we critically review the authors’perspective and analyze the relevance of the results obtained in the original article of clinical research by Liu et al.We consider that additional factors associated with colon cance...we critically review the authors’perspective and analyze the relevance of the results obtained in the original article of clinical research by Liu et al.We consider that additional factors associated with colon cancer progression have recently been described in extensive clinical research,and should be included in this analysis to achieve a more accurate prognosis.These factors include inflammation,gut microbiota composition,immune status and nutritional balance,as they influence the post-surgical survival profile of patients with stage II colorectal cancer.We also address the clinical implementation and limitations of these analyses.Evaluation of the patient´s entire context is essential for selection of the most appropriate therapy.展开更多
As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigat...As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.展开更多
According to the Japanese Ministry of Health,Labour,and Welfare,14.2%of people were aged>75 years in Japan in 2018,and this number continues to rise.With population aging,the incidence of congestive heart failure(C...According to the Japanese Ministry of Health,Labour,and Welfare,14.2%of people were aged>75 years in Japan in 2018,and this number continues to rise.With population aging,the incidence of congestive heart failure(CHF)is also increasing.[1–3]Reports have shown that the presence of cognitive impairment(CI)in patients with CHF is associated with poor prognosis,[4–6]and the degree of CI is related to CHF severity.展开更多
Dear Editor,Lung cancer is a major global health concern,with 2.2 million patients diagnosed in 2020.Non-small cell lung cancer(NSCLC)accounts for 80%of these cases,primarily comprising two subtypes:lung adenocarcinom...Dear Editor,Lung cancer is a major global health concern,with 2.2 million patients diagnosed in 2020.Non-small cell lung cancer(NSCLC)accounts for 80%of these cases,primarily comprising two subtypes:lung adenocarcinoma(LUAD)and squamous cell carcinoma(LUSC)[1].Researchers use immunohisto-chemistry,next-generation sequencing,and single-cell RNA sequencing to study genetic alterations,tumor heterogeneity,and tumor microenvironments,aiming to identify potential therapeutic options for specific NSCLC subtypes[2].展开更多
Objective:Small cell lung cancer(SCLC)is commonly recognized as the most fatal lung cancer type.Despite substantial advances in immune checkpoint blockade therapies for treating solid cancers,their benefits are limite...Objective:Small cell lung cancer(SCLC)is commonly recognized as the most fatal lung cancer type.Despite substantial advances in immune checkpoint blockade therapies for treating solid cancers,their benefits are limited to a minority of patients with SCLC.In the present study,novel indicators for predicting the outcomes and molecular targets for SCLC treatment were elucidated.Methods:We conducted bioinformatics analysis to identify the key genes associated with tumor-infiltrating lymphocytes in SCLC.The functional role of the key gene identified in SCLC was determined both in vitro and in vivo.Results:A significant correlation was observed between patient survival and CD56dim natural killer(NK)cell proportion.Furthermore,we noted that the hub gene ubiquitin-specific protease 1(USP1)is closely correlated with both CD56dim NK cells and overall survival in SCLC.Bioinformatics analysis revealed that USP1 is upregulated in SCLC.In addition,gene set enrichment analysis revealed that USP1 overexpression hinders NK cell-mediated immune responses.By co-cultivating NK-92 cells with SCLC cells,we demonstrated that NK cell cytotoxicity against SCLC could be improved either via USP1 knock-down or pharmacological inhibition.Furthermore,using a nude-mice xenograft tumor model,we noted that USP1 inhibition effectively suppressed tumor proliferation and increased the expression of NK cell-associated markers.Conclusions:Our study findings highlight the importance of NK cells in regulating SCLC.USP1 overexpression can inhibit NK cell-mediated immunity;therefore,USP1 may serve not only as a prognostic biomarker but also as a potential molecular target of SCLC therapy.展开更多
Objective INF2 is a member of the formins family.Abnormal expression and regulation of INF2 have been associated with the progression of various tumors,but the expression and role of INF2 in hepatocellular carcinoma(H...Objective INF2 is a member of the formins family.Abnormal expression and regulation of INF2 have been associated with the progression of various tumors,but the expression and role of INF2 in hepatocellular carcinoma(HCC)remain unclear.HCC is a highly lethal malignant tumor.Given the limitations of traditional treatments,this study explored the expression level,clinical value and potential mechanism of INF2 in HCC in order to seek new therapeutic targets.Methods In this study,we used public databases to analyze the expression of INF2 in pan-cancer and HCC,as well as the impact of INF2 expression levels on HCC prognosis.Quantitative real time polymerase chain reaction(RT-qPCR),Western blot,and immunohistochemistry were used to detect the expression level of INF2 in liver cancer cells and human HCC tissues.The correlation between INF2 expression and clinical pathological features was analyzed using public databases and clinical data of human HCC samples.Subsequently,the effects of INF2 expression on the biological function and Drp1 phosphorylation of liver cancer cells were elucidated through in vitro and in vivo experiments.Finally,the predictive value and potential mechanism of INF2 in HCC were further analyzed through database and immunohistochemical experiments.Results INF2 is aberrantly high expression in HCC samples and the high expression of INF2 is correlated with overall survival,liver cirrhosis and pathological differentiation of HCC patients.The expression level of INF2 has certain diagnostic value in predicting the prognosis and pathological differentiation of HCC.In vivo and in vitro HCC models,upregulated expression of INF2 triggers the proliferation and migration of the HCC cell,while knockdown of INF2 could counteract this effect.INF2 in liver cancer cells may affect mitochondrial division by inducing Drp1 phosphorylation and mediate immune escape by up-regulating PD-L1 expression,thus promoting tumor progression.Conclusion INF2 is highly expressed in HCC and is associated with poor prognosis.High expression of INF2 may promote HCC progression by inducing Drp1 phosphorylation and up-regulation of PD-L1 expression,and targeting INF2 may be beneficial for HCC patients with high expression of INF2.展开更多
BACKGROUND Mitochondrial genes are involved in tumor metabolism in ovarian cancer(OC)and affect immune cell infiltration and treatment responses.AIM To predict prognosis and immunotherapy response in patients diagnose...BACKGROUND Mitochondrial genes are involved in tumor metabolism in ovarian cancer(OC)and affect immune cell infiltration and treatment responses.AIM To predict prognosis and immunotherapy response in patients diagnosed with OC using mitochondrial genes and neural networks.METHODS Prognosis,immunotherapy efficacy,and next-generation sequencing data of patients with OC were downloaded from The Cancer Genome Atlas and Gene Expression Omnibus.Mitochondrial genes were sourced from the MitoCarta3.0 database.The discovery cohort for model construction was created from 70% of the patients,whereas the remaining 30% constituted the validation cohort.Using the expression of mitochondrial genes as the predictor variable and based on neural network algorithm,the overall survival time and immunotherapy efficacy(complete or partial response)of patients were predicted.RESULTS In total,375 patients with OC were included to construct the prognostic model,and 26 patients were included to construct the immune efficacy model.The average area under the receiver operating characteristic curve of the prognostic model was 0.7268[95% confidence interval(CI):0.7258-0.7278]in the discovery cohort and 0.6475(95%CI:0.6466-0.6484)in the validation cohort.The average area under the receiver operating characteristic curve of the immunotherapy efficacy model was 0.9444(95%CI:0.8333-1.0000)in the discovery cohort and 0.9167(95%CI:0.6667-1.0000)in the validation cohort.CONCLUSION The application of mitochondrial genes and neural networks has the potential to predict prognosis and immunotherapy response in patients with OC,providing valuable insights into personalized treatment strategies.展开更多
Hepatocellular carcinoma(HCC)represents a major global health burden,ranking third as the leading cause of cancer-related mortality worldwide.This compre-hensive review examines the substantial body of evidence linkin...Hepatocellular carcinoma(HCC)represents a major global health burden,ranking third as the leading cause of cancer-related mortality worldwide.This compre-hensive review examines the substantial body of evidence linking modifiable lifestyle factors to HCC pathogenesis and clinical outcomes.We systematically evaluate dietary components,alcohol consumption patterns,tobacco use,physical activity levels,and emerging factors including metabolic disorders,psychological stress,and sleep disturbances.These factors collectively influence hepatocarcino-genesis through diverse biological mechanisms,including genotoxic damage,metabolic dysregulation,chronic inflammatory responses,and gut microbiome-mediated pathways.The accumulated data underscore the urgent need to inte-grate lifestyle interventions into multidisciplinary HCC management.展开更多
The published article titled“lncRNA FEZF1-AS1 Is Associated with Prognosis in Lung Adenocarcinoma and Promotes Cell Proliferation,Migration,and Invasion”has been retracted from Oncology Research,Vol.27,No.1,2019,pp...The published article titled“lncRNA FEZF1-AS1 Is Associated with Prognosis in Lung Adenocarcinoma and Promotes Cell Proliferation,Migration,and Invasion”has been retracted from Oncology Research,Vol.27,No.1,2019,pp.39–45.展开更多
Patients with chronic kidney disease(CKD),particularly those undergoingmaintenance hemodialysis(MHD),often experience mental health issues.Recentstudies have indicated a significantly elevated prevalence of anxiety an...Patients with chronic kidney disease(CKD),particularly those undergoingmaintenance hemodialysis(MHD),often experience mental health issues.Recentstudies have indicated a significantly elevated prevalence of anxiety and depressioncoupled with reduced resilience in this population.The complex interactionbetween these three factors is exacerbated by multiple negative influences.This study reviews recent advances in research on the relationship betweenmental health impairment,quality of life(QoL),and prognosis in patients withCKD.The findings revealed that prolonged MHD dependence,economic burdenof healthcare,and other psychological factors diminish patients’resilience andintensify negative emotions(e.g.,anxiety and depression).The interactionsbetween negative emotions and physiology create a vicious cycle,deterioratingQoL and clinical outcomes.We propose that patients with long-term MHDdependentCKD should be classified as a high-risk group for mental healthimpairments that need regular psychological screening and personalized psychomedicalinterventions.This integrated management model may help improvenegative emotions and disrupt the bidirectional psychophysiological interplay,offering a novel clinical pathway for improving the QoL and prognosis.展开更多
BACKGROUND The cellular prion protein(PrPC),traditionally associated with neurodegenerative disorders,plays an important role in cancer progression and metastasis by inhibiting apoptosis.AIM To investigate the influen...BACKGROUND The cellular prion protein(PrPC),traditionally associated with neurodegenerative disorders,plays an important role in cancer progression and metastasis by inhibiting apoptosis.AIM To investigate the influence of PrPC expression in cholangiocarcinoma(CCA)on patient outcomes following surgical resection.METHODS Patients who underwent curative surgical resection for either intrahepatic or hilar CCA were enrolled in this retrospective study.Based on the immunohistochemical staining results of the surgical specimens,patients were categorized into two groups:The low PrPC group(negative or 1+)and the high PrPC group(2+or 3+).Survival analyses,including overall survival and recurrence-free survival,were conducted using the Kaplan-Meier method and compared using the log-rank test.RESULTS In total,seventy-six patients diagnosed with CCA(39 with intrahepatic and 37 with hilar CCA)underwent curative hepatectomy from January 2011 to November 2021.Among these patients,38(50%)demonstrated high PrPC expression,whereas the remaining 38(50%)showed low expression of PrPC.During a median follow-up period of 31.2 months(range:1 to 137 months),the high PrPC group had a significantly shorter median overall survival than the low PrPC group(40.4 months vs 137.9 months,respectively;P=0.041).Moreover,the high PrPC group had a significantly shorter median recurrence-free survival than the low PrPC group(13.3 months vs 23.8 months,respectively;P=0.026).CONCLUSION PrPC expression is significantly associated with early recurrence and decreased survival period in CCA patients following surgical resection.Thus,PrPC may be used as a prognostic factor in treatment planning.展开更多
Background:Kidney renal clear cell carcinoma(KIRC),a prevalent urological malignancy,represents about 3%of all adult malignancies.KIRC,accounting for~75%of renal malignancies,has poor prognosis in metastatic stages.Id...Background:Kidney renal clear cell carcinoma(KIRC),a prevalent urological malignancy,represents about 3%of all adult malignancies.KIRC,accounting for~75%of renal malignancies,has poor prognosis in metastatic stages.Identifying robust prognostic markers remains urgent.Block of proliferation 1(BOP1),a WD40-repeat protein,is implicated in cancer pathogenesis,but its role in KIRC is unclear.This study aimed to characterize BOP1 expression in KIRC and evaluate its prognostic value.Methods:BOP1 transcriptional levels were assessed through TCGA-KIRC RNA sequencing datasets.ROC curve construction was implemented via R statistical packages for diagnostic evaluation.Patient survival outcomes were visualized through Kaplan-Meier plotting with log-rank testing.Multivariate logistic regression models quantified associations between BOP1 expression and clinicopathological parameters.TIMER algorithm analyzed immune microenvironment composition.Genomic alterations and epigenetic modifications were investigated using cBioPortal and MethSurv platforms respectively.BOP1 protein levels in 786-O clear cell renal cell carcinoma(ccRCC)versus HK-2(normal renal)cell lines were validated by immunoblotting.Results:Evaluation of the TCGA database demonstrated that BOP1 mRNA abundance was higher in tumor specimens than in corresponding adjacent tissues.Patients with KIRC who had high BOP1 expression had differential overall survival(OS),disease-specific survival(DSS),and disease-free interval(DFI).BOP1 expression accurately recognised tumour tissues versus normal tissues(AUC=0.858),and the area under the ROCs for survival at 1,3,and 5 years were all greater than 0.6.The BOP1 gene variant rate was<1%.Out of the 15 DNA methylation CpG sites examined,7 exhibited prognostic significance in KIRC.BOP1 displayed a distinct relationship with immune cell infiltration in KIRC.The 786-O experimental group exhibited substantially higher BOP1 expression,as confirmed by Western blot detection.Conclusion:This study indicates that heightened BOP1 expression is linked to an adverse prognosis in KIRC,establishing it as an independent risk factor for this disease.These findings establish BOP1 as a novel and independent prognostic biomarker for KIRC,offering potential clinical utility for risk stratification and personalized therapeutic strategies.展开更多
BACKGROUND Studies on the application of recombinant human endostatin(RH-endostatin)intraperitoneal perfusion in gastric cancer(GC)with malignant ascites are limited.AIM To explore the effectiveness,prognosis,and safe...BACKGROUND Studies on the application of recombinant human endostatin(RH-endostatin)intraperitoneal perfusion in gastric cancer(GC)with malignant ascites are limited.AIM To explore the effectiveness,prognosis,and safety of intraperitoneal RH-endostatin perfusion in treating patients with GC and malignant ascites.METHODS Patients with GC and malignant ascites were divided into the cisplatin intraperi-toneal perfusion(control group)group and the cisplatin combined with RH-endostatin intraperitoneal perfusion group(RH-endostatin group).Efficient ascites control,overall survival(OS),quality of life,and adverse events were observed,and possible influencing factors on prognosis outcomes analyzed.RESULTS We identified no significant differences in baseline characteristics between the control and RH-endostatin groups.The latter group had higher ascites control rates than the control group.Treatment methods were identified as an independent OS factor.Clinically,RH-endostatin-treated patients had significantly improved OS rates when compared with control patients,particularly in those with small and moderate ascites volumes.Quality of life improvements in control patients were significantly lower when compared with RH-endostatin patients.Adverse events were balanced between the groups.CONCLUSION Overall,intraperitoneal RH-endostatin improved treatment efficacy and prolonged prognosis in patients with GC and malignant ascites.This approach may benefit further clinical applications for treating GC.展开更多
Objective To investigate the combined effects of thymidine phosphorylase(TYMP)and sine oculis homeobox homologue 1(Six1)on the tumor microenvironment and their role in promoting metastasis in gastric cancer(GC).Method...Objective To investigate the combined effects of thymidine phosphorylase(TYMP)and sine oculis homeobox homologue 1(Six1)on the tumor microenvironment and their role in promoting metastasis in gastric cancer(GC).Methods A total of 674 GC patients who underwent surgical resection were enrolled.Correlations between TYMP/Six1 expression and the clinicopathological characteristics and overall survival of patients were analysed.The expression of TYMP,Six1 and vascular endothelial growth factor C(VEGFc)was quantified via immunohistochemistry and quantitative real-time polymerase chain reaction.Cell transfection,wound-healing assays and bioinformatics analyses were used to explore the potential underlying mechanisms involved.Results Compared with the other groups,the Six1+/TYMP+patients exhibited poor differentiation,advanced tumor stage,a higher rate of lymphatic vessel invasion and shorter survival.Additionally,the protein expression of TYMP and Six1 was positively correlated with the VEGFc level.A significant increase in VEGFc expression was observed in cells transfected with TYMP,Six1,and TYMP/Six1 vectors.The results of the wound-healing assay indicated that the synergistic effect of TYMP and Six1 enhanced the migratory ability of GC cells.Furthermore,bioinformatics analysis revealed that TYMP and Six1 were positively correlated with immunosuppressive immune cell subsets and elevated the expression of inhibitory immune checkpoints in GC.Conclusions The combination of TYMP and Six1 is a good predictive and prognostic biomarker for GC.This combination enhances the expression of VEGFc,facilitates the invasion of GC cells,and may be linked to inhibitory immune cells and the tumor immune microenvironment.展开更多
BACKGROUND Liver transplantation(LT)is recognized as an effective approach that offers survival benefits for patients with acute-on-chronic liver failure(ACLF).However,controversies remain regarding the LT selection c...BACKGROUND Liver transplantation(LT)is recognized as an effective approach that offers survival benefits for patients with acute-on-chronic liver failure(ACLF).However,controversies remain regarding the LT selection criteria,and meta-analyses reporting overall survival outcomes across different ACLF severity grades are lacking.AIM To depict a comprehensive postoperative picture of patients with ACLF of varying severity and contribute to updating LT selection.METHODS Systematic searches in Web of Science,EMBASE,PubMed,and Cochrane databases were performed,from inception to December 26,2023,for studies exploring post-transplant outcomes among ACLF patients,stratified by severity grades as identified by the European Association for the Study of the Liver-Chronic Liver Failure criteria.The primary outcome of interest was the survival rate within one year,with post-transplant complications as secondary outcomes.Additionally,the subgroup analysis examined region-specific one-year survival rates.RESULTS A total of 17 studies involving 28025 participants were included.Patients with ACLF-1 and ACLF-2 have favorable survival within one year,with survival rates reaching 87%[95%confidence interval(CI):84%-91%]and 86%(95%CI:81%-91%),respectively.Despite the relatively lower survival(73%,95%CI:66%-80%)and higher incidence of infection(48%,95%CI:29%-67%)observed in ACLF-3 patients,their survival exceeds that of those who do not undergo LT.Moreover,post-transplant survival was highest in North America across all ACLF grades.CONCLUSION LT can provide survival advantages for ACLF patients.To optimize the utilization of scarce donor organs and improve prognosis,comprehensive preoperative health evaluations are essential,especially for ACLF-3 patients.展开更多
