LLMs Recognize TDM Problems but Reason Overconfidently on NTI Drugs

This benchmark shows current large language models interpret phenytoin and digoxin levels well but falter on pharmacokinetic reasoning and uncertainty acknowledgment, reinforcing that pharmacist oversight remains mandatory.

phenytoindigoxintherapeutic drug monitoringTDMnarrow therapeutic index drugslarge language modelsartificial intelligenceclinical decision supportChatGPTClaudeGeminiclinical pharmacybenchmark study Pharmacokinetics / TDM

Background Information

LLMs show promise for drug monitoring, yet caution remains due to potential reasoning errors.

Large language models (LLMs) are being considered as tools for therapeutic drug monitoring (TDM) but their reliability in clinical settings remains uncertain. Claude Sonnet 4.6 had the highest performance (94.9% ± 8.3%), outperforming ChatGPT 5.5 and Gemini 3.1 Pro, particularly in reasoning-dependent tasks. LLMs can identify TDM issues but struggle with reasoning tasks, highlighting the importance of pharmacist oversight to ensure patient safety. Pharmacist supervision is crucial when using LLMs for therapeutic drug monitoring to prevent safety concerns from overconfidence errors.

📊 Deep Analysis Available

Subscribers get the full breakdown: study design, outcomes, pharmacist implications, clinical pearls, GRADE evidence grade, and a downloadable PDF report.

Subscribe for Full Access →

Authors: Azmakan H, Azamakan T

Citation: Azmakan H, Azamakan T Performance of large language models on narrow therapeutic index drug monitoring: Implications for clinical pharmacy practice. Journal of the American Pharmacists Association : JAPhA. 2026:103524. doi:10.1016/j.japh.2026.103524

Article Links: PubMed · Journal / DOI

🎓

Reviewed by a licensed pharmacist

Every analysis is reviewed and approved by a licensed pharmacist before publication, ensuring clinical accuracy and relevance.

Accurate and up-to-date information is our highest priority.

If you spot an error, please suggest a correction. If there is a topic you want covered, tell us and we will look at it.

Suggest a correction Request a topic

Thanks for the feedback!

🔒

Deep Analysis: Subscribers Only

Subscribers receive access to a complete clinical analysis, available online and as a downloadable PDF.

Executive Summary

Study Design

Patient Population

Primary Outcomes

Secondary Outcomes & Safety Profile

Pharmacist Implications

Clinical Pearls

Limitations

Controversies & Evidence Gaps

Cost & Logistics

Want the full analysis?

Subscribe to PharmD Signal for unrestricted access to every deep analysis, plus PDF reports, GRADE evidence grades, and pharmacist implications for every article we publish.

Become a Subscriber →