AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis

Abstract Background Standard‐of‐care for warfarin dose titration is conventionally based on physician‐guided drug dosing. This may lead to frequent deviations from target international normalized ratio (INR) due to inter‐ and intra‐patient variability and may potentially result in adverse events inc...

Full description

Saved in:
Bibliographic Details
Main Authors: Tiffany Rui Xuan Gan, Lester W. J. Tan, Mathias Egermark, Anh T. L. Truong, Kirthika Kumar, Shi‐Bei Tan, Sarah Tang, Agata Blasiak, Boon Cher Goh, Kee Yuan Ngiam, Dean Ho
Format: Article
Language:English
Published: Wiley 2025-05-01
Series:Bioengineering & Translational Medicine
Subjects:
Online Access:https://doi.org/10.1002/btm2.10757
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849321689294307328
author Tiffany Rui Xuan Gan
Lester W. J. Tan
Mathias Egermark
Anh T. L. Truong
Kirthika Kumar
Shi‐Bei Tan
Sarah Tang
Agata Blasiak
Boon Cher Goh
Kee Yuan Ngiam
Dean Ho
author_facet Tiffany Rui Xuan Gan
Lester W. J. Tan
Mathias Egermark
Anh T. L. Truong
Kirthika Kumar
Shi‐Bei Tan
Sarah Tang
Agata Blasiak
Boon Cher Goh
Kee Yuan Ngiam
Dean Ho
author_sort Tiffany Rui Xuan Gan
collection DOAJ
description Abstract Background Standard‐of‐care for warfarin dose titration is conventionally based on physician‐guided drug dosing. This may lead to frequent deviations from target international normalized ratio (INR) due to inter‐ and intra‐patient variability and may potentially result in adverse events including recurrent thromboembolism and life‐threatening hemorrhage. Objectives We aim to employ CURATE.AI, a small‐data, artificial intelligence‐derived platform that has been clinically validated in a range of indications, to optimize and guide warfarin dosing. Patients/methods A personalized CURATE.AI response profile was generated using warfarin dose (inputs) and corresponding change in INR between two consecutive days (phenotypic outputs) and used to identify and recommend an optimal dose to achieve target treatment outcomes. CURATE.AI's predictive performance was then evaluated with a set of metrics that assessed both technical performance and clinical relevance. Results and conclusions In this retrospective study of 127 patients, CURATE.AI fared better in terms of Percentage Absolute Prediction Error and Percentage Prediction Error of 20% compared to other models in the literature. It also had negligible underprediction bias, potentially translating into lower bleeding risk. Modeled potential time in therapeutic range with CURATE.AI was not significantly different from physician‐guided dosing, so it is on‐par yet provides a systematic approach to warfarin dosing, easing the mental‐burden on guesswork by physicians. This study lays the groundwork for the prospective study of CURATE.AI as a clinical decision support system. CURATE.AI may facilitate the effective use of affordable warfarin with a well‐established safety profile, without the need for costly, new oral anticoagulants. This can have significant impact both on the individual and public health.
format Article
id doaj-art-40c25dc7f58047bf8bcaef29701b84fe
institution Kabale University
issn 2380-6761
language English
publishDate 2025-05-01
publisher Wiley
record_format Article
series Bioengineering & Translational Medicine
spelling doaj-art-40c25dc7f58047bf8bcaef29701b84fe2025-08-20T03:49:41ZengWileyBioengineering & Translational Medicine2380-67612025-05-01103n/an/a10.1002/btm2.10757AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysisTiffany Rui Xuan Gan0Lester W. J. Tan1Mathias Egermark2Anh T. L. Truong3Kirthika Kumar4Shi‐Bei Tan5Sarah Tang6Agata Blasiak7Boon Cher Goh8Kee Yuan Ngiam9Dean Ho10Division of Surgery Ng Teng Fong General Hospital Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeYong Loo Lin School of Medicine National University of SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeDivision of Haematology‐Oncology National University Hospital Singapore SingaporeDivision of Surgery National University Hospital Singapore SingaporeThe N.1 Institute for Health (N.1), National University of Singapore Singapore SingaporeAbstract Background Standard‐of‐care for warfarin dose titration is conventionally based on physician‐guided drug dosing. This may lead to frequent deviations from target international normalized ratio (INR) due to inter‐ and intra‐patient variability and may potentially result in adverse events including recurrent thromboembolism and life‐threatening hemorrhage. Objectives We aim to employ CURATE.AI, a small‐data, artificial intelligence‐derived platform that has been clinically validated in a range of indications, to optimize and guide warfarin dosing. Patients/methods A personalized CURATE.AI response profile was generated using warfarin dose (inputs) and corresponding change in INR between two consecutive days (phenotypic outputs) and used to identify and recommend an optimal dose to achieve target treatment outcomes. CURATE.AI's predictive performance was then evaluated with a set of metrics that assessed both technical performance and clinical relevance. Results and conclusions In this retrospective study of 127 patients, CURATE.AI fared better in terms of Percentage Absolute Prediction Error and Percentage Prediction Error of 20% compared to other models in the literature. It also had negligible underprediction bias, potentially translating into lower bleeding risk. Modeled potential time in therapeutic range with CURATE.AI was not significantly different from physician‐guided dosing, so it is on‐par yet provides a systematic approach to warfarin dosing, easing the mental‐burden on guesswork by physicians. This study lays the groundwork for the prospective study of CURATE.AI as a clinical decision support system. CURATE.AI may facilitate the effective use of affordable warfarin with a well‐established safety profile, without the need for costly, new oral anticoagulants. This can have significant impact both on the individual and public health.https://doi.org/10.1002/btm2.10757artificial intelligenceblood coagulationclinicaldecision support systemsprecision medicinewarfarin
spellingShingle Tiffany Rui Xuan Gan
Lester W. J. Tan
Mathias Egermark
Anh T. L. Truong
Kirthika Kumar
Shi‐Bei Tan
Sarah Tang
Agata Blasiak
Boon Cher Goh
Kee Yuan Ngiam
Dean Ho
AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
Bioengineering & Translational Medicine
artificial intelligence
blood coagulation
clinical
decision support systems
precision medicine
warfarin
title AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
title_full AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
title_fullStr AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
title_full_unstemmed AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
title_short AI‐assisted warfarin dose optimisation with CURATE.AI for clinical impact: Retrospective data analysis
title_sort ai assisted warfarin dose optimisation with curate ai for clinical impact retrospective data analysis
topic artificial intelligence
blood coagulation
clinical
decision support systems
precision medicine
warfarin
url https://doi.org/10.1002/btm2.10757
work_keys_str_mv AT tiffanyruixuangan aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT lesterwjtan aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT mathiasegermark aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT anhtltruong aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT kirthikakumar aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT shibeitan aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT sarahtang aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT agatablasiak aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT boonchergoh aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT keeyuanngiam aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis
AT deanho aiassistedwarfarindoseoptimisationwithcurateaiforclinicalimpactretrospectivedataanalysis