BACKGROUND Colorectal cancer(CRC)is a common malignancy that has become a global burden.The prognostic prediction of CRC patients on the basis of inflammatory biomarkers and nutritional biomarkers has shown some poten...BACKGROUND Colorectal cancer(CRC)is a common malignancy that has become a global burden.The prognostic prediction of CRC patients on the basis of inflammatory biomarkers and nutritional biomarkers has shown some potential but has not been fully explored.AIM To develop and validate a prognostic model for CRC based on inflammation and nutrition-related biomarkers and to evaluate its predictive value for patient outcomes.METHODS Patients were randomized at a 3:2 ratio into a training cohort(n=282)or a validation cohort(n=188).To identify the optimal prognostic factors for constructing the risk score(RS),LASSO Cox regression analysis was conducted.The association between the RS and overall survival(OS)was evaluated using receiver operating characteristic(ROC)curves and Kaplan-Meier(K-M)survival analysis.Independent risk factors were screened by multivariate Cox regression analysis.Nomograms were constructed and validated on the basis of these factors.RESULTS In the training cohort,univariate analysis of all the inflammatory and nutritional biomarkers demonstrated some predictive value.A LASSO-Cox analysis included four biomarkers and constructed an RS.Through ROC analysis,the area under the prognostic curve was 0.795.K-M survival curve analyses revealed that the five-year OS was significantly greater in the Low-RS group than in the High-RS group(P<0.001).Multivariate analysis demonstrated that the degree of differentiation(P=0.001),degree of nerve invasion(P=0.022),and RS(P<0.001)were independent risk factors.We constructed a nomogram to predict the OS of CRC patients and validated it in a separate cohort.The calibration curve showed high accuracy.Additionally,decision curve analysis for 1-year,3-year,and 5-year survival probabilities indicated significant clinical utility in predicting survival outcomes.CONCLUSION This study developed a nomogram based on the RS to predict the OS of CRC patients.This nomogram can guide treatment decisions and enable the formulation of personalized follow-up strategies on the basis of predicted recurrence risk,aiming to improve long-term prognosis.展开更多
Cancer is a major threat to human health worldwide.Colorectal cancer(CRC),a highly prevalent malignant tumor,poses a significant public health challenge.Therefore,the identification of effective biomarkers is of great...Cancer is a major threat to human health worldwide.Colorectal cancer(CRC),a highly prevalent malignant tumor,poses a significant public health challenge.Therefore,the identification of effective biomarkers is of great significance[1].The NFKBIE gene encodes an inhibitor of nuclear factorκBε(IkBε).IκBε,a key regulator of the NF-κB signaling pathway,is closely associated with tumorigenesis.However,their roles in CRC remain unclear[2].Pan-cancer research is crucial for accelerating the identification of biomarkers and translational medical research,as it can reveal molecular commonalities and differences among different tumor types[3].展开更多
Hypertrophic cardiomyopathy(HCM)is an autosomal dominant inherited cardiomyopathy characterized by left ventricular hypertrophy.It is one of the chief causes of sudden cardiac death in younger people and athletes.Mole...Hypertrophic cardiomyopathy(HCM)is an autosomal dominant inherited cardiomyopathy characterized by left ventricular hypertrophy.It is one of the chief causes of sudden cardiac death in younger people and athletes.Molecular-genetic studies have confirmed that the vast majority of HCM is caused by mutations in genes encoding sarcomere proteins.HCM has a relatively wide phenotypic heterogeneity,varying from asymptomatic to sudden cardiac death,because of the many different mutations and pathogenic genes underlying it.Many studies have explored the clinical symptoms and prognosis of HCM,emphasizing the importance of genotype in evaluating patient prognosis and guiding the clinical management of HCM.To elaborate the main pathogenic genes and phenotypic prognosis in HCM to promote a better understanding of this genetic disease.Retrospective analysis of literature to evaluate the association between underlying gene mutations and clinical phenotypes in HCM patients.As sequencing technology advances,the pathogenic gene mutation spectrum and phenotypic characteristics of HCM are gradually becoming clearer.HCM is a widespread inherited disease with a highly variable clinical phenotype.The precise mechanisms linking known pathogenic gene mutations and the clinical course of this heterogeneous condition remain elusive.展开更多
Hepatocellular carcinoma(HCC)is a prevalent and aggressive liver cancer that poses significant challenges in diagnosis and prognosis.Recent advancements in radiomics and machine learning(ML)offer promising solutions t...Hepatocellular carcinoma(HCC)is a prevalent and aggressive liver cancer that poses significant challenges in diagnosis and prognosis.Recent advancements in radiomics and machine learning(ML)offer promising solutions to enhance the accuracy of HCC diagnosis,treatment response prediction,and survival prognosis.Radiomics,which extracts quantitative features from medical images,captures the complex tumor heterogeneity that is often undetectable with traditional imaging methods.When combined with ML algorithms,these features can be used to differentiate between various stages of HCC,predict treatment outcomes,and assess long-term survival.This review explores key radiomic features,including texture,shape,and intensity,and their integration with ML techniques like binary classification models,XGBoost,LightGBM,and deep learning architectures.We also discuss the challenges faced in model interpretation,data heterogeneity,and the integration of multi-modal data.Despite the promising potential of these technologies,the clinical adoption of radiomics and ML models in HCC management will require overcoming these obstacles through standardization and improved interpretability.展开更多
We read with great interest the study by Huang et al.Cholangiocarcinoma(CC)is the second most common type of primary liver tumor worldwide.Although surgical resection remains the primary treatment for this disease,alm...We read with great interest the study by Huang et al.Cholangiocarcinoma(CC)is the second most common type of primary liver tumor worldwide.Although surgical resection remains the primary treatment for this disease,almost 50%of patients experience relapse within 2 years after surgery,which negatively affects their prognosis.Key predictors can be used to identify several factors(e.g.,tumor size,tumor location,tumor stage,nerve invasion,the presence of intravascular emboli)and their correlations with long-term survival and the risk of postoperative morbidity.In recent years,artificial intelligence(AI)has become a new tool for prognostic assessment through the integration of multiple clinical,surgical,and imaging parameters.However,a crucial question has arisen:Are we ready to trust AI with respect to clinical decisions?The study by Huang et al demonstrated that AI can predict preoperative textbook outcomes in patients with CC and highlighted the precision of machine learning algorithms using useful prognostic factors.This letter to the editor aimed to explore the challenges and potential impact of AI and machine learning in the prognostic assessment of patients with CC.展开更多
基金Supported by Consejo Nacional de Investigaciones Científicas y Técnicas,No.PIP11220200103061COAgencia Nacional de promoción Científica y Tecnológica,No.PICT-2020-SERIEA-03440Universidad Nacional del Sur,No.PGI 24/B303 and No.PGI 24/ZB01.
