Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning
Objective Unfractionated heparin (UFH) is a widely used therapy in intensive care units (ICUs) and is associated with an increased risk of serious adverse events or death if the therapeutic target is not reached quickly. Adjusting UFH dosage is challenging, and no reliable algorithms exist for predi...
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SAGE Publishing
2025-04-01
|
| Series: | Digital Health |
| Online Access: | https://doi.org/10.1177/20552076241305957 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850173456809721856 |
|---|---|
| author | Boris Delange Guillaume Bouzillé Pauline Guillot Anaëlle Bichon Océane Bernard de Lajartre Isabelle Gouin Yoann Launey Alexandre Mansour Mathieu Lesouhaitier Jean-Marc Tadié Arnaud Gacouin Marc Cuggia Adel Maamar |
| author_facet | Boris Delange Guillaume Bouzillé Pauline Guillot Anaëlle Bichon Océane Bernard de Lajartre Isabelle Gouin Yoann Launey Alexandre Mansour Mathieu Lesouhaitier Jean-Marc Tadié Arnaud Gacouin Marc Cuggia Adel Maamar |
| author_sort | Boris Delange |
| collection | DOAJ |
| description | Objective Unfractionated heparin (UFH) is a widely used therapy in intensive care units (ICUs) and is associated with an increased risk of serious adverse events or death if the therapeutic target is not reached quickly. Adjusting UFH dosage is challenging, and no reliable algorithms exist for predicting anti-Xa levels in ICUs. This study aimed to develop and evaluate machine learning algorithms to predict anti-Xa levels during UFH therapy, helping clinicians optimize dosing. Methods This single-center retrospective cohort study was conducted using Rennes University Hospital's clinical data warehouse from December 21, 2019 to November 22, 2021. Critically ill patients ≥ 18 years on UFH, without other anticoagulants and complete data, were included. Anti-Xa levels were classified as infra-therapeutic (<0.3), therapeutic (0.3–0.7), or supra-therapeutic (>0.7). Models incorporated UFH rate, bolus, prior anti-Xa, kidney function, inflammation, volemic state, extracorporeal membrane oxygenation, and bilirubinemia. Performance was assessed using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, and specificity. Results A total of 3790 anti-Xa intervals, corresponding to 211 patients, were included in the study. Out of several machine learning algorithms, random forest achieved the best results with an AUROC score of 0.80 [0.77;0.83], an AUPRC score of 0.61 [0.58;0.65], sensitivity of 0.56 [0.53;0.59] and specificity of 0.82 [0.82;0.82]. Conclusion In this cohort study, machine learning-based prediction models achieved good performance for predicting anti-Xa results during UFH therapy in an ICU setting. Further validation with prospective multicenter data is needed in order to confirm the model's generalizability and support its integration into clinical practice to assist clinicians in selecting the optimal heparin dose. |
| format | Article |
| id | doaj-art-046ccc583f2a419d8ce514ebd0b9aca7 |
| institution | OA Journals |
| issn | 2055-2076 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | SAGE Publishing |
| record_format | Article |
| series | Digital Health |
| spelling | doaj-art-046ccc583f2a419d8ce514ebd0b9aca72025-08-20T02:19:51ZengSAGE PublishingDigital Health2055-20762025-04-011110.1177/20552076241305957Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learningBoris Delange0Guillaume Bouzillé1Pauline Guillot2Anaëlle Bichon3Océane Bernard de Lajartre4Isabelle Gouin5Yoann Launey6Alexandre Mansour7Mathieu Lesouhaitier8Jean-Marc Tadié9Arnaud Gacouin10Marc Cuggia11Adel Maamar12*Current affiliation: INSERM, LTSI-UMR 1099, Université de Rennes, Rennes, France. CHU Rennes, INSERM, LTSI-UMR 1099, , Rennes, France Service de Maladies Infectieuses et Réanimation Médicale, Hôpital Pontchaillou, , Rennes, France Service de Maladies Infectieuses et Réanimation Médicale, Hôpital Pontchaillou, , Rennes, France Service de Maladies Infectieuses et Réanimation Médicale, Hôpital Pontchaillou, , Rennes, France Laboratoire d’Hématologie-Hémostase, Centre Hospitalo-Universitaire de Rennes, Rennes, France Département Anesthésie Réanimation et Médecine Périopératoire, Centre Hospitalier Universitaire Rennes, Rennes, France Département Anesthésie Réanimation et Médecine Périopératoire, Centre Hospitalier