Identification of hepatic steatosis in living liver donors by machine learning models
Abstract Selecting an optimal donor for living donor liver transplantation is crucial for the safety of both the donor and recipient, and hepatic steatosis is an important consideration. We aimed to build a prediction model with noninvasive variables to evaluate macrovesicular steatosis in potential...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wolters Kluwer Health/LWW
2022-07-01
|
| Series: | Hepatology Communications |
| Online Access: | https://doi.org/10.1002/hep4.1921 |
| _version_ | 1827839613106913280 |
|---|---|
| author | Jihye Lim Seungbong Han Danbi Lee Ju Hyun Shim Kang Mo Kim Young‐Suk Lim Han Chu Lee Dong Hwan Jung Sung‐Gyu Lee Ki‐Hun Kim Jonggi Choi |
| author_facet | Jihye Lim Seungbong Han Danbi Lee Ju Hyun Shim Kang Mo Kim Young‐Suk Lim Han Chu Lee Dong Hwan Jung Sung‐Gyu Lee Ki‐Hun Kim Jonggi Choi |
| author_sort | Jihye Lim |
| collection | DOAJ |
| description | Abstract Selecting an optimal donor for living donor liver transplantation is crucial for the safety of both the donor and recipient, and hepatic steatosis is an important consideration. We aimed to build a prediction model with noninvasive variables to evaluate macrovesicular steatosis in potential donors by using various prediction models. The study population comprised potential living donors who had undergone donation workup, including percutaneous liver biopsy, in the Republic of Korea between 2016 and 2019. Meaningful macrovesicular hepatic steatosis was defined as >5%. Whole data were divided into training (70.5%) and test (29.5%) data sets based on the date of liver biopsy. Random forest, support vector machine, regularized discriminant analysis, mixture discriminant analysis, flexible discriminant analysis, and deep neural network machine learning methods as well as traditional logistic regression were employed. The mean patient age was 31.4 years, and 66.3% of the patients were men. Of the 1652 patients, 518 (31.4%) had >5% macrovesicular steatosis on the liver biopsy specimen. The logistic model had the best prediction power and prediction performances with an accuracy of 80.0% and 80.9% in the training and test data sets, respectively. A cut‐off value of 31.1% for the predicted risk of hepatic steatosis was selected with a sensitivity of 77.7% and specificity of 81.0%. We have provided our model on the website (https://hanseungbong.shinyapps.io/shiny_app_up/) under the name DONATION Model. Our algorithm to predict macrovesicular steatosis using routine parameters is beneficial for identifying optimal potential living donors by avoiding superfluous liver biopsy results. |
| first_indexed | 2024-03-12T07:22:51Z |
| format | Article |
| id | doaj.art-ffe00f853b70486c89b8c9766b516114 |
| institution | Directory Open Access Journal |
| issn | 2471-254X |
| language | English |
| last_indexed | 2024-03-12T07:22:51Z |
| publishDate | 2022-07-01 |
| publisher | Wolters Kluwer Health/LWW |
| record_format | Article |
| series | Hepatology Communications |
| spelling | doaj.art-ffe00f853b70486c89b8c9766b5161142023-09-02T22:19:15ZengWolters Kluwer Health/LWWHepatology Communications2471-254X2022-07-01671689169810.1002/hep4.1921Identification of hepatic steatosis in living liver donors by machine learning modelsJihye Lim0Seungbong Han1Danbi Lee2Ju Hyun Shim3Kang Mo Kim4Young‐Suk Lim5Han Chu Lee6Dong Hwan Jung7Sung‐Gyu Lee8Ki‐Hun Kim9Jonggi Choi10Department of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Biostatistics Korea University College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDivision of Hepatobiliary Surgery and Liver Transplantation Department of Surgery Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDivision of Hepatobiliary Surgery and Liver Transplantation Department of Surgery Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDivision of Hepatobiliary Surgery and Liver Transplantation Department of Surgery Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaDepartment of Gastroenterology Asan Liver Center Asan Medical Center University of Ulsan College of Medicine Seoul Republic of KoreaAbstract Selecting an optimal donor for living donor liver transplantation is crucial for the safety of both the donor and recipient, and hepatic steatosis is an important consideration. We aimed to build a prediction model with noninvasive variables to evaluate macrovesicular steatosis in potential donors by using various prediction models. The study population comprised potential living donors who had undergone donation workup, including percutaneous liver biopsy, in the Republic of Korea between 2016 and 2019. Meaningful macrovesicular hepatic steatosis was defined as >5%. Whole data were divided into training (70.5%) and test (29.5%) data sets based on the date of liver biopsy. Random forest, support vector machine, regularized discriminant analysis, mixture discriminant analysis, flexible discriminant analysis, and deep neural network machine learning methods as well as traditional logistic regression were employed. The mean patient age was 31.4 years, and 66.3% of the patients were men. Of the 1652 patients, 518 (31.4%) had >5% macrovesicular steatosis on the liver biopsy specimen. The logistic model had the best prediction power and prediction performances with an accuracy of 80.0% and 80.9% in the training and test data sets, respectively. A cut‐off value of 31.1% for the predicted risk of hepatic steatosis was selected with a sensitivity of 77.7% and specificity of 81.0%. We have provided our model on the website (https://hanseungbong.shinyapps.io/shiny_app_up/) under the name DONATION Model. Our algorithm to predict macrovesicular steatosis using routine parameters is beneficial for identifying optimal potential living donors by avoiding superfluous liver biopsy results.https://doi.org/10.1002/hep4.1921 |
| spellingShingle | Jihye Lim Seungbong Han Danbi Lee Ju Hyun Shim Kang Mo Kim Young‐Suk Lim Han Chu Lee Dong Hwan Jung Sung‐Gyu Lee Ki‐Hun Kim Jonggi Choi Identification of hepatic steatosis in living liver donors by machine learning models Hepatology Communications |
| title | Identification of hepatic steatosis in living liver donors by machine learning models |
| title_full | Identification of hepatic steatosis in living liver donors by machine learning models |
| title_fullStr | Identification of hepatic steatosis in living liver donors by machine learning models |
| title_full_unstemmed | Identification of hepatic steatosis in living liver donors by machine learning models |
| title_short | Identification of hepatic steatosis in living liver donors by machine learning models |
| title_sort | identification of hepatic steatosis in living liver donors by machine learning models |
| url | https://doi.org/10.1002/hep4.1921 |
| work_keys_str_mv | AT jihyelim identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT seungbonghan identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT danbilee identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT juhyunshim identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT kangmokim identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT youngsuklim identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT hanchulee identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT donghwanjung identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT sunggyulee identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT kihunkim identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels AT jonggichoi identificationofhepaticsteatosisinlivingliverdonorsbymachinelearningmodels |