Retrospective modeling study of ChatGPT (GPT 4) warfarin dose adjustment in patients with INRs outside the therapeutic range

Sep 29, 2026

Retrospective modeled evaluation compares ChatGPT (GPT-4) warfarin dose adjustments with clinician recommendations in patients whose international normalized ratio (INR) values fall outside the therapeutic range (2–3) at the Cardiology Clinic of Konya City Hospital. Physician inputs (baseline INR, indication, comorbidities, and current dose) were used to generate hypothetical weekly dose suggestions, and INR normalization was modeled via standard dose–response assumptions versus physician-guided outcomes. Across 180 eligible patients, ChatGPT showed high dose concordance, with adverse events reported as infrequent under physician management. Results are hypothesis-generating and require prospective, physician-supervised validation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Materials and methods

Study design

Retrospective modeling study of ChatGPT (GPT 4) warfarin dose adjustment in patients with INRs outside the therapeutic range DIGITAL HEALTH Volume 12: 1–11 © The Author(s) 2026 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/20552076251412985](DOI: 10.1177/20552076251412985)[ ](DOI: 10.1177/20552076251412985)[journals.sagepub.com/home/dhj](journals.sagepub.com/home/dhj) Hüseyin Tezcan 1 , Abdullah Tunçez 1, Yasin Özen 1, Muhammed Ulvi Yalçın1 and Kadri Murat Gürses 1 Abstract Objective: This retrospective, modeled study evaluates the accuracy of ChatGPT (GPT-4)-based warfarin dose adjustments compared to clinician recommendations at the Cardiology Clinic of Konya City Hospital, focusing on patients with international normalized ratio (INR) values outside the therapeutic range (2–3). We hypothesized that ChatGPT could provide reliable, consistent dose guidance. Methods: We reviewed the records of warfarin-treated patients from 1 June 2022 through 24 November 2024. Clinical data used by physicians (e.g. baseline INR, warfarin indication, comorbidities, and current dose) were provided to ChatGPT to generate hypothetical weekly dose recommendations. ChatGPT’s impact on INR normalization was modeled using standard dose–response assumptions and compared with actual outcomes under physician-guided therapy. Results: A total of 180 patients met the inclusion criteria. ChatGPT’s recommended doses were within ± 1 mg/week of physician prescriptions in 74% of cases and within ±2 mg/week in 84%. The mean physician dose was 28.0 ± 6.1 mg/week versus ChatGPT’s 27.5 ± 5.9 mg/week (p = .12). Seventy-two percent of patients achieved therapeutic INR under physician-managed dosing, while the model suggested a 69% success rate for ChatGPT-guided dosing (p = .15). Real-world adverse events were infrequent under physician management (1.1% major bleeding, 0.6% thrombotic events). Conclusion: In this retrospective, exploratory analysis with modeled outcomes, ChatGPT’s weekly dose suggestions showed high concordance with clinician dosing. These ﬁndings are hypothesis-generating and do not establish clinical efﬁcacy or safety; prospective, physician-supervised trials—potentially integrated with home INR monitoring—are required for validation. Keywords Warfarin, artiﬁcial intelligence, ChatGPT, INR monitoring, dosing, anticoagulation Received: 16 August 2025; accepted: 17 December 2025 Introduction Warfarin remains one of the most widely used oral anticoagulants worldwide for various indications, including nonvalvular atrial ﬁbrillation (AF), mechanical heart valves, and moderate-to-severe mitral stenosis, despite the increasing use of direct oral anticoagulants (DOACs) . 1,2 Maintaining an optimal international normalized ratio (INR), typically between 2.0 and 3.0, is crucial for minimizing thrombotic events while avoiding excessive bleeding risk.3,4 Yet, warfarin dose adjustment poses a signiﬁcant challenge due to a host of inﬂuencing factors, such as drug interactions, dietary changes, and individual genetic variability.5,6 As a result, clinicians often face a demanding process of frequent dose reﬁnements and close INR monitoring. 1 Department of Cardiology, Konya Selcuk University Medical Faculty Hospital, Konya, Turkey Corresponding author: Hüseyin Tezcan, Department of Cardiology, Konya Selcuk University Medical Faculty Hospital, Konya, Turkey. Email: [drhuseyintezcan@hotmail.com](drhuseyintezcan@hotmail.com) Creative Commons Non Commercial CC BY-NC: This article is distributed under the terms of the Creative Commons Attribution NonCommercial 4.0 License ([https://creativecommons.org/licenses/by-nc/4.0/](https://creativecommons.org/licenses/by-nc/4.0/)) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as speciﬁed on the SAGE

FAQs

What was the objective of the retrospective modeled study?

To evaluate how accurately ChatGPT (GPT-4) could perform warfarin dose adjustments compared with clinician recommendations for patients with INR values outside the therapeutic range.

How were ChatGPT dose recommendations generated in the study?

Physicians provided baseline INR, indication, comorbidities, and current dose to ChatGPT, which then produced hypothetical weekly dose recommendations.

What did the results show about dose agreement and therapeutic INR achievement?

ChatGPT’s recommended doses fell within ±1 mg/week of clinician prescriptions in 74% of cases and within ±2 mg/week in 84%. Therapeutic INR success was 72% with physician-managed dosing versus a modeled 69% for ChatGPT-guided dosing.

Sep 29, 2026

Upload by Indoniesian Boy