文摘we critically review the authors’perspective and analyze the relevance of the results obtained in the original article of clinical research by Liu et al.We consider that additional factors associated with colon cancer progression have recently been described in extensive clinical research,and should be included in this analysis to achieve a more accurate prognosis.These factors include inflammation,gut microbiota composition,immune status and nutritional balance,as they influence the post-surgical survival profile of patients with stage II colorectal cancer.We also address the clinical implementation and limitations of these analyses.Evaluation of the patient´s entire context is essential for selection of the most appropriate therapy.
基金supported by the National Natural Science Foundation of China(22379021 and 22479021)。
文摘As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.
文摘According to the Japanese Ministry of Health,Labour,and Welfare,14.2%of people were aged>75 years in Japan in 2018,and this number continues to rise.With population aging,the incidence of congestive heart failure(CHF)is also increasing.[1–3]Reports have shown that the presence of cognitive impairment(CI)in patients with CHF is associated with poor prognosis,[4–6]and the degree of CI is related to CHF severity.
基金support through Manipal University Jaipur for the Enhanced Seed Grant under the Endowment Fund(Grant No.E3/2023-24/QE-04-05).
文摘Dear Editor,Lung cancer is a major global health concern,with 2.2 million patients diagnosed in 2020.Non-small cell lung cancer(NSCLC)accounts for 80%of these cases,primarily comprising two subtypes:lung adenocarcinoma(LUAD)and squamous cell carcinoma(LUSC)[1].Researchers use immunohisto-chemistry,next-generation sequencing,and single-cell RNA sequencing to study genetic alterations,tumor heterogeneity,and tumor microenvironments,aiming to identify potential therapeutic options for specific NSCLC subtypes[2].
基金supported by grants from the Dongguan Science and Technology of Social Development Program(No.20231800940192)the Talent Development Foundation of the First Dongguan Affiliated Hospital of Guangdong Medical University(No.PU2023002).
文摘Objective:Small cell lung cancer(SCLC)is commonly recognized as the most fatal lung cancer type.Despite substantial advances in immune checkpoint blockade therapies for treating solid cancers,their benefits are limited to a minority of patients with SCLC.In the present study,novel indicators for predicting the outcomes and molecular targets for SCLC treatment were elucidated.Methods:We conducted bioinformatics analysis to identify the key genes associated with tumor-infiltrating lymphocytes in SCLC.The functional role of the key gene identified in SCLC was determined both in vitro and in vivo.Results:A significant correlation was observed between patient survival and CD56dim natural killer(NK)cell proportion.Furthermore,we noted that the hub gene ubiquitin-specific protease 1(USP1)is closely correlated with both CD56dim NK cells and overall survival in SCLC.Bioinformatics analysis revealed that USP1 is upregulated in SCLC.In addition,gene set enrichment analysis revealed that USP1 overexpression hinders NK cell-mediated immune responses.By co-cultivating NK-92 cells with SCLC cells,we demonstrated that NK cell cytotoxicity against SCLC could be improved either via USP1 knock-down or pharmacological inhibition.Furthermore,using a nude-mice xenograft tumor model,we noted that USP1 inhibition effectively suppressed tumor proliferation and increased the expression of NK cell-associated markers.Conclusions:Our study findings highlight the importance of NK cells in regulating SCLC.USP1 overexpression can inhibit NK cell-mediated immunity;therefore,USP1 may serve not only as a prognostic biomarker but also as a potential molecular target of SCLC therapy.
文摘Objective INF2 is a member of the formins family.Abnormal expression and regulation of INF2 have been associated with the progression of various tumors,but the expression and role of INF2 in hepatocellular carcinoma(HCC)remain unclear.HCC is a highly lethal malignant tumor.Given the limitations of traditional treatments,this study explored the expression level,clinical value and potential mechanism of INF2 in HCC in order to seek new therapeutic targets.Methods In this study,we used public databases to analyze the expression of INF2 in pan-cancer and HCC,as well as the impact of INF2 expression levels on HCC prognosis.Quantitative real time polymerase chain reaction(RT-qPCR),Western blot,and immunohistochemistry were used to detect the expression level of INF2 in liver cancer cells and human HCC tissues.The correlation between INF2 expression and clinical pathological features was analyzed using public databases and clinical data of human HCC samples.Subsequently,the effects of INF2 expression on the biological function and Drp1 phosphorylation of liver cancer cells were elucidated through in vitro and in vivo experiments.Finally,the predictive value and potential mechanism of INF2 in HCC were further analyzed through database and immunohistochemical experiments.Results INF2 is aberrantly high expression in HCC samples and the high expression of INF2 is correlated with overall survival,liver cirrhosis and pathological differentiation of HCC patients.The expression level of INF2 has certain diagnostic value in predicting the prognosis and pathological differentiation of HCC.In vivo and in vitro HCC models,upregulated expression of INF2 triggers the proliferation and migration of the HCC cell,while knockdown of INF2 could counteract this effect.INF2 in liver cancer cells may affect mitochondrial division by inducing Drp1 phosphorylation and mediate immune escape by up-regulating PD-L1 expression,thus promoting tumor progression.Conclusion INF2 is highly expressed in HCC and is associated with poor prognosis.High expression of INF2 may promote HCC progression by inducing Drp1 phosphorylation and up-regulation of PD-L1 expression,and targeting INF2 may be beneficial for HCC patients with high expression of INF2.
