Key result
A population health intervention using machine learning algorithms and pharmacist review to identify and contact providers about undertreated atrial fibrillation patients did not increase new anticoagulant prescriptions compared to usual care (4.1% vs 4.0%, p=0.86).
Why the study?
Anticoagulation is recommended for high-risk AF, but studies report 40% of this population is not anticoagulated.
Does a population health intervention involving EHR algorithms and pharmacist outreach increase appropriate anticoagulant prescribing in high-risk patients with atrial fibrillation?
RCT (n=3,776)
Open-label
Stepped-wedge
Yes
Does a population health intervention involving EHR algorithms and pharmacist outreach increase appropriate anticoagulant prescribing in high-risk patients with atrial fibrillation?
Absolute Event Rate: 4.1% vs 4%
p-value: p=0.86
An EHR-based algorithm and pharmacist outreach intervention failed to increase appropriate anticoagulation prescribing in high-risk AF patients, highlighting the limitations of automated identification and the challenge of changing clinician behavior.
Intervention does not increase anticoagulation prescriptions in undertreated AF; challenges efficacy of ML-driven population health outreach.
BACKGROUND: Clinical guidelines recommend anticoagulation for patients with atrial fibrillation (AF) at high risk of stroke; however, studies report 40% of this population is not anticoagulated. OBJECTIVE: To evaluate a population health intervention to increase anticoagulation use in high-risk patients with AF. METHODS: -VASc risk score ≥2), and no anticoagulant prescriptions within 12 months. A clinical pharmacist in the anticoagulation service reviewed charts for algorithm-identified patients to assess appropriateness of initiating an anticoagulant. The pharmacist then contacted primary care providers of potentially undertreated patients and offered assistance with anticoagulation management. We used a stepped-wedge design, evaluating the proportion of potentially undertreated patients with AF started on anticoagulant therapy within 28 days for clinics randomised to intervention versus usual care. RESULTS: Of 1727 algorithm-identified high-risk patients with AF in clinics at the time of randomisation to intervention, 432 (25%) lacked evidence of anticoagulant prescriptions in the prior year. After pharmacist review, only 17% (75 of 432) of algorithm-identified patients were considered potentially undertreated at the time their clinic was randomised to intervention. Over a third (155 of 432) were excluded because they had a single prior AF episode (transient or provoked by serious illness); 36 (8%) had documented refusal of anticoagulation, the remainder had other reasons for exclusion. The intervention did not increase new anticoagulant prescriptions (intervention: 4.1% vs usual care: 4.0%, p=0.86). CONCLUSIONS: Algorithms to identify underuse of anticoagulation among patients with AF in healthcare databases may not capture clinical subtleties or patient preferences and may overestimate the extent of undertreatment. Changing clinician behaviour remains challenging.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2019) conducted an RCT in Atrial fibrillation (n=3,776). Population health intervention (algorithm identification, pharmacist review, and provider outreach) vs. Usual care was evaluated on Proportion of algorithm-identified eligible patients prescribed an oral anticoagulant within 28 days (p=0.86). A population health intervention using machine learning algorithms and pharmacist review to identify and contact providers about undertreated atrial fibrillation patients did not increase new anticoagulant prescriptions compared to usual care (4.1% vs 4.0%, p=0.86).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: