Unraveling the impact of therapeutic drug monitoring via machine learning for patients with sepsis

• DOI: 10.1016/j.xcrm.2024.101681
• Publication Date: 2024-08-09T14:40:54Z
• Authors: H. Ceren Ates; Abdallah Alshanawani; Stefan Hagel; Menino O. Cotta; Jason A. Roberts; Can Dincer; Cihan Ates
• Keywords: Therapeutic Drug Monitoring

Clinical studies investigating the benefits of beta-lactam therapeutic drug monitoring (TDM) among critically ill patients are hindered by small patient groups, variability between studies, heterogeneity, and inadequate use TDM. Accordingly, definitive conclusions regarding efficacy TDM remain elusive. To address these challenges, we propose an innovative approach that leverages data-driven methods to unveil concealed connections therapy effectiveness data, collected through a randomized controlled trial (DRKS00011159; 10th October 2016). Our findings reveal machine learning algorithms can successfully identify informative features distinguish healthy sick states. These hold promise as potential markers for disease classification severity stratification, well offering continuous "multidimensional" Sequential Organ Failure Assessment (SOFA) score. The positive impact on recovery rates is demonstrated unraveling intricate clinically relevant data via learning.