Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system
Background and objectivesThe prognosis of liver failure treated with non-bioartificial liver support systems is poor. Detecting its risk factors and developing relevant prognostic models still represent the top priority to lower its death risk.MethodsAll 215 patients with liver failure treated with...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmed.2024.1368899/full |
| _version_ | 1827319215916318720 |
|---|---|
| author | Shi Shi Shi Shi Yanfen Yang Yuanli Liu Rong Chen XiaoXia Jia Yutong Wang Chunqing Deng Chunqing Deng |
| author_facet | Shi Shi Shi Shi Yanfen Yang Yuanli Liu Rong Chen XiaoXia Jia Yutong Wang Chunqing Deng Chunqing Deng |
| author_sort | Shi Shi |
| collection | DOAJ |
| description | Background and objectivesThe prognosis of liver failure treated with non-bioartificial liver support systems is poor. Detecting its risk factors and developing relevant prognostic models still represent the top priority to lower its death risk.MethodsAll 215 patients with liver failure treated with non-bioartificial liver support system were retrospectively analyzed. Potential prognostic factors were investigated, and the Nomogram and the Random Survival Forests (RSF) models were constructed, respectively. Notably, we evaluated the performance of models and calculated the risk scores to divide patients into low-risk and high-risk groups.ResultsIn the training set, multifactorial Cox regression analysis showed that etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score were independent factors of short-term prognosis. The RSF model (AUC: 0.863, 0.792) performed better in prediction than the Nomogram model (AUC: 0.816, 0.756) and MELD (AUC: 0.658, 0.700) in the training and validation groups. On top of that, patients in the low-risk group had a significantly better prognosis than those in the high-risk group.ConclusionWe constructed the RSF model with etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score, which showed better prognostic power than the Nomogram model and MELD score and could help physicians make optimal treatment decisions. |
| first_indexed | 2024-04-25T00:16:53Z |
| format | Article |
| id | doaj.art-a35e5cf6fdcc4ee7a9df92811f525510 |
| institution | Directory Open Access Journal |
| issn | 2296-858X |
| language | English |
| last_indexed | 2024-04-25T00:16:53Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Medicine |
| spelling | doaj.art-a35e5cf6fdcc4ee7a9df92811f5255102024-03-13T04:38:34ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2024-03-011110.3389/fmed.2024.13688991368899Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support systemShi Shi0Shi Shi1Yanfen Yang2Yuanli Liu3Rong Chen4XiaoXia Jia5Yutong Wang6Chunqing Deng7Chunqing Deng8Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Infectious Disease, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, ChinaThe 1st School of Clinical Medicine, Shanxi Medical University, Taiyuan, Shanxi, ChinaThe 1st School of Clinical Medicine, Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Health Statistics, School of Medical Sciences, Shanxi Medical University, Taiyuan, Shanxi, ChinaThe 1st School of Clinical Medicine, Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Health Statistics, School of Medical Sciences, Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi, ChinaDepartment of Infectious Disease, First Hospital of Shanxi Medical University, Taiyuan, Shanxi, ChinaBackground and objectivesThe prognosis of liver failure treated with non-bioartificial liver support systems is poor. Detecting its risk factors and developing relevant prognostic models still represent the top priority to lower its death risk.MethodsAll 215 patients with liver failure treated with non-bioartificial liver support system were retrospectively analyzed. Potential prognostic factors were investigated, and the Nomogram and the Random Survival Forests (RSF) models were constructed, respectively. Notably, we evaluated the performance of models and calculated the risk scores to divide patients into low-risk and high-risk groups.ResultsIn the training set, multifactorial Cox regression analysis showed that etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score were independent factors of short-term prognosis. The RSF model (AUC: 0.863, 0.792) performed better in prediction than the Nomogram model (AUC: 0.816, 0.756) and MELD (AUC: 0.658, 0.700) in the training and validation groups. On top of that, patients in the low-risk group had a significantly better prognosis than those in the high-risk group.ConclusionWe constructed the RSF model with etiology, hepatic encephalopathy, total bilirubin, serum alkaline phosphatase, platelets, and MELD score, which showed better prognostic power than the Nomogram model and MELD score and could help physicians make optimal treatment decisions.https://www.frontiersin.org/articles/10.3389/fmed.2024.1368899/fullnon-bioartificial liver support systemliver failurerandom survival forestsmultivariate cox regressionnomogram |
| spellingShingle | Shi Shi Shi Shi Yanfen Yang Yuanli Liu Rong Chen XiaoXia Jia Yutong Wang Chunqing Deng Chunqing Deng Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system Frontiers in Medicine non-bioartificial liver support system liver failure random survival forests multivariate cox regression nomogram |
| title | Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system |
| title_full | Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system |
| title_fullStr | Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system |
| title_full_unstemmed | Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system |
| title_short | Development and validation of a machine learning model to predict prognosis in liver failure patients treated with non-bioartificial liver support system |
| title_sort | development and validation of a machine learning model to predict prognosis in liver failure patients treated with non bioartificial liver support system |
| topic | non-bioartificial liver support system liver failure random survival forests multivariate cox regression nomogram |
| url | https://www.frontiersin.org/articles/10.3389/fmed.2024.1368899/full |
| work_keys_str_mv | AT shishi developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT shishi developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT yanfenyang developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT yuanliliu developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT rongchen developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT xiaoxiajia developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT yutongwang developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT chunqingdeng developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem AT chunqingdeng developmentandvalidationofamachinelearningmodeltopredictprognosisinliverfailurepatientstreatedwithnonbioartificialliversupportsystem |