Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making
Objectives Liver transplantation is a complex procedure frequently requiring transfusion of blood products to manage coagulopathy and haemorrhage. This study aimed to develop machine learning models to predict the biological effects of blood product transfusions, assisting clinicians in selecting op...
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2025-06-01
|
| Series: | BMJ Health & Care Informatics |
| Online Access: | https://informatics.bmj.com/content/32/1/e101466.full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850207814069256192 |
|---|---|
| author | Jacques Creteur Thibault Martinez Valerio Lucidi Turgay Tuna Florian Blanchard Olivier Duranteau Benjamin Popoff Axel Abels Eric Savier Patrizia Loi Desislava Germanova Anne Demulder |
| author_facet | Jacques Creteur Thibault Martinez Valerio Lucidi Turgay Tuna Florian Blanchard Olivier Duranteau Benjamin Popoff Axel Abels Eric Savier Patrizia Loi Desislava Germanova Anne Demulder |
| author_sort | Jacques Creteur |
| collection | DOAJ |
| description | Objectives Liver transplantation is a complex procedure frequently requiring transfusion of blood products to manage coagulopathy and haemorrhage. This study aimed to develop machine learning models to predict the biological effects of blood product transfusions, assisting clinicians in selecting optimal therapeutic combinations.Methods Using data from two cohorts over 20 years from two academic hospitals, 10 supervised machine learning models were trained and validated on four biomarkers: fibrinogen, haemoglobin, prothrombin time and activated partial thromboplastin time ratio. Models were evaluated using R², root mean squared error and SD metrics, with external validation performed on the second cohort.Results The results indicated that while certain models, such as the stack model for late fibrinogen (R²=0.63) or the extra trees model for late prothrombin time (R²=0.66), demonstrated promising predictive capacity, the overall external validation performance was suboptimal. Despite the use of a large healthcare database, a rigorous statistical methodology and an academic machine learning methodology, most models showed limited generalisability (R² < 0.5).Discussion Key limitations included the small dataset size relative to machine learning requirements, lack of advanced haemostatic parameters (eg, ROtational ThromboElastoMetry (ROTEM) or Thromboelastography (TEG)) and the variability introduced by evolving surgical practices over the 20-year study period. Despite these limitations, this study provides a reproducible framework for evaluating transfusion efficacy, supported by openly shared Python code and the application of Taylor diagrams for model evaluation.Conclusion While our models are unsuitable for routine clinical use, they highlight the potential of machine learning in transfusion medicine. Future work should focus on integrating larger datasets, advanced biomarkers and real-time data. |
| format | Article |
| id | doaj-art-b0228d9a1bc1482cb29f574e8d8ab0d9 |
| institution | OA Journals |
| issn | 2632-1009 |
| language | English |
| publishDate | 2025-06-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Health & Care Informatics |
| spelling | doaj-art-b0228d9a1bc1482cb29f574e8d8ab0d92025-08-20T02:10:24ZengBMJ Publishing GroupBMJ Health & Care Informatics2632-10092025-06-0132110.1136/bmjhci-2025-101466Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-makingJacques Creteur0Thibault Martinez1Valerio Lucidi2Turgay Tuna3Florian Blanchard4Olivier Duranteau5Benjamin Popoff6Axel Abels7Eric Savier8Patrizia Loi9Desislava Germanova10Anne Demulder11Department of Intensive Care, Université Libre de Bruxelles, Bruxelles, Bruxelles, BelgiumFederation of Anesthesiology, Intensive Care Unit, Burns and Operating Theater, Percy Military Training Hospital, Clamart, FranceUniversité Libre de Bruxelles, Brussels, Belgium1Anesthesia and Reanimation, Hôpitaux Universitaires de Bruxelles – Hôpital Erasme, Bruxelles, BelgiumDepartment of Anesthesiology and Critical Care, Hopital Universitaire Pitie Salpetriere Bibliotheque de La Pitié, Paris, FranceIntensive Care, HIA Percy, Clamart, FranceDepartment of Anesthesiology and Critical Care, CHU de Rouen, Rouen, FranceMachine Learning Group, Université Libre de Bruxelles, Bruxelles, BelgiumDepartment of Hepato-Biliary and Pancreatic Surgery and Liver Transplantation, Sorbonne University, Paris, FranceUniversité Libre de Bruxelles, Brussels, BelgiumDepartment of Digestive Surgery, Hopital Erasme, Brussels, BelgiumUniversité Libre de Bruxelles, Brussels, BelgiumObjectives Liver transplantation is a complex procedure frequently requiring transfusion of blood products to manage coagulopathy and haemorrhage. This study aimed to develop machine learning models to predict the biological effects of blood product transfusions, assisting clinicians in selecting optimal therapeutic combinations.Methods Using data from two cohorts over 20 years from two academic hospitals, 10 supervised machine learning models were trained and validated on four biomarkers: fibrinogen, haemoglobin, prothrombin time and activated partial thromboplastin time ratio. Models were evaluated using R², root mean squared error and SD metrics, with external validation performed on the second cohort.Results The results indicated that while certain models, such as the stack model for late fibrinogen (R²=0.63) or the extra trees model for late prothrombin time (R²=0.66), demonstrated promising predictive capacity, the overall external validation performance was suboptimal. Despite the use of a large healthcare database, a rigorous statistical methodology and an academic machine learning methodology, most models showed limited generalisability (R² < 0.5).Discussion Key limitations included the small dataset size relative to machine learning requirements, lack of advanced haemostatic parameters (eg, ROtational ThromboElastoMetry (ROTEM) or Thromboelastography (TEG)) and the variability introduced by evolving surgical practices over the 20-year study period. Despite these limitations, this study provides a reproducible framework for evaluating transfusion efficacy, supported by openly shared Python code and the application of Taylor diagrams for model evaluation.Conclusion While our models are unsuitable for routine clinical use, they highlight the potential of machine learning in transfusion medicine. Future work should focus on integrating larger datasets, advanced biomarkers and real-time data.https://informatics.bmj.com/content/32/1/e101466.full |
| spellingShingle | Jacques Creteur Thibault Martinez Valerio Lucidi Turgay Tuna Florian Blanchard Olivier Duranteau Benjamin Popoff Axel Abels Eric Savier Patrizia Loi Desislava Germanova Anne Demulder Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making BMJ Health & Care Informatics |
| title | Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making |
| title_full | Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making |
| title_fullStr | Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making |
| title_full_unstemmed | Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making |
| title_short | Prediction of biological evolution following blood product transfusion during liver transplantation: the contribution of machine learning to decision-making |
| title_sort | prediction of biological evolution following blood product transfusion during liver transplantation the contribution of machine learning to decision making |
| url | https://informatics.bmj.com/content/32/1/e101466.full |
| work_keys_str_mv | AT jacquescreteur predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT thibaultmartinez predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT valeriolucidi predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT turgaytuna predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT florianblanchard predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT olivierduranteau predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT benjaminpopoff predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT axelabels predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT ericsavier predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT patrizialoi predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT desislavagermanova predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking AT annedemulder predictionofbiologicalevolutionfollowingbloodproducttransfusionduringlivertransplantationthecontributionofmachinelearningtodecisionmaking |