Universitaire Rennes, Rennes, France Service de Maladies Infectieuses et Réanimation Médicale, Hôpital Pontchaillou, , Rennes, France Faculté de Médecine, Université de Rennes 1, Unité INSERM CIC 1414, IFR 140, Rennes, France Faculté de Médecine, Université de Rennes 1, Unité INSERM CIC 1414, IFR 140, Rennes, France CHU Rennes, INSERM, LTSI-UMR 1099, , Rennes, France Service de Maladies Infectieuses et Réanimation Médicale, Hôpital Pontchaillou, , Rennes, FranceObjective Unfractionated heparin (UFH) is a widely used therapy in intensive care units (ICUs) and is associated with an increased risk of serious adverse events or death if the therapeutic target is not reached quickly. Adjusting UFH dosage is challenging, and no reliable algorithms exist for predicting anti-Xa levels in ICUs. This study aimed to develop and evaluate machine learning algorithms to predict anti-Xa levels during UFH therapy, helping clinicians optimize dosing. Methods This single-center retrospective cohort study was conducted using Rennes University Hospital's clinical data warehouse from December 21, 2019 to November 22, 2021. Critically ill patients ≥ 18 years on UFH, without other anticoagulants and complete data, were included. Anti-Xa levels were classified as infra-therapeutic (<0.3), therapeutic (0.3–0.7), or supra-therapeutic (>0.7). Models incorporated UFH rate, bolus, prior anti-Xa, kidney function, inflammation, volemic state, extracorporeal membrane oxygenation, and bilirubinemia. Performance was assessed using the area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), sensitivity, and specificity. Results A total of 3790 anti-Xa intervals, corresponding to 211 patients, were included in the study. Out of several machine learning algorithms, random forest achieved the best results with an AUROC score of 0.80 [0.77;0.83], an AUPRC score of 0.61 [0.58;0.65], sensitivity of 0.56 [0.53;0.59] and specificity of 0.82 [0.82;0.82]. Conclusion In this cohort study, machine learning-based prediction models achieved good performance for predicting anti-Xa results during UFH therapy in an ICU setting. Further validation with prospective multicenter data is needed in order to confirm the model's generalizability and support its integration into clinical practice to assist clinicians in selecting the optimal heparin dose.https://doi.org/10.1177/20552076241305957 |
| spellingShingle | Boris Delange Guillaume Bouzillé Pauline Guillot Anaëlle Bichon Océane Bernard de Lajartre Isabelle Gouin Yoann Launey Alexandre Mansour Mathieu Lesouhaitier Jean-Marc Tadié Arnaud Gacouin Marc Cuggia Adel Maamar Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning Digital Health |
| title | Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning |
| title_full | Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning |
| title_fullStr | Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning |
| title_full_unstemmed | Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning |
| title_short | Anti-factor Xa during unfractionated heparin therapy in critically ill patients: Development of prediction models using machine learning |
| title_sort | anti factor xa during unfractionated heparin therapy in critically ill patients development of prediction models using machine learning |
| url | https://doi.org/10.1177/20552076241305957 |
| work_keys_str_mv | AT borisdelange antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT guillaumebouzille antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT paulineguillot antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT anaellebichon antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT oceanebernarddelajartre antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT isabellegouin antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT yoannlauney antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT alexandremansour antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT mathieulesouhaitier antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT jeanmarctadie antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT arnaudgacouin antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT marccuggia antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning AT adelmaamar antifactorxaduringunfractionatedheparintherapyincriticallyillpatientsdevelopmentofpredictionmodelsusingmachinelearning |