基金Supported by National Key Technology Research and Developmental Program of China,No.2022YFC2704400 and No.2022YFC2704405.
文摘BACKGROUND Mitochondrial genes are involved in tumor metabolism in ovarian cancer(OC)and affect immune cell infiltration and treatment responses.AIM To predict prognosis and immunotherapy response in patients diagnosed with OC using mitochondrial genes and neural networks.METHODS Prognosis,immunotherapy efficacy,and next-generation sequencing data of patients with OC were downloaded from The Cancer Genome Atlas and Gene Expression Omnibus.Mitochondrial genes were sourced from the MitoCarta3.0 database.The discovery cohort for model construction was created from 70% of the patients,whereas the remaining 30% constituted the validation cohort.Using the expression of mitochondrial genes as the predictor variable and based on neural network algorithm,the overall survival time and immunotherapy efficacy(complete or partial response)of patients were predicted.RESULTS In total,375 patients with OC were included to construct the prognostic model,and 26 patients were included to construct the immune efficacy model.The average area under the receiver operating characteristic curve of the prognostic model was 0.7268[95% confidence interval(CI):0.7258-0.7278]in the discovery cohort and 0.6475(95%CI:0.6466-0.6484)in the validation cohort.The average area under the receiver operating characteristic curve of the immunotherapy efficacy model was 0.9444(95%CI:0.8333-1.0000)in the discovery cohort and 0.9167(95%CI:0.6667-1.0000)in the validation cohort.CONCLUSION The application of mitochondrial genes and neural networks has the potential to predict prognosis and immunotherapy response in patients with OC,providing valuable insights into personalized treatment strategies.
基金Supported by Chinese Academy of Medical Sciences Initiative for Innovative Medicine,No.2021-I2M-1-015the National Natural Science Foundation of China,No.82330061 and No.82001937+1 种基金the Peking Union Medical College Graduate Curriculum Informatization Development Special Fund Project,No.2024YXX004the Science and Education Cultivation Fund of the National Cancer and Regional Medical Center of Shanxi Provincial Cancer Hospital,No.TD2023003.
文摘Hepatocellular carcinoma(HCC)represents a major global health burden,ranking third as the leading cause of cancer-related mortality worldwide.This compre-hensive review examines the substantial body of evidence linking modifiable lifestyle factors to HCC pathogenesis and clinical outcomes.We systematically evaluate dietary components,alcohol consumption patterns,tobacco use,physical activity levels,and emerging factors including metabolic disorders,psychological stress,and sleep disturbances.These factors collectively influence hepatocarcino-genesis through diverse biological mechanisms,including genotoxic damage,metabolic dysregulation,chronic inflammatory responses,and gut microbiome-mediated pathways.The accumulated data underscore the urgent need to inte-grate lifestyle interventions into multidisciplinary HCC management.
文摘The published article titled“lncRNA FEZF1-AS1 Is Associated with Prognosis in Lung Adenocarcinoma and Promotes Cell Proliferation,Migration,and Invasion”has been retracted from Oncology Research,Vol.27,No.1,2019,pp.39–45.
文摘Patients with chronic kidney disease(CKD),particularly those undergoingmaintenance hemodialysis(MHD),often experience mental health issues.Recentstudies have indicated a significantly elevated prevalence of anxiety and depressioncoupled with reduced resilience in this population.The complex interactionbetween these three factors is exacerbated by multiple negative influences.This study reviews recent advances in research on the relationship betweenmental health impairment,quality of life(QoL),and prognosis in patients withCKD.The findings revealed that prolonged MHD dependence,economic burdenof healthcare,and other psychological factors diminish patients’resilience andintensify negative emotions(e.g.,anxiety and depression).The interactionsbetween negative emotions and physiology create a vicious cycle,deterioratingQoL and clinical outcomes.We propose that patients with long-term MHDdependentCKD should be classified as a high-risk group for mental healthimpairments that need regular psychological screening and personalized psychomedicalinterventions.This integrated management model may help improvenegative emotions and disrupt the bidirectional psychophysiological interplay,offering a novel clinical pathway for improving the QoL and prognosis.
基金Supported by National Research Foundation of Korea Grant Funded by the Korea Government,No.RS-2023-00213951.
文摘BACKGROUND The cellular prion protein(PrPC),traditionally associated with neurodegenerative disorders,plays an important role in cancer progression and metastasis by inhibiting apoptosis.AIM To investigate the influence of PrPC expression in cholangiocarcinoma(CCA)on patient outcomes following surgical resection.METHODS Patients who underwent curative surgical resection for either intrahepatic or hilar CCA were enrolled in this retrospective study.Based on the immunohistochemical staining results of the surgical specimens,patients were categorized into two groups:The low PrPC group(negative or 1+)and the high PrPC group(2+or 3+).Survival analyses,including overall survival and recurrence-free survival,were conducted using the Kaplan-Meier method and compared using the log-rank test.RESULTS In total,seventy-six patients diagnosed with CCA(39 with intrahepatic and 37 with hilar CCA)underwent curative hepatectomy from January 2011 to November 2021.Among these patients,38(50%)demonstrated high PrPC expression,whereas the remaining 38(50%)showed low expression of PrPC.During a median follow-up period of 31.2 months(range:1 to 137 months),the high PrPC group had a significantly shorter median overall survival than the low PrPC group(40.4 months vs 137.9 months,respectively;P=0.041).Moreover,the high PrPC group had a significantly shorter median recurrence-free survival than the low PrPC group(13.3 months vs 23.8 months,respectively;P=0.026).CONCLUSION PrPC expression is significantly associated with early recurrence and decreased survival period in CCA patients following surgical resection.Thus,PrPC may be used as a prognostic factor in treatment planning.
基金supported by Young Talents Cultivation Program of Xianning City,the Natural Science Foundation of Hubei Province,China(No.2024AFB502)Ph.D.Start-up Funding(No.BK202413)Medical Fund(No.2023YKY04)of Hubei University of Science and Technology.
