Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis
Background Portal vein system thrombosis (PVST) is a common and potentially life-threatening complication following splenectomy plus pericardial devascularisation (SPDV) in patients with cirrhosis and portal hypertension. Early prediction of PVST is critical for timely intervention. This study aimed...
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-04-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/32/1/e101319.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850136571033944064 |
|---|---|
| author | Caixia Dong Guodong Li Rui Zhou Dou Qu Duwei Dai Junxia Zhao Lingbo An Xiaojie Song Jiazhen Zhu Zong Fang Li |
| author_facet | Caixia Dong Guodong Li Rui Zhou Dou Qu Duwei Dai Junxia Zhao Lingbo An Xiaojie Song Jiazhen Zhu Zong Fang Li |
| author_sort | Caixia Dong |
| collection | DOAJ |
| description | Background Portal vein system thrombosis (PVST) is a common and potentially life-threatening complication following splenectomy plus pericardial devascularisation (SPDV) in patients with cirrhosis and portal hypertension. Early prediction of PVST is critical for timely intervention. This study aimed to develop a machine learning-based prediction model for PVST occurrence within 3 months after splenectomy.Methods 392 patients with cirrhosis who underwent splenectomy at the Second Affiliated Hospital of Xi’an Jiaotong University between 1 July 2016 and 31 December 2022 were enrolled in this study and followed up for 3 months. The predictive model integrated 37 candidate predictors based on accessible clinical data, including demographic characteristics, disease features, imaging results, laboratory values, perioperative details and postoperative prophylactic therapies, and finally, eight predictors were selected for model construction. The five machine learning algorithms (logistic regression, Gaussian Naive Bayes, decision tree, random forest and AdaBoost) were employed to train the predictive models for assessing risks of PVST, which were validated using five fold cross-validation. Model discrimination and calibration were estimated using receiver operating characteristic curves(ROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value and Brier scores. The outcome of the predictive model was interpreted using SHapley Additive exPlanations (SHAP), which provided insights into the factors influencing PVST risk prediction.Results During the 3-month follow-up, a total of 144 (36.73%) patients developed PVST. The AdaBoost model demonstrated the highest discriminative ability, with a mean area under the receiver operating characteristic curve (AUROC) of 0.72 (95% CI 0.60 to 0.84). Important features for predicting PVST included albumin, platelet addition, the diameter of the portal vein, γ-glutamyl transferase, length of stay, activated partial thromboplastin time, D-dimer level and history of preoperative gastrointestinal bleeding, as revealed by SHAP analysis.Conclusions 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. |
| format | Article |
| id | doaj-art-bf6a650791a84653853e8afeb54b7b5e |
| institution | OA Journals |
| issn | 2632-1009 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj-art-bf6a650791a84653853e8afeb54b7b5e2025-08-20T02:31:04ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092025-04-0132110.1136/bmjhci-2024-101319Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosisCaixia Dong0Guodong Li1Rui Zhou2Dou Qu3Duwei Dai4Junxia Zhao5Lingbo An6Xiaojie Song7Jiazhen Zhu8Zong Fang Li9Institute of Medical Artificial Intelligence, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaInstitute of Medical Artificial Intelligence, The Second Affiliated Hospital of Xi’an Jiaotong University, Xi’an, ChinaShaanxi Provincial Clinical Medical Research Center for Liver and Spleen Diseases, Xi`an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaShaanxi Provincial Clinical Medical Research Center for Liver and Spleen Diseases, Xi`an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaNational-Local Joint Engineering Research Center of Biodiagnosis & Biotherapy, The Second Affiliated Hospital of Xi`an Jiaotong University, Xi’an, ChinaBackground Portal vein system thrombosis (PVST) is a common and potentially life-threatening complication following splenectomy plus pericardial devascularisation (SPDV) in patients with cirrhosis and portal hypertension. Early prediction of PVST is critical for timely intervention. This study aimed to develop a machine learning-based prediction model for PVST occurrence within 3 months after splenectomy.Methods 392 patients with cirrhosis who underwent splenectomy at the Second Affiliated Hospital of Xi’an Jiaotong University between 1 July 2016 and 31 December 2022 were enrolled in this study and followed up for 3 months. The predictive model integrated 37 candidate predictors based on accessible clinical data, including demographic characteristics, disease features, imaging results, laboratory values, perioperative details and postoperative prophylactic therapies, and finally, eight predictors were selected for model construction. The five machine learning algorithms (logistic regression, Gaussian Naive Bayes, decision tree, random forest and AdaBoost) were employed to train the predictive models for assessing risks of PVST, which were validated using five fold cross-validation. Model discrimination and calibration were estimated using receiver operating characteristic curves(ROC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value and Brier scores. The outcome of the predictive model was interpreted using SHapley Additive exPlanations (SHAP), which provided insights into the factors influencing PVST risk prediction.Results During the 3-month follow-up, a total of 144 (36.73%) patients developed PVST. The AdaBoost model demonstrated the highest discriminative ability, with a mean area under the receiver operating characteristic curve (AUROC) of 0.72 (95% CI 0.60 to 0.84). Important features for predicting PVST included albumin, platelet addition, the diameter of the portal vein, γ-glutamyl transferase, length of stay, activated partial thromboplastin time, D-dimer level and history of preoperative gastrointestinal bleeding, as revealed by SHAP analysis.Conclusions 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.https://informatics.bmj.com/content/32/1/e101319.full |
| spellingShingle | Caixia Dong Guodong Li Rui Zhou Dou Qu Duwei Dai Junxia Zhao Lingbo An Xiaojie Song Jiazhen Zhu Zong Fang Li Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis BMJ Health & Care Informatics |
| title | Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis |
| title_full | Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis |
| title_fullStr | Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis |
| title_full_unstemmed | Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis |
| title_short | Development of an explainable prediction model for portal vein system thrombosis post-splenectomy in patients with cirrhosis |
| title_sort | development of an explainable prediction model for portal vein system thrombosis post splenectomy in patients with cirrhosis |
| url | https://informatics.bmj.com/content/32/1/e101319.full |
| work_keys_str_mv | AT caixiadong developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT guodongli developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT ruizhou developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT douqu developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT duweidai developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT junxiazhao developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT lingboan developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT xiaojiesong developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT jiazhenzhu developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis AT zongfangli developmentofanexplainablepredictionmodelforportalveinsystemthrombosispostsplenectomyinpatientswithcirrhosis |