Diagnostic Prediction of portal vein thrombosis in chronic cirrhosis patients using data-driven precision medicine model

Li, Ying4; Gao, Jing5,6,7; Zheng, Xubin8,9; Nie, Guole10; Qin, Jican8; Wang, Haiping4; He, Tao11; Wheelock, Asa12,13; Li, Chuan-Xing3,5; Cheng, Lixin2,14; Li, Xun1,15,16

2024

10.1093/bib/bbad478

BRIEFINGS IN BIOINFORMATICS   影响因子和分区

1467-5463

1477-4054

Background Portal vein thrombosis (PVT) is a significant issue in cirrhotic patients, necessitating early detection. This study aims to develop a data-driven predictive model for PVT diagnosis in chronic hepatitis liver cirrhosis patients.Methods We employed data from a total of 816 chronic cirrhosis patients with PVT, divided into the Lanzhou cohort (n = 468) for training and the Jilin cohort (n = 348) for validation. This dataset encompassed a wide range of variables, including general characteristics, blood parameters, ultrasonography findings and cirrhosis grading. To build our predictive model, we employed a sophisticated stacking approach, which included Support Vector Machine (SVM), Naive Bayes and Quadratic Discriminant Analysis (QDA).Results In the Lanzhou cohort, SVM and Naive Bayes classifiers effectively classified PVT cases from non-PVT cases, among the top features of which seven were shared: Portal Velocity (PV), Prothrombin Time (PT), Portal Vein Diameter (PVD), Prothrombin Time Activity (PTA), Activated Partial Thromboplastin Time (APTT), age and Child-Pugh score (CPS). The QDA model, trained based on the seven shared features on the Lanzhou cohort and validated on the Jilin cohort, demonstrated significant differentiation between PVT and non-PVT cases (AUROC = 0.73 and AUROC = 0.86, respectively). Subsequently, comparative analysis showed that our QDA model outperformed several other machine learning methods.Conclusion Our study presents a comprehensive data-driven model for PVT diagnosis in cirrhotic patients, enhancing clinical decision-making. The SVM-Naive Bayes-QDA model offers a precise approach to managing PVT in this population.

portal vein thrombosis chronic cirrhosis patients diagnostic prediction data-driven precision medicine model machine learning

SCI

英语

通讯

National Natural Science Foundation of China["32370711","32300554"] ; Shenzhen Science and Technology Program[JCYJ20220530152409020] ; Shenzhen Medical Research Fund[A2303033] ; Clinical Research Center for General Surgery of Gansu Province[20JR10FA661]

Biochemistry & Molecular Biology ; Mathematical & Computational Biology

Biochemical Research Methods ; Mathematical & Computational Biology

WOS:001173375300080

OXFORD UNIV PRESS

COMPUTER SCIENCE

Web of Science

1.First Hosp Lanzhou Univ, Lanzhou 730000, Peoples R China
2.Southern Univ Sci & Technol, Jinan Univ, Affiliated Hosp 1, Shenzhen Peoples Hosp,Clin Med Coll 2, Shenzhen 518000, Peoples R China
3.Karolinska Inst, Resp Med Unit, Dept Med & Ctr Mol Med, S-16340 Stockholm, Sweden
4.First Hosp Lanzhou Univ, Lanzhou, Peoples R China
5.Karolinska Inst, Solna, Sweden
6.Univ Helsinki, Helsinki, Finland
7.Helsinki Univ Hosp, Helsinki, Finland
8.Great Bay Univ, Sch Comp & Informat Technol, Portsmouth, NH USA
9.Great Bay Inst Adv Study, Princeton, NJ USA
10.Lanzhou Univ, Sch Clin Med, Lanzhou, Peoples R China
11.Jilin Hepatobiliary Dis Hosp, Changchun, Peoples R China
12.Karolinska Inst, Resp Med Unit, Dept Med, Stockholm, Sweden
13.Karolinska Inst, Ctr Mol Med, Stockholm, Sweden
14.Shenzhen Peoples Hosp, bioinformat, Shenzhen, Peoples R China
15.First Hosp Lanzhou Univ, Dept Gen Surg, Lanzhou, Peoples R China
16.First Hosp Lanzhou Univ, Key Lab Biotherapy & Regenerat Med Gansu Prov, Lanzhou, Peoples R China

Li, Ying,Gao, Jing,Zheng, Xubin,et al. Diagnostic Prediction of portal vein thrombosis in chronic cirrhosis patients using data-driven precision medicine model[J]. BRIEFINGS IN BIOINFORMATICS,2024,25(1).

Li, Ying.,Gao, Jing.,Zheng, Xubin.,Nie, Guole.,Qin, Jican.,...&Li, Xun.(2024).Diagnostic Prediction of portal vein thrombosis in chronic cirrhosis patients using data-driven precision medicine model.BRIEFINGS IN BIOINFORMATICS,25(1).

Li, Ying,et al."Diagnostic Prediction of portal vein thrombosis in chronic cirrhosis patients using data-driven precision medicine model".BRIEFINGS IN BIOINFORMATICS 25.1(2024).