Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients
Abstract Post-Liver transplantation (LT) survival rates stagnate, with biliary complications (BC) as a major cause of death. We analyzed longitudinal data with a median 19-month follow-up. BC was diagnosed with ultrasounds and MRCP. Missing data was imputed using mean and median. Data preprocessing...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-89570-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823862652450897920 |
|---|---|
| author | Aref Andishgar Sina Bazmi Kamran B. Lankarani Seyed Alireza Taghavi Mohammad Hadi Imanieh Gholamreza Sivandzadeh Samira Saeian Nazanin Dadashpour Alireza Shamsaeefar Mahdi Ravankhah Hamed Nikoupour Deylami Reza Tabrizi Mohammad Hossein Imanieh |
| author_facet | Aref Andishgar Sina Bazmi Kamran B. Lankarani Seyed Alireza Taghavi Mohammad Hadi Imanieh Gholamreza Sivandzadeh Samira Saeian Nazanin Dadashpour Alireza Shamsaeefar Mahdi Ravankhah Hamed Nikoupour Deylami Reza Tabrizi Mohammad Hossein Imanieh |
| author_sort | Aref Andishgar |
| collection | DOAJ |
| description | Abstract Post-Liver transplantation (LT) survival rates stagnate, with biliary complications (BC) as a major cause of death. We analyzed longitudinal data with a median 19-month follow-up. BC was diagnosed with ultrasounds and MRCP. Missing data was imputed using mean and median. Data preprocessing involved feature scaling and one-hot encoding. Survival analysis used filter (Cox-P, Cox-c) and embedded (RSF, LASSO) feature selection methods. Seven survival machine learning algorithms were used: LASSO, Ridge, RSF, E-NET, GBS, C-GBS, and FS-SVM. Model development employed 5-fold cross-validation, random oversampling, and hyperparameter tuning. Random oversampling addressed data imbalance. Optimal hyperparameters were determined based on average C-index. Features importance was assessed using standardized regression coefficients and permutation importance for top models. Stability was evaluated using 5-fold cross-validation standard deviation. Finally, 1799 observations with 40 outcome predictors were included. RSF with Ridge achieved the highest performance (C-index: 0.699) for BC prediction, while RSF with RSF had the highest performance (C-index: 0.784) for mortality prediction. Top BC predictors were LT graft types, IBD in recipients, recipient’s BMI, recipient’s history of PVT, and previous LT history. For mortality, they were post-transplant AST, creatinine, recipient’s age, post-transplant ALT, and tacrolimus consumption. We identified BC and mortality risk factors, improving decision-making and outcomes. |
| format | Article |
| id | doaj-art-5d7cc36c60994c9a88728c86ded9c90d |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-5d7cc36c60994c9a88728c86ded9c90d2025-02-09T12:28:07ZengNature PortfolioScientific Reports2045-23222025-02-0115111410.1038/s41598-025-89570-4Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patientsAref Andishgar0Sina Bazmi1Kamran B. Lankarani2Seyed Alireza Taghavi3Mohammad Hadi Imanieh4Gholamreza Sivandzadeh5Samira Saeian6Nazanin Dadashpour7Alireza Shamsaeefar8Mahdi Ravankhah9Hamed Nikoupour Deylami10Reza Tabrizi11Mohammad Hossein Imanieh12USERN Office, Fasa University of Medical SciencesUSERN Office, Fasa University of Medical SciencesHealth Policy Research Center, Institute of Heath, Shiraz University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesAbu Ali Sina Organ Transplant Center, Shiraz University of Medical SciencesStudent Research Committee, School of Medicine, Shiraz University of Medical SciencesAbu Ali Sina Organ Transplant Center, Shiraz University of Medical SciencesNoncommunicable Diseases Research Center, Fasa University of Medical SciencesGastroenterohepatology Research Center, Shiraz University of Medical SciencesAbstract Post-Liver transplantation (LT) survival rates stagnate, with biliary complications (BC) as a major cause of death. We analyzed longitudinal data with a median 19-month follow-up. BC was diagnosed with ultrasounds and MRCP. Missing data was imputed using mean and median. Data preprocessing involved feature scaling and one-hot encoding. Survival analysis used filter (Cox-P, Cox-c) and embedded (RSF, LASSO) feature selection methods. Seven survival machine learning algorithms were used: LASSO, Ridge, RSF, E-NET, GBS, C-GBS, and FS-SVM. Model development employed 5-fold cross-validation, random oversampling, and hyperparameter tuning. Random oversampling addressed data imbalance. Optimal hyperparameters were determined based on average C-index. Features importance was assessed using standardized regression coefficients and permutation importance for top models. Stability was evaluated using 5-fold cross-validation standard deviation. Finally, 1799 observations with 40 outcome predictors were included. RSF with Ridge achieved the highest performance (C-index: 0.699) for BC prediction, while RSF with RSF had the highest performance (C-index: 0.784) for mortality prediction. Top BC predictors were LT graft types, IBD in recipients, recipient’s BMI, recipient’s history of PVT, and previous LT history. For mortality, they were post-transplant AST, creatinine, recipient’s age, post-transplant ALT, and tacrolimus consumption. We identified BC and mortality risk factors, improving decision-making and outcomes.https://doi.org/10.1038/s41598-025-89570-4Survival analysisMachine learningLiver transplantationMortalityPostoperative complicationsBiliary complications |
| spellingShingle | Aref Andishgar Sina Bazmi Kamran B. Lankarani Seyed Alireza Taghavi Mohammad Hadi Imanieh Gholamreza Sivandzadeh Samira Saeian Nazanin Dadashpour Alireza Shamsaeefar Mahdi Ravankhah Hamed Nikoupour Deylami Reza Tabrizi Mohammad Hossein Imanieh Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients Scientific Reports Survival analysis Machine learning Liver transplantation Mortality Postoperative complications Biliary complications |
| title | Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| title_full | Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| title_fullStr | Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| title_full_unstemmed | Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| title_short | Comparison of time-to-event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| title_sort | comparison of time to event machine learning models in predicting biliary complication and mortality rate in liver transplant patients |
| topic | Survival analysis Machine learning Liver transplantation Mortality Postoperative complications Biliary complications |
| url | https://doi.org/10.1038/s41598-025-89570-4 |
| work_keys_str_mv | AT arefandishgar comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT sinabazmi comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT kamranblankarani comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT seyedalirezataghavi comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT mohammadhadiimanieh comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT gholamrezasivandzadeh comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT samirasaeian comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT nazanindadashpour comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT alirezashamsaeefar comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT mahdiravankhah comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT hamednikoupourdeylami comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT rezatabrizi comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients AT mohammadhosseinimanieh comparisonoftimetoeventmachinelearningmodelsinpredictingbiliarycomplicationandmortalityrateinlivertransplantpatients |