Think-HF: Development, feasibility, and usability of an electronic health record integrated tool for identifying missed diagnoses of heart failure in primary care

Authors:
Preprint
Publisher website
Google Scholar
Abstract
Background: Many patients with heart failure (HF) remain undiagnosed until acute hospital admission for decompensation. Think-HF is a clinical decision support tool (CDST) designed to identify possible undiagnosed HF in primary care and trigger timely, guideline recommended assessment. Methods: Think-HF was developed through epidemiological evidence and codesign. Integrated within SystmOne, it analyses routine primary care data (codes, medications, test results, free text) to detect missed or emerging HF signals. When a record is opened, if a patient has ≥ two comorbidity indicators plus an HF-suggestive symptom, an alert is triggered and a structured template opens with one-click options for natriuretic peptide (NP) testing, echocardiography, specialist referral and coding. Additional algorithms identify unresolved investigations, coding inconsistencies and medication-based signals, generating a marker on the patient’s record. A mixed-methods feasibility study across six primary care practices assessed reach, usability, acceptability, and early implementation signals, using the RE-AIM framework. Results: Six socioeconomically and ethnically diverse general practices participated (63 GPs; 78,640 patients [47.5% women, 59.4% White, 17.8% South Asian, 8.5% Black, 3% Chinese and 2.8% mixed ethnicities]). At baseline, 876 patients (1.1%) met the main alert criteria and 2,805 (3.6%) met additional algorithm criteria. Of 801 patients on the HF register, 665 (83%) lacked a refined HF left ventricular phenotype code. During four months of testing, Think-HF generated 299 clinically relevant main trigger alerts (75% during consultations). Early improvements included (i) 31 new HF diagnoses (+4.2%), with higher gains (+10%) in practices with lower baseline prevalence; (ii) a 14% increase in refined HF phenotype coding; (iii) fewer raised NT-proBNP results without follow-up (−7%); and (iv) fewer patients prescribed loop diuretics without NP testing (−14%, up to −45% in one practice with pharmacist-supported review). Clinicians reported improved awareness, more systematic assessment, and better follow-up of missed investigations or coding anomalies. Identified gaps aligned with patient-reported delays and misattributed symptoms. Conclusions: Think-HF is feasible, acceptable and well aligned with routine primary care workflows. Early gains in diagnostic processes and coding accuracy highlight its potential to improve patient care. Team-based implementation will be essential for scale-up. Larger evaluation is required to assess clinical impact.

This publication has 59 references indexed in Scilit: