Safety and Performance Evaluation of a Clinical Decision Support System for Imatinib Therapeutic Drug Monitoring: In Silico Study.

BACKGROUND

Therapeutic drug monitoring (TDM) aims to optimize clinical outcomes but is hindered by logistical delays and susceptibility to data errors. Integrating model-informed precision dosing with point-of-care testing, fortified by rule-based validation and alerts, forms a transformative clinical decision support system (CDSS) essential for securing this complex workflow.

OBJECTIVE

This study evaluates, in silico, the effectiveness of a rule-based CDSS for imatinib in detecting data-quality issues and optimizing therapeutic dosing, compared with a human TDM expert.

METHODS

We simulated a set of 60 virtual patients using a previously developed population pharmacokinetic model and deliberately enriched it with data-quality errors (eg, timing inaccuracies and reporting errors) to stress-test system resilience. We compared CDSS and TDM expert performances based on their error-detection capabilities and the clinical impact on therapeutic target attainment and safety.

RESULTS

The CDSS and the expert demonstrated comparable error-detection capabilities. The CDSS showed numerically higher sensitivity (53%, 95% CI 35%-70% vs 45%, 95% CI 30%-61%) and lower specificity (83%, 95% CI 63%-95% vs 100%, 95% CI 81%-100%). Clinically, the CDSS demonstrated significantly higher rates of target attainment than the expert (33/60, 55% vs 22/60, 37%; P=.046). However, the CDSS resulted in 5 detrimental outcomes against 1 for the TDM expert, in which patients initially within the target range fell outside it.

CONCLUSIONS

The CDSS demonstrated high efficacy in optimizing imatinib exposure while serving as a robust digital gatekeeper. While active optimization drives higher efficacy, a few observed detrimental cases highlight that algorithmic safety remains contingent on data integrity. This proof-of-concept study validates the CDSS architecture as a prerequisite for future prospective clinical trials.