Development, Implementation, and Assessment of a Computer Decision Support System for Monitoring and Management of Oral Anticoagulation With Warfarin in Resource-Constrained Settings: Mixed Methods Study

Background: Warfarin remains the mainstay of oral anticoagulation in low- and middle-income countries and in specific clinical conditions, despite its complex management and the risks associated with poor anticoagulation control. In this context, clinical decision support systems (CDSS) have the potential to improve anticoagulation safety and efficacy, particularly in primary care. Objective: This study aims to develop a CDSS aimed at enhancing anticoagulation management in primary care, to implement it in a resource-constrained region, and to evaluate its usability and satisfaction among health care professionals. Methods: The study followed a mixed methods, 4-phase design based on the Medical Research Council framework. Phase 1 involved a cross-sectional assessment of primary care units to identify gaps in usual anticoagulation care. In phase 2, a baseline prototype of a secure, web-based application was developed, featuring structured patient data entry and tools for monitoring anticoagulation quality, but without decision-support messages. Formative evaluation was conducted over 8 months through real-world use of the prototype by health care professionals, assessing system functionality, usability, and data entry processes to guide refinement of system features; these professionals assessed 514 patients in 4022 consultations. Phase 3 focused on the development of individualized decision-support messages. Phase 4 consisted of a pilot implementation during routine outpatient consultations, in which trained clinical pharmacists used the CDSS, and usability and acceptability were evaluated through semistructured interviews, and qualitative data were analyzed thematically. Results: The final CDSS included 210 tailored clinical recommendations addressing anticoagulation indication, dose adjustment, drug-drug interactions, and bleeding management. Internal validation demonstrated the logical consistency of the algorithms and accurate triggering of decision support messages. The system was successfully adopted by all trained pharmacists and integrated into routine workflows. Users reported high usability, intuitive navigation, and perceived usefulness of graphical tools for monitoring international normalized ratio (INR) and time in therapeutic range. The system was perceived to improve consultation organization, standardize clinical decision-making, enhance patient education, and support longitudinal follow-up. Key barriers included time constraints, competing demands, occasional technical issues, and lack of integration with electronic health records. Conclusions: This study demonstrates the feasibility and acceptability of a CDSS for anticoagulation management in primary care in a resource-constrained setting. The iterative development process, including extensive real-world formative evaluation prior to implementation of decision-support logic, strengthened system usability and alignment with clinical workflows. Future studies should evaluate its effectiveness on clinical outcomes and explore strategies to enhance integration, scalability, and sustainability.

Authors

Institutions

Publication Details

Journal
JMIR Medical Informatics
Published
2026-11-16
DOI
https://doi.org/10.2196/94103
Primary Topic
Electronic Health Records Systems
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Development, Implementation, and Assessment of a Computer Decision Support System for Monitoring and Management of Oral Anticoagulation With Warfarin in Resource-Constrained Settings: Mixed Methods Study

Isabella Viana Gomes Schettini, Thiago Barbabela de Castro Soares, Lílian Cristina Rezende, Thábata Queiroz Vivas de Sá et al.
JMIR Medical Informatics
Electronic Health Records Systems
article

Development, Implementation, and Assessment of a Computer Decision Support System for Monitoring and Management of Oral Anticoagulation With Warfarin in Resource-Constrained Settings: Mixed Methods Study

Isabella Viana Gomes Schettini, Thiago Barbabela de Castro Soares, Lílian Cristina Rezende, Thábata Queiroz Vivas de Sá, Danyelle Romana Alves Rios, Milena Soriano Marcolino, Antônio Luiz Pinho Ribeiro, Rafaela Bonfioli Costa, Lara Mattos Pires, Leticia Vitoria Ramos da Cunha
article en

Abstract

Background: Warfarin remains the mainstay of oral anticoagulation in low- and middle-income countries and in specific clinical conditions, despite its complex management and the risks associated with poor anticoagulation control. In this context, clinical decision support systems (CDSS) have the potential to improve anticoagulation safety and efficacy, particularly in primary care. Objective: This study aims to develop a CDSS aimed at enhancing anticoagulation management in primary care, to implement it in a resource-constrained region, and to evaluate its usability and satisfaction among health care professionals. Methods: The study followed a mixed methods, 4-phase design based on the Medical Research Council framework. Phase 1 involved a cross-sectional assessment of primary care units to identify gaps in usual anticoagulation care. In phase 2, a baseline prototype of a secure, web-based application was developed, featuring structured patient data entry and tools for monitoring anticoagulation quality, but without decision-support messages. Formative evaluation was conducted over 8 months through real-world use of the prototype by health care professionals, assessing system functionality, usability, and data entry processes to guide refinement of system features; these professionals assessed 514 patients in 4022 consultations. Phase 3 focused on the development of individualized decision-support messages. Phase 4 consisted of a pilot implementation during routine outpatient consultations, in which trained clinical pharmacists used the CDSS, and usability and acceptability were evaluated through semistructured interviews, and qualitative data were analyzed thematically. Results: The final CDSS included 210 tailored clinical recommendations addressing anticoagulation indication, dose adjustment, drug-drug interactions, and bleeding management. Internal validation demonstrated the logical consistency of the algorithms and accurate triggering of decision support messages. The system was successfully adopted by all trained pharmacists and integrated into routine workflows. Users reported high usability, intuitive navigation, and perceived usefulness of graphical tools for monitoring international normalized ratio (INR) and time in therapeutic range. The system was perceived to improve consultation organization, standardize clinical decision-making, enhance patient education, and support longitudinal follow-up. Key barriers included time constraints, competing demands, occasional technical issues, and lack of integration with electronic health records. Conclusions: This study demonstrates the feasibility and acceptability of a CDSS for anticoagulation management in primary care in a resource-constrained setting. The iterative development process, including extensive real-world formative evaluation prior to implementation of decision-support logic, strengthened system usability and alignment with clinical workflows. Future studies should evaluate its effectiveness on clinical outcomes and explore strategies to enhance integration, scalability, and sustainability.

JMIR Medical InformaticsVol. 14
Universidade Federal de Minas Gerais (BR), Universidade Federal de Viçosa (BR), Federal University of São João del-Rei (BR)
Electronic Health Records Systems
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon