MétaCan
Menu
← Back to cohort
Record W4415217156 · doi:10.1136/heartjnl-2025-ics.21

21 Clinical logic and reasoning algorithm (CLARA): a whatsapp-based AI chatbot using artificial intelligence for precision anticoagulation in atrial fibrillation using a simulated and validated dataset

2025· article· en· W4415217156 on OpenAlexaff
Alaa Badawi, Kathryn L. Hong, Ben Glover

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsChatbotAtrial fibrillationDosingClinical decision support systemOral anticoagulantClinical PracticeSensitivity (control systems)

Abstract

fetched live from OpenAlex

Introduction The use of oral anticoagulation (OAC) in atrial fibrillation (AF) is often complicated by comorbidities such as renal dysfunction and bleeding risk. We developed and tested CLARA (Clinical Logic and Reasoning Algorithm), an AI-driven clinical decision support tool that uses a WhatsApp chatbot interface with a real-time Excel database (figure 1). Methods A simulated dataset of 150,000 AF patients was generated, each with full clinical profiles including age, sex, CHA2DS2-VASc components, HAS-BLED criteria, renal function (eGFR), weight, and previous anticoagulant exposure. A WhatsApp chatbot API was built to interact with healthcare providers, capturing structured inputs and relaying them in real time to a backend Excel-based clinical engine. The system matched responses with validated dosing algorithms (DOAC adjustment criteria) to recommend the precise agent and dose. To evaluate accuracy, CLARA was tested on a real-world dataset of 100 complex AF patients—preselected for challenging clinical profiles including renal impairment (eGFR <60) and high bleeding risk. The system’s OAC recommendations were compared against expert cardiologist consensus. Results CLARA achieved a sensitivity of 96% and a specificity of 94% in prescribing the correct agent and dose of OAC, based on gold-standard clinician judgement. Amongst patients with renal dysfunction (n=41), the algorithm correctly adjusted DOAC dosing in 39/41 cases. In patients with HAS-BLED ≥3 (n=36), CLARA accurately flagged bleeding risk and maintained guideline-appropriate prescribing. No inappropriate full-dose DOAC recommendations were issued in patients meeting criteria for dose reduction. The chatbot interaction averaged under 90 seconds per user. Conclusions/Implications CLARA demonstrates high sensitivity and specificity in providing individualized OAC recommendations in AF, including complex patients with renal impairment and bleeding risk. Its WhatsApp-based interface makes it highly accessible and adaptable in real-time clinical workflows. Further prospective validation is planned, but initial results support its potential as a scalable decision support tool for AF.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.017
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.010
Threshold uncertainty score0.034

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.017
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0020.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0100.002

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.335
GPT teacher head0.534
Teacher spread0.199 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicArtificial Intelligence in Healthcare and Education→French-language works237,207→