JMIR Publications

ABSTRACT

Background:

Narrow therapeutic index medications require careful dose individualization because small changes in drug exposure may result in treatment failure or toxicity. Their management often requires multiple pharmacokinetic calculations, therapeutic drug monitoring, and interpretation of clinical guidelines, which can make the dosing process complex and time-consuming.

Objective:

This study aimed to develop KFU Dose AI, an integrated clinical decision-support application that combines validated pharmacokinetic calculations with artificial intelligence assisted interpretation to support individualized dosing and therapeutic drug monitoring of NTI medications.

Methods:

KFU Dose AI was developed using R for deterministic pharmacokinetic calculations and incorporated the OpenAI GPT-4o model with a local Retrieval-Augmented Generation system. Validated pharmacokinetic equations and established clinical guidelines were integrated into medication-specific modules. The AI component was designed as a clinical auditing and interpretation layer rather than as the primary calculation engine. Patient-specific clinical and laboratory parameters are entered into the application, after which the system performs pharmacokinetic calculations and generates clinical assessments, dosing recommendations, and safety alerts. The interface also incorporates a color-coded system to facilitate rapid interpretation of therapeutic, subtherapeutic, and supratherapeutic results.

Results:

The developed platform incorporated modules for several NTI medications, including vancomycin, gentamicin, phenytoin, valproate, lithium, and digoxin. The system successfully integrated patient-specific pharmacokinetic calculations with guideline-based AI-assisted interpretation within a single interface. Depending on the medication, the application provides outputs such as estimated drug exposure, corrected drug concentrations, predicted doses or trough concentrations, clinical interpretation, dosing recommendations, and relevant safety-monitoring alerts.

Conclusions:

KFU Dose AI provides an integrated approach to pharmacokinetic dosing and therapeutic drug monitoring by combining deterministic pharmacokinetic calculations with guideline-grounded AI-assisted clinical interpretation. The platform may simplify complex dosing workflows and support clinical decision-making for NTI medications. Further prospective clinical validation is required to evaluate its accuracy, usability, and impact on clinical outcomes.