for prognostic evaluation of patients with oral squamous cell carcinoma(OSCC)based on the expression of heterogeneous nuclear ribonucleoprotein C(HNRNPC),YTH domain-binding protein 2(YTHDF2),and methyltransferase 14(METTL14).Methods:We obtained the RNA sequence and clinical information of OSCC patients from The Cancer Genome Atlas database.An optical method was established by the least absolute shrinkage and selection operator Cox regression algorithm,which was used to calculate the risk score of every sample.In addition,all samples(n=239)were classified into high-risk(n=119)and low-risk(n=120)groups,and the overall survival(OS)time and clinical characteristics were compared between groups.Moreover,bioinformatics analysis was carried out.Gene set enrichment analysis was performed to investigate the signaling pathways of HNRNPC,YTHDF2,and METTL14.Results:The two groups showed significantly different OS time,tumor grades,tumor stages,and pathologic T stages(P<0.05).The receiver operating characteristic analysis identified that our method was effective and it was more accurate than use of age,gender,tumor grade,tumor stage,pathologic T stage,and pathologic N stage in OSCC prognostic prediction.Gene set enrichment analysis revealed that HNRNPC,YTHDF2,and METTL14 were mainly associated with ubiquitin-mediated proteolysis,cell cycle,RNA degradation,and spliceosome signaling pathways.Conclusion:The method based on the expression of HNRNPC,YTHDF2,and METTL14 can predict the prognosis of patients with OSCC independently,and its prognostic value is better than that of clinicopathological characteristic indicators.
基金supported by Health Commission of Hubei Province Scientific Research Project[WJ2021M217]the Scientific Research Foundation of Jianghan University[2020010].
文摘Hepatocellular carcinoma(HCC)is a common immunogenic malignant tumor.Although the new strategies of immunotherapy and targeted therapy have made considerable progress in the treatment of HCC,the 5-year survival rate of patients is still very low.The identification of new prognostic signatures and the exploration of the immune microenvironment are crucial to the optimization and improvement of molecular therapy strategies.We studied the potential clinical benefits of the inflammation regulator miR-93-3p and mined its target genes.Weighted gene coexpression network analysis(WGCNA),univariate and multivariate COX regression and the LASSO COX algorithm are employed to identify prognostic-related genes and construct multi-gene signature-based risk model and nomogram for survival prediction.Support vector machine(SVM)based Cibersort’s deconvolution algorithm and gene set enrichment analysis(GSEA)is used to evaluate the changes in tumor immune microenvironment and pathway differences.The study found the favorable prognostic performance of miR-93-3p and identified 389 prognostic-related target genes.The risk model based on a novel 5-gene signature(cct5,cdk4,cenpa,dtnbp1 and flvcr1)was developed and has prominent prognostic significance in the training cohort(P<0.0001)and validation cohort(P=0.0016).The nomogram constructed by combining the gene signature and the AJCC stage further improves the survival prediction ability of the gene signature.The infiltration level of multiple immune cells(especially T cells,B cells and macrophages)were positively correlated with the expression of prognostic signature.In addition,we found that gene markers of T cells and B cells is monitored and regulated by prognostic signature.Meanwhile,several GSEA pathways related to the immune system are enriched in the high-risk group.In general,we integrated the WGCNA,LASSO COX and SVM algorithms to develop and verify 5-gene signatures and nomograms related to immune infiltration to improve the survival prediction of patients.
基金Shenzhen Municipal Government’s"Peacock Plan",No.KQTD2016053112051497.
文摘BACKGROUND The novel coronavirus disease 2019(COVID-19)pandemic is a global threat caused by the severe acute respiratory syndrome coronavirus-2.AIM To develop and validate a risk stratification tool for the early prediction of intensive care unit(ICU)admission among COVID-19 patients at hospital admission.METHODS The training cohort included COVID-19 patients admitted to the Wuhan Third Hospital.We selected 13 of 65 baseline laboratory results to assess ICU admission risk,which were used to develop a risk prediction model with the random forest(RF)algorithm.A nomogram for the logistic regression model was built based on six selected variables.The predicted models were carefully calibrated,and the predictive performance was evaluated and compared with two previously published models.RESULTS There were 681 and 296 patients in the training and validation cohorts,respectively.The patients in the training cohort were older than those in the validation cohort(median age:63.0 vs 49.0 years,P<0.001),and the percentages of male gender were similar(49.6%vs 49.3%,P=0.958).The top predictors selected in the RF model were neutrophil-to-lymphocyte ratio,age,lactate dehydrogenase,C-reactive protein,creatinine,D-dimer,albumin,procalcitonin,glucose,platelet,total bilirubin,lactate and creatine kinase.The accuracy,sensitivity and specificity for the RF model were 91%,88%and 93%,respectively,higher than those for the logistic regression model.The area under the receiver operating characteristic curve of our model was much better than those of two other published methods(0.90 vs 0.82 and 0.75).Model A underestimated risk of ICU admission in patients with a predicted risk less than 30%,whereas the RF risk score demonstrated excellent ability to categorize patients into different risk strata.Our predictive model provided a larger standardized net benefit across the major high-risk range compared with model A.CONCLUSION Our model can identify ICU admission risk in COVID-19 patients at admission,who can then receive prompt care,thus improving medical resource allocation.
基金Supported by National Natural Science Foundation of China,No.81902499 and No.81874205Key Research Project of Tongji Hospital Scientific Research Fund,No.2023A18.
文摘Intrahepatic cholangiocarcinoma(ICC)is a primary liver malignancy with increasing global incidence and mortality rates.The 5-year overall survival rate for patients with ICC is approximately 9%.Surgical resection currently represents the only curative treatment option.However,due to the high aggressiveness,insidious onset,and atypical clinical presentation of ICC,many patients either miss the optimal surgical window or experience early postoperative recurrence and metastasis.This poses significant challenges for hepatobiliary surgeons worldwide.Artificial intelligence(AI),as a prominent driver of technological advancement,offers promising new avenues for managing ICC.By leveraging powerful machine learning and deep learning algorithms,AI has demonstrated promising outcomes in ICC diagnosis,particularly in differentiating it from hepatocellular carcinoma,and in predicting critical prognostic factors such as early recurrence,lymph node metastasis,and microvascular invasion.These innovations can support clinical decision-making and ultimately improve patient outcomes.Future efforts should prioritize robust clinical studies evaluating the effectiveness of AI in ICC management.
基金Natural Science Foundation of Liaoning Province(2022-MS-083)Application Basic Research Plan of Liaoning Province(2023JH2/101300084).
文摘Background:As a major histopathological subtype of gastric cancer(GC),stomach adenocarcinoma(STAD)is an important malignant tumor in the digestive system.Increasing evidence also indicates that endoplasmic reticulum(ER)stress plays a pivotal role in the pathogenesis and progression of GC.Therefore,this study aims to screen and identify vital ER stress-related genes that could contribute to the malignant development and poor prognosis for STAD.Methods:A novel ER stress-related risk score signature was developed employingmachine learning techniques.Then,a prognostic prediction nomogram was also built based on the clinicopathological characteristics and the risk score signature.The tumor immune microenvironment characteristics and pathway enrichment analysis in different risk groups were also explored.Furthermore,through the single-cell RNA sequencing(scRNA-seq)analysis,the study highlightedCytochrome P450 Family 19 SubfamilyAMember 1(CYP19A1)as the pivotal research target and detected its effect on cell proliferation by 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyl tetrazoliumbromide(MTT)and the expression of ER stress-related genes by RT-qPCR in STAD.Results:Based on the evaluation of five screened key ER stressrelated genes(AKR1B1,SERPINE1,ADCYAP1,MATN3,CYP19A1),our ER stress-related risk score signature offers a novel approach for assessing STAD prognosis hazards.The novel prognostic prediction nomogram based on the signature also accurately predicted the survival outcomes of patients with STAD.Furthermore,the expression of CYP19A1 is significantly higher in STAD tissues than in normal tissues.High expression of CYP19A1 was related to a poor survival outcome for patients with STAD.Besides,compared to normal gastric epithelial cells,the expression of CYP19A1 was significantly higher in STAD cell lines.Silencing the expression of CYP19A1 significantly inhibited the cell proliferation ability and decreased the expression of ER stress-related genes,including ATF4,DDIT3 and XBP1 in STAD.Conclusions:In conclusion,our study developed a novel prognosis prediction signature and identified the novel diagnostic and therapeutic target CYP19A1 for patients with STAD.
基金supported by the Italian Ministry of Health (’Ricerca Corrente’2020-2021)(to MT)。
文摘Multiple system atrophy is a sporadic,progressive,adult-onset,neurodegenerative disorder characte rized by autonomic dysfunction symptoms,parkinsonian features,and cerebellar signs in va rious combinations.An early diagnosis of multiple system atrophy is of utmost impo rtance for the proper prevention and management of its potentially fatal complications leading to the poor prognosis of these patients.The current diagnostic criteria incorporate several clinical red flags and magnetic resonance imaging marke rs supporting diagnosis of multiple system atrophy.Nonetheless,especially in the early disease stage,it can be challenging to differentiate multiple system atrophy from mimic disorders,in particular Parkinson’s disease.Electromyography of the external anal sphincter represents a useful neurophysiological tool for diffe rential diagnosis since it can provide indirect evidence of Onuf’s nucleus degeneration,which is a pathological hallmark of multiple system atrophy.However,the diagnostic value of external anal sphincter electromyography has been a matter of debate for three decades due to controve rsial reports in the literature.In this review,after a brief ove rview of the electrophysiological methodology,we first aimed to critically analyze the available knowledge on the diagnostic role of external anal sphincter electromyography.We discussed the conflicting evidence on the clinical correlations of neurogenic abnormalities found at external anal sphincter electro myography.Finally,we repo rted recent prognostic findings of a novel classification of electromyography patterns of the external anal sphincter that could pave the way toward the implementation of this neurophysiological technique for survival prediction in patients with multiple system atrophy.
文摘Solid pseudopapillary tumor of the pancreas(SPTP)is a rare neoplasm predom-inantly observed in young females.Pathologically,CTNNB1 mutations,β-catenin nuclear accumulation,and subsequent Wnt-signaling pathway activation are the leading molecular features.Accurate preoperative diagnosis often relies on imaging techniques and endoscopic biopsies.Surgical resection remains the mainstay treatment.Risk models,such as the Fudan Prognostic Index,show promise as predictive tools for assessing the prognosis of SPTP.Establishing three types of metachronous liver metastasis can be beneficial in tailoring individu-alized treatment and follow-up strategies.Despite advancements,challenges persist in understanding its etiology,establishing standardized treatments for unresectable or metastatic diseases,and developing a widely recognized grading system.This comprehensive review aims to elucidate the enigma by consolidating current knowledge on the epidemiology,clinical presentation,pathology,molecular characteristics,diagnostic methods,treatment options,and prognostic factors.