文摘Background:Kidney renal clear cell carcinoma(KIRC),a prevalent urological malignancy,represents about 3%of all adult malignancies.KIRC,accounting for~75%of renal malignancies,has poor prognosis in metastatic stages.Identifying robust prognostic markers remains urgent.Block of proliferation 1(BOP1),a WD40-repeat protein,is implicated in cancer pathogenesis,but its role in KIRC is unclear.This study aimed to characterize BOP1 expression in KIRC and evaluate its prognostic value.Methods:BOP1 transcriptional levels were assessed through TCGA-KIRC RNA sequencing datasets.ROC curve construction was implemented via R statistical packages for diagnostic evaluation.Patient survival outcomes were visualized through Kaplan-Meier plotting with log-rank testing.Multivariate logistic regression models quantified associations between BOP1 expression and clinicopathological parameters.TIMER algorithm analyzed immune microenvironment composition.Genomic alterations and epigenetic modifications were investigated using cBioPortal and MethSurv platforms respectively.BOP1 protein levels in 786-O clear cell renal cell carcinoma(ccRCC)versus HK-2(normal renal)cell lines were validated by immunoblotting.Results:Evaluation of the TCGA database demonstrated that BOP1 mRNA abundance was higher in tumor specimens than in corresponding adjacent tissues.Patients with KIRC who had high BOP1 expression had differential overall survival(OS),disease-specific survival(DSS),and disease-free interval(DFI).BOP1 expression accurately recognised tumour tissues versus normal tissues(AUC=0.858),and the area under the ROCs for survival at 1,3,and 5 years were all greater than 0.6.The BOP1 gene variant rate was<1%.Out of the 15 DNA methylation CpG sites examined,7 exhibited prognostic significance in KIRC.BOP1 displayed a distinct relationship with immune cell infiltration in KIRC.The 786-O experimental group exhibited substantially higher BOP1 expression,as confirmed by Western blot detection.Conclusion:This study indicates that heightened BOP1 expression is linked to an adverse prognosis in KIRC,establishing it as an independent risk factor for this disease.These findings establish BOP1 as a novel and independent prognostic biomarker for KIRC,offering potential clinical utility for risk stratification and personalized therapeutic strategies.
基金Supported by Scientific Research Project of Tianjin Municipal Education Commission,No.2018KJ015.
文摘BACKGROUND Studies on the application of recombinant human endostatin(RH-endostatin)intraperitoneal perfusion in gastric cancer(GC)with malignant ascites are limited.AIM To explore the effectiveness,prognosis,and safety of intraperitoneal RH-endostatin perfusion in treating patients with GC and malignant ascites.METHODS Patients with GC and malignant ascites were divided into the cisplatin intraperi-toneal perfusion(control group)group and the cisplatin combined with RH-endostatin intraperitoneal perfusion group(RH-endostatin group).Efficient ascites control,overall survival(OS),quality of life,and adverse events were observed,and possible influencing factors on prognosis outcomes analyzed.RESULTS We identified no significant differences in baseline characteristics between the control and RH-endostatin groups.The latter group had higher ascites control rates than the control group.Treatment methods were identified as an independent OS factor.Clinically,RH-endostatin-treated patients had significantly improved OS rates when compared with control patients,particularly in those with small and moderate ascites volumes.Quality of life improvements in control patients were significantly lower when compared with RH-endostatin patients.Adverse events were balanced between the groups.CONCLUSION Overall,intraperitoneal RH-endostatin improved treatment efficacy and prolonged prognosis in patients with GC and malignant ascites.This approach may benefit further clinical applications for treating GC.
基金supported by the National Natural Science Foundation of China(No.81602104).
文摘Objective To investigate the combined effects of thymidine phosphorylase(TYMP)and sine oculis homeobox homologue 1(Six1)on the tumor microenvironment and their role in promoting metastasis in gastric cancer(GC).Methods A total of 674 GC patients who underwent surgical resection were enrolled.Correlations between TYMP/Six1 expression and the clinicopathological characteristics and overall survival of patients were analysed.The expression of TYMP,Six1 and vascular endothelial growth factor C(VEGFc)was quantified via immunohistochemistry and quantitative real-time polymerase chain reaction.Cell transfection,wound-healing assays and bioinformatics analyses were used to explore the potential underlying mechanisms involved.Results Compared with the other groups,the Six1+/TYMP+patients exhibited poor differentiation,advanced tumor stage,a higher rate of lymphatic vessel invasion and shorter survival.Additionally,the protein expression of TYMP and Six1 was positively correlated with the VEGFc level.A significant increase in VEGFc expression was observed in cells transfected with TYMP,Six1,and TYMP/Six1 vectors.The results of the wound-healing assay indicated that the synergistic effect of TYMP and Six1 enhanced the migratory ability of GC cells.Furthermore,bioinformatics analysis revealed that TYMP and Six1 were positively correlated with immunosuppressive immune cell subsets and elevated the expression of inhibitory immune checkpoints in GC.Conclusions The combination of TYMP and Six1 is a good predictive and prognostic biomarker for GC.This combination enhances the expression of VEGFc,facilitates the invasion of GC cells,and may be linked to inhibitory immune cells and the tumor immune microenvironment.
基金Supported by National Natural Science Foundation of China,No.82300857.
文摘BACKGROUND Liver transplantation(LT)is recognized as an effective approach that offers survival benefits for patients with acute-on-chronic liver failure(ACLF).However,controversies remain regarding the LT selection criteria,and meta-analyses reporting overall survival outcomes across different ACLF severity grades are lacking.AIM To depict a comprehensive postoperative picture of patients with ACLF of varying severity and contribute to updating LT selection.METHODS Systematic searches in Web of Science,EMBASE,PubMed,and Cochrane databases were performed,from inception to December 26,2023,for studies exploring post-transplant outcomes among ACLF patients,stratified by severity grades as identified by the European Association for the Study of the Liver-Chronic Liver Failure criteria.The primary outcome of interest was the survival rate within one year,with post-transplant complications as secondary outcomes.Additionally,the subgroup analysis examined region-specific one-year survival rates.RESULTS A total of 17 studies involving 28025 participants were included.Patients with ACLF-1 and ACLF-2 have favorable survival within one year,with survival rates reaching 87%[95%confidence interval(CI):84%-91%]and 86%(95%CI:81%-91%),respectively.Despite the relatively lower survival(73%,95%CI:66%-80%)and higher incidence of infection(48%,95%CI:29%-67%)observed in ACLF-3 patients,their survival exceeds that of those who do not undergo LT.Moreover,post-transplant survival was highest in North America across all ACLF grades.CONCLUSION LT can provide survival advantages for ACLF patients.To optimize the utilization of scarce donor organs and improve prognosis,comprehensive preoperative health evaluations are essential,especially for ACLF-3 patients.
