Applying Machine Learning for Prescriptive Support: A Use Case with Unfractionated Heparin in Intensive Care Units

Stud Health Technol Inform. 2024 Aug 22:316:1739-1743. doi: 10.3233/SHTI240763.

Abstract

Continuous unfractionated heparin is widely used in intensive care, yet its complex pharmacokinetic properties complicate the determination of appropriate doses. To address this challenge, we developed machine learning models to predict over- and under-dosing, based on anti-Xa results, using a monocentric retrospective dataset. The random forest model achieved a mean AUROC of 0.80 [0.77-0.83], while the XGB model reached a mean AUROC of 0.80 [0.76-0.83]. Feature importance was employed to enhance the interpretability of the model, a critical factor for clinician acceptance. After prospective validation, machine learning models such as those developed in this study could be implemented within a computerized physician order entry (CPOE) as a clinical decision support system (CDSS).

Keywords: Clinical decision support system; Intensive care unit; Machine learning.

MeSH terms

  • Anticoagulants* / therapeutic use
  • Decision Support Systems, Clinical*
  • Heparin* / therapeutic use
  • Humans
  • Intensive Care Units*
  • Machine Learning*
  • Medical Order Entry Systems
  • Retrospective Studies

Substances

  • Heparin
  • Anticoagulants