文摘Background:Tumor heterogeneity is closely related to the occurrence,progression and recurrence of renal clear cell carcinoma(ccRCC),making early diagnosis and effective treatment difficult.DNA methylation is an important regulator of gene expression and can affect tumor heterogeneity.Methods:In this study,we investigated the prognostic value of subtypes based on DNA methylation status in 506 ccRCC samples with paired clinical data from the TCGA database.Differences in DNA methylation levels were associated with differences in T,N and M categories,age,stage and prognosis.Finally,the samples were divided into the training group and the testing group according to 450K and 27K.Univariate and multivariate Cox regression analysis was used to construct the prediction model in the training group,and the model was verified and evaluated in the testing group.Results:By univariate Cox regression analysis,21,122 methylation sites and 6,775 CpG sites were identified as potential DNA methylation biomarkers for overall survival of ccRCC patients(P<0.05).3,050 CpG sites independently associated with prognosis were identified with T,N,M,stage and age as covariables.Consensus cluster of 3,050 potential prognostic methylation sites was used to identify different DNA methylation subsets of ccRCC for prognostic purposes.We performed functional enrichment analysis on these 3,640 genes and identified 75 significantly enriched pathways(P<0.05).We then researched the expression of methylated genes in subgroups.Verifing with the training set,suggesting that DNA methylation levels generally reflect the expression of these genes.Conclusion:Based on TCGA database and a series of bioinformatics methods,We identified prognostic specific methylation sites and established prognostic prediction models for ccRCC patients.This model helps to identify novel biomarkers,precision drug targets and disease molecular subtypes in patients with ccRCC.Therefore,this model may be useful in predicting the prognosis,clinical diagnosis and management of patients with different epigenetic subtypes of ccRCC.
基金supported by Medical Scientific Research Foundation of Chongqing of China(2022MSXM048).
文摘Background:Cholangiocarcinoma(CCA)is highly malignant and has a poor prognosis has a high malignant degree and poor prognosis.The purpose of this study is to develop a new prognostic model based on genes related to the tumor microenvironment(TME).Methods:Derived from the discerned differentially expressed genes within The Cancer Genome Atlas(TCGA)dataset,this investigation employed the methodology of weighted gene co-expression network analysis(WGCNA)to ascertain gene co-expressed modules intricately linked to the Tumor Microenvironment(TME)among Cholangiocarcinoma(CCA)patients.The genes associated with prognosis,as identified through Cox regression analysis,were employed in the formulation of a predictive model.This model underwent validation,leading to the development of a risk score formula and nomogram.Concurrently,we validated the model’s reliability using data from CCA patients in the Gene Expression Omnibus(GEO)database(accession:GSE107943).Results:6139 DEGs were divided into 10 co-expressed gene modules using WGCNA.Among these,two modules(blue module with 832 genes and brown module with 1379 genes)showed high correlation with the TME.Five prognostic genes(BNIP3,COL4A3,SPRED3,CEBPB,PLOD2)were identified through Cox regression analysis,and a prognostic model and risk score formula were developed based on these genes.Risk score formula:Risk score=BNIP3×1.70520-COL4A3×2.39815+SPRED3×1.17936+CEBPB×0.40456+PLOD2×0.24785.Kaplan-Meier survival analysis revealed that the survival probabilities of the low-risk group were significantly higher than those of the high-risk group.Furthermore,the related evaluation indexes suggested that the model exhibited strong predictive ability.Conclusion:The prognostic model,based on five TME-related genes(BNIP3,COL4A3,SPRED3,CEBPB,PLOD2),could accurately assess the prognosis of CCA patients to aid in guiding clinical decisions.
文摘Epigenetics is the main mechanism that controls transcription of specific genes with no changes in the underlying DNA sequences. Epigenetic alterations lead to abnormal gene expression patterns that contribute to carcinogenesis and persist throughout disease progression. Because of the reversible nature, epigenetic modifications emerge as promising anticancer drug targets. Several compounds have been developed to reverse the aberrant activities of enzymes involved in epigenetic regulation, and some of them show encouraging results in both preclinical and clinical studies. In this article, we comprehensively review the up-to-date roles of epigenetics in the development and progression of prostate cancer. We especially focus on three epigenetic mechanisms: DNA methylation, histone modifications, and noncoding RNAs. We elaborate on current models/theories that explain the necessity of these epigenetic programs in driving the malignant phenotypes of prostate cancer cells. In particular, we elucidate how certain epigenetic regulators crosstalk with critical biological pathways, such as androgen receptor (AR) signaling, and how the cooperation dynamically controls cancer-oriented transcriptional profiles. Restoration of a “normal” epigenetic landscape holds promise as a cure for prostate cancer, so we concluded by highlighting particular epigenetic modifications as diagnostic and prognostic biomarkers or new therapeutic targets for treatment of the disease.