基金Supported by Natural Science Foundation of Xinjiang Uygur Autonomous Region,No.2022D01C297.
文摘BACKGROUND Colorectal cancer(CRC)is a common malignancy that has become a global burden.The prognostic prediction of CRC patients on the basis of inflammatory biomarkers and nutritional biomarkers has shown some potential but has not been fully explored.AIM To develop and validate a prognostic model for CRC based on inflammation and nutrition-related biomarkers and to evaluate its predictive value for patient outcomes.METHODS Patients were randomized at a 3:2 ratio into a training cohort(n=282)or a validation cohort(n=188).To identify the optimal prognostic factors for constructing the risk score(RS),LASSO Cox regression analysis was conducted.The association between the RS and overall survival(OS)was evaluated using receiver operating characteristic(ROC)curves and Kaplan-Meier(K-M)survival analysis.Independent risk factors were screened by multivariate Cox regression analysis.Nomograms were constructed and validated on the basis of these factors.RESULTS In the training cohort,univariate analysis of all the inflammatory and nutritional biomarkers demonstrated some predictive value.A LASSO-Cox analysis included four biomarkers and constructed an RS.Through ROC analysis,the area under the prognostic curve was 0.795.K-M survival curve analyses revealed that the five-year OS was significantly greater in the Low-RS group than in the High-RS group(P<0.001).Multivariate analysis demonstrated that the degree of differentiation(P=0.001),degree of nerve invasion(P=0.022),and RS(P<0.001)were independent risk factors.We constructed a nomogram to predict the OS of CRC patients and validated it in a separate cohort.The calibration curve showed high accuracy.Additionally,decision curve analysis for 1-year,3-year,and 5-year survival probabilities indicated significant clinical utility in predicting survival outcomes.CONCLUSION This study developed a nomogram based on the RS to predict the OS of CRC patients.This nomogram can guide treatment decisions and enable the formulation of personalized follow-up strategies on the basis of predicted recurrence risk,aiming to improve long-term prognosis.
基金supported by the Basic Research and Talent Cultivation Program of Zhangjiakou City(No.2511028A).
文摘Cancer is a major threat to human health worldwide.Colorectal cancer(CRC),a highly prevalent malignant tumor,poses a significant public health challenge.Therefore,the identification of effective biomarkers is of great significance[1].The NFKBIE gene encodes an inhibitor of nuclear factorκBε(IkBε).IκBε,a key regulator of the NF-κB signaling pathway,is closely associated with tumorigenesis.However,their roles in CRC remain unclear[2].Pan-cancer research is crucial for accelerating the identification of biomarkers and translational medical research,as it can reveal molecular commonalities and differences among different tumor types[3].
基金Supported by National Natural Science Foundation of China,No.81770379 and 81470521.
文摘Hypertrophic cardiomyopathy(HCM)is an autosomal dominant inherited cardiomyopathy characterized by left ventricular hypertrophy.It is one of the chief causes of sudden cardiac death in younger people and athletes.Molecular-genetic studies have confirmed that the vast majority of HCM is caused by mutations in genes encoding sarcomere proteins.HCM has a relatively wide phenotypic heterogeneity,varying from asymptomatic to sudden cardiac death,because of the many different mutations and pathogenic genes underlying it.Many studies have explored the clinical symptoms and prognosis of HCM,emphasizing the importance of genotype in evaluating patient prognosis and guiding the clinical management of HCM.To elaborate the main pathogenic genes and phenotypic prognosis in HCM to promote a better understanding of this genetic disease.Retrospective analysis of literature to evaluate the association between underlying gene mutations and clinical phenotypes in HCM patients.As sequencing technology advances,the pathogenic gene mutation spectrum and phenotypic characteristics of HCM are gradually becoming clearer.HCM is a widespread inherited disease with a highly variable clinical phenotype.The precise mechanisms linking known pathogenic gene mutations and the clinical course of this heterogeneous condition remain elusive.
文摘Hepatocellular carcinoma(HCC)is a prevalent and aggressive liver cancer that poses significant challenges in diagnosis and prognosis.Recent advancements in radiomics and machine learning(ML)offer promising solutions to enhance the accuracy of HCC diagnosis,treatment response prediction,and survival prognosis.Radiomics,which extracts quantitative features from medical images,captures the complex tumor heterogeneity that is often undetectable with traditional imaging methods.When combined with ML algorithms,these features can be used to differentiate between various stages of HCC,predict treatment outcomes,and assess long-term survival.This review explores key radiomic features,including texture,shape,and intensity,and their integration with ML techniques like binary classification models,XGBoost,LightGBM,and deep learning architectures.We also discuss the challenges faced in model interpretation,data heterogeneity,and the integration of multi-modal data.Despite the promising potential of these technologies,the clinical adoption of radiomics and ML models in HCC management will require overcoming these obstacles through standardization and improved interpretability.
文摘We read with great interest the study by Huang et al.Cholangiocarcinoma(CC)is the second most common type of primary liver tumor worldwide.Although surgical resection remains the primary treatment for this disease,almost 50%of patients experience relapse within 2 years after surgery,which negatively affects their prognosis.Key predictors can be used to identify several factors(e.g.,tumor size,tumor location,tumor stage,nerve invasion,the presence of intravascular emboli)and their correlations with long-term survival and the risk of postoperative morbidity.In recent years,artificial intelligence(AI)has become a new tool for prognostic assessment through the integration of multiple clinical,surgical,and imaging parameters.However,a crucial question has arisen:Are we ready to trust AI with respect to clinical decisions?The study by Huang et al demonstrated that AI can predict preoperative textbook outcomes in patients with CC and highlighted the precision of machine learning algorithms using useful prognostic factors.This letter to the editor aimed to explore the challenges and potential impact of AI and machine learning in the prognostic assessment of patients with CC.
