Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis
The machine learning-based prediction models can provide an initial assessment of 3-month PVST risk after SPDV in patients with cirrhosis and portal hypertension. The AdaBoost model demonstrates moderate discriminative ability in distinguishing between high-risk and low-risk patients, with an AUROC of 0.72 (95% CI 0.60 to 0.84). By incorporating SHAP analysis, the model can offer transparent explanations for personalised risk predictions, facilitating targeted preventive interventions and reducing excessive interventions across the entire patient population.
Authors
- Caixia Dong (ORCID: https://orcid.org/0000-0002-6353-7273)
- Dou Qu
- Rui Zhou (ORCID: https://orcid.org/0000-0001-5897-9918)
- Junyu Zhu
- Zongfang Li (ORCID: https://orcid.org/0000-0003-4813-1176)
- Duwei Dai (ORCID: https://orcid.org/0000-0001-6351-4840)
- Guodong Li (ORCID: https://orcid.org/0000-0003-4128-2887)
- Junxia Zhao
- Xingrong Song (ORCID: https://orcid.org/0000-0002-4473-3367)
Institutions
- Xi'an Medical University (CN)
- Second Affiliated Hospital of Xi'an Jiaotong University (CN)
Publication Details
- Journal
- BMJ Health & Care Informatics
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1136/bmjhci-2024-101319
- Primary Topic
- Liver Disease and Transplantation
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Shaanxi Provincial Science and Technology Department