Development and Validation of a Machine Learning-Based Model Used for Predicting Hepatocellular Carcinoma Risk in Patients with Hepatitis B-Related Cirrhosis: A Retrospective Study
IF 2.7 4区 医学Q3 BIOTECHNOLOGY & APPLIED MICROBIOLOGY
Yixin Hou, Jianguo Yan, Ke Shi, Xiaoli Liu, Fangyuan Gao, Tong Wu, Peipei Meng, Min Zhang, Yuyong Jiang, Xianbo Wang
{"title":"Development and Validation of a Machine Learning-Based Model Used for Predicting Hepatocellular Carcinoma Risk in Patients with Hepatitis B-Related Cirrhosis: A Retrospective Study","authors":"Yixin Hou, Jianguo Yan, Ke Shi, Xiaoli Liu, Fangyuan Gao, Tong Wu, Peipei Meng, Min Zhang, Yuyong Jiang, Xianbo Wang","doi":"10.2147/ott.s444536","DOIUrl":null,"url":null,"abstract":"<strong>Object:</strong> Our objective was to estimate the 5-year cumulative risk of HCC in patients with HBC by utilizing an artificial neural network (ANN).<br/><strong>Methods:</strong> We conducted this study with 1589 patients hospitalized at Beijing Ditan Hospital of Capital Medical University and People’s Liberation Army Fifth Medical Center. The training cohort consisted of 913 subjects from Beijing Ditan Hospital of Capital Medical University, while the validation cohort comprised 676 subjects from People’s Liberation Army Fifth Medical Center. Through univariate analysis, we identified factors that independently influenced the occurrence of HCC, which were then used to develop the ANN model. To evaluate the ANN model, we assessed its predictive accuracy, discriminative ability, and clinical net benefit using metrics such as the area under the receiver operating characteristic curve (AUC), concordance index (C-index), calibration curves.<br/><strong>Results:</strong> In total, we included nine independent risk factors in the development of the ANN model. Remarkably, the AUC of the ANN model was 0.880, significantly outperforming the AUC values of other existing models including mPAGE-B (0.719) (95% CI 0.670– 0.768), PAGE-B (0. 710) (95% CI 0.660– 0.759), FIB-4 (0.693) (95% CI 0.640– 0.745), and Toronto hepatoma risk index (THRI) (0.705) (95% CI 0.654– 0.756) (p< 0.001 for all). The ANN model effectively stratified patients into low, medium, and high-risk groups based on their 5-year In the training cohort, the positive predictive value (PPV) for low-risk patients was 26.2% (95% CI 25.0– 27.4), and the negative predictive value (NPV) was 98.7% (95% CI 95.2– 99.7). For high-risk patients, the PPV was 54.7% (95% CI 48.6– 60.7), and the NPV was 91.6% (95% CI 89.4– 93.4). These findings were validated in the independent validation cohort.<br/><strong>Conclusion:</strong> The ANNs model has good individualized prediction performance and may be helpful to evaluate the probability of the 5-year risk of HCC in patients with HBC.<br/><br/><strong>Keywords:</strong> machine learning-based model, hepatocellular carcinoma, risk, hepatitis B-related cirrhosis<br/>","PeriodicalId":19534,"journal":{"name":"OncoTargets and therapy","volume":null,"pages":null},"PeriodicalIF":2.7000,"publicationDate":"2024-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"OncoTargets and therapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.2147/ott.s444536","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"BIOTECHNOLOGY & APPLIED MICROBIOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Object: Our objective was to estimate the 5-year cumulative risk of HCC in patients with HBC by utilizing an artificial neural network (ANN). Methods: We conducted this study with 1589 patients hospitalized at Beijing Ditan Hospital of Capital Medical University and People’s Liberation Army Fifth Medical Center. The training cohort consisted of 913 subjects from Beijing Ditan Hospital of Capital Medical University, while the validation cohort comprised 676 subjects from People’s Liberation Army Fifth Medical Center. Through univariate analysis, we identified factors that independently influenced the occurrence of HCC, which were then used to develop the ANN model. To evaluate the ANN model, we assessed its predictive accuracy, discriminative ability, and clinical net benefit using metrics such as the area under the receiver operating characteristic curve (AUC), concordance index (C-index), calibration curves. Results: In total, we included nine independent risk factors in the development of the ANN model. Remarkably, the AUC of the ANN model was 0.880, significantly outperforming the AUC values of other existing models including mPAGE-B (0.719) (95% CI 0.670– 0.768), PAGE-B (0. 710) (95% CI 0.660– 0.759), FIB-4 (0.693) (95% CI 0.640– 0.745), and Toronto hepatoma risk index (THRI) (0.705) (95% CI 0.654– 0.756) (p< 0.001 for all). The ANN model effectively stratified patients into low, medium, and high-risk groups based on their 5-year In the training cohort, the positive predictive value (PPV) for low-risk patients was 26.2% (95% CI 25.0– 27.4), and the negative predictive value (NPV) was 98.7% (95% CI 95.2– 99.7). For high-risk patients, the PPV was 54.7% (95% CI 48.6– 60.7), and the NPV was 91.6% (95% CI 89.4– 93.4). These findings were validated in the independent validation cohort. Conclusion: The ANNs model has good individualized prediction performance and may be helpful to evaluate the probability of the 5-year risk of HCC in patients with HBC.
期刊介绍:
OncoTargets and Therapy is an international, peer-reviewed journal focusing on molecular aspects of cancer research, that is, the molecular diagnosis of and targeted molecular or precision therapy for all types of cancer.
The journal is characterized by the rapid reporting of high-quality original research, basic science, reviews and evaluations, expert opinion and commentary that shed novel insight on a cancer or cancer subtype.
Specific topics covered by the journal include:
-Novel therapeutic targets and innovative agents
-Novel therapeutic regimens for improved benefit and/or decreased side effects
-Early stage clinical trials
Further considerations when submitting to OncoTargets and Therapy:
-Studies containing in vivo animal model data will be considered favorably.
-Tissue microarray analyses will not be considered except in cases where they are supported by comprehensive biological studies involving multiple cell lines.
-Biomarker association studies will be considered only when validated by comprehensive in vitro data and analysis of human tissue samples.
-Studies utilizing publicly available data (e.g. GWAS/TCGA/GEO etc.) should add to the body of knowledge about a specific disease or relevant phenotype and must be validated using the authors’ own data through replication in an independent sample set and functional follow-up.
-Bioinformatics studies must be validated using the authors’ own data through replication in an independent sample set and functional follow-up.
-Single nucleotide polymorphism (SNP) studies will not be considered.