Twelve-Year Real-World Evaluation of a Regulated Guideline-Based Warfarin Dosing and Care Automation System
Tiihonen, M.
Show abstract
Background: Warfarin therapy requires repetitive dose adjustments based on INR (International Normalised Ratio) monitoring. We evaluated the long-term real-world performance of Forsante Warfarin Advisor (WA), a CE-marked class IIb guideline-based decision support and care automation medical device used in anticoagulation management. Methods: Retrospective real-world data from routine clinical use between 2016 and 2026 were analysed. Treatment quality was assessed using Time in Therapeutic Range (TTR). Recommendation performance was evaluated by comparing achievement of target INR after clinician acceptance or modification of Warfarin Advisor recommendations. Results: Among 1348 patients in March 2026 median TTR was 83%, compared with 70% in March 2016. Dosages congruent with Warfarin Advisor recommendations were strongly associated with achieving target INR at follow-up in INR target ranges of 2.0-3.0 and 2.5-3.5. Treatment quality remained consistently high across years of deployment. No serious device-attributable safety incidents, regulatory incident reports, or CAPA cases were identified during 12 calendar years and 82,709 patient years of routine use. Conclusions: The findings provide real-world long-term evidence that a guideline-based warfarin dosing and care automation system can support sustained high-quality anticoagulation control in routine clinical practice. The findings support the feasibility of deploying workflow-integrated execution of selected guideline-driven clinical processes, while the causal effects on clinical outcomes require prospective confirmation. Keywords: Clinical decision support systems, Guideline execution, Real-world evidence, Warfarin, Anticoagulation
Matching journals
The top 8 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Aggregating Multiple Real-World Data Sources using a Patient-Centered Health Data Sharing Platform: an 8-week Cohort Study among Patients Undergoing Bariatric Surgery or Catheter Ablation of Atrial Fibrillation 91%
- How AI is used in FDA-authorized medical devices: a taxonomy across 1,016 authorizations 90%
- The clinician-AI interface: intended use and explainability in FDA-cleared AI devices for medical image interpretation 90%
Similar papers in this journal
- An Informatics Consult approach for generating clinical evidence for treatment decisions 93%
- Electronic prescribing systems as tools to improve patient care: a learning health systems approach to increase guideline concordant prescribing for venous thromboembolism prevention 92%
- Impact of CancelRx on Discontinuation of Controlled Substance Prescriptions 89%
Similar papers in this journal
- Empowering Personalized Pharmacogenomics with Generative AI Solutions 91%
- Usability of a Machine-Learning Clinical Order Recommender System Interface for Clinical Decision Support and Physician Workflow 91%
- Learning Decision Thresholds for Risk-Stratification Models from Aggregate Clinician Behavior 91%
Similar papers in this journal
- Determining prescriptions in electronic health care (EHR) data: methods for development of standardised, reproducible drug codelists 92%
- Development and Application of Pharmacological Statin-Associated Muscle Symptoms Phenotyping Algorithms Using Structured and Unstructured Electronic Health Records Data 91%
- Framework for Identifying Drug Repurposing Candidates from Observational Healthcare Data 90%
Similar papers in this journal
- Medical Clinical Minds Meet Artificial Intelligence: Italian Physicians' Knowledge, Attitudes, and Concordance between Italian Physicians and AI-Generated Diagnoses. A National Cross-Sectional Study 90%
- Large Language Models in Real-World Clinical Workflows: A Systematic Review of Applications and Implementation 89%
- Development and Validation of a Machine Learning Model Integrated with the Clinical Workflow for Inpatient Discharge Date Prediction 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.