{"id":"01884c9bbf4b","type":"article","url":"https://hartvaat.nl/2026/08/25/risicogestuurde-af-screening-met-machine-learning-verhoogt-detectiegraad-find-af/","title":"Risicogestuurde AF-screening met machine learning verhoogt detectiegraad — FIND-AF 2.0","title_en":"Risk-Guided Screening for Atrial Fibrillation Using Electronic Health Records.","category":"atriumfibrilleren","category_label":"Atriumfibrilleren","professions":["cardioloog","huisarts"],"tags":[],"journal":"Circulation","doi":"10.1161/CIRCULATIONAHA.126.079391","source_url":"https://doi.org/10.1161/CIRCULATIONAHA.126.079391","authors":["Ramesh Nadarajah","Jianhua Wu","Ali Wahab","Catherine Reynolds","Mohammad Haris","Tobin Joseph","Keerthenan Raveendra","Ben Hurdus","Khalid Kazi","Sheena Bennett","Chris Hayward","Ben Mercer","Jing Kang","Chenyi Gao","Yoko M Nakao","Koji Kawakami","Carlin Chang","Abraham Wai","Jiandong Zhou","Gary Tse","Talish Razi Benita","Lior Rokach","Ronen Arbel","Moti Haim","Doron Zahger","Dina Labib","Jacqueline Flewitt","James A White","Konsta Teppo","Mika Lehto","Ville Langén","Aleksi K Winstén","K E Juhani Airaksinen","Jari Haukka","Olli Halminen","Jukka Putaala","Juha Hartikainen","Miika Linna","Ben Freedman","Emma Svennberg","A John Camm","Gregory Y H Lip","Chris P Gale"],"significance":7,"published":"2026-09-01","source_date":"2026-08-25","image":"","kennis":["https://hartvaat.nl/kennis/atriumfibrilleren/af-en-beroerte/","https://hartvaat.nl/kennis/atriumfibrilleren/chadsvasc-score/"],"congress":"","summary_en":"Researchers developed and externally validated FIND-AF 2.0, a machine learning model using electronic health records to identify patients at high risk of developing atrial fibrillation (AF). In a prospective screening study of 1,923 adults, AF was detected in 4.5% of high-risk participants compared to 0.6% of low-risk individuals (OR 8.46; P<0.001), outperforming conventional risk scores like CHA₂DS₂-VASc. Implementing this EHR-driven approach could enable targeted AF screening in primary care and cardiology, catching high-burden AF earlier and reducing the risk of ischemic stroke (6.0 events per 100 patient-years) in untreated patients.","created":"2026-08-25T01:08:52Z","updated":"2026-08-25T01:08:52Z","licence":"Citeer vrij, met bronvermelding en een link naar hartvaat.nl (de url van het record). Samenvattingen zijn redactioneel werk van HartVaat; de oorspronkelijke publicaties blijven van hun uitgevers (doi). Geen medisch advies.","body_markdown":"Onderzoekers ontwikkelden en valideerden FIND-AF 2.0, een machine learning-model op basis van elektronische patiëntendossiers, om patiënten met een verhoogd risico op atriumfibrilleren (AF) te identificeren. In een prospectieve studie met 1923 deelnemers werd AF bij 4,5% van de hoog-risicopatiënten gedetecteerd tegenover 0,6% in de laag-risicogroep (OR 8,46; p<0,001). Het model overtreft traditionele scores zoals CHA₂DS₂-VASc en kan huisartsen en cardiologen helpen om AF-screening gerichter in te zetten, waardoor onbehandelde AF met een hoog stroke-risico eerder wordt opgespoord.","abstract_original":"BACKGROUND: Screening for atrial fibrillation (AF) on the basis of AF risk may be more effective. We aimed to develop, externally validate, and prospectively test a machine learning prediction model using electronic health records (EHRs) to guide AF screening. METHODS: We developed and validated a random forest prediction model for new AF within 6 months, using age, sex, and 10 comorbidities (Future Innovations in Novel Detection of Atrial Fibrillation [FIND-AF] 2.0) in EHRs in the United Kingdom (n=2 081 139), Japan (n=7 795 244), Israel (n=2 166 795), Canada (n=627 919), and China (n=149 145). We conducted a prospective study where participants ≥30 years old without AF and with a CHA2DS2-VASc score ≥2 in men and ≥3 in women, stratified by FIND-AF 2.0 into high and low risk, undertook 4 ECG recordings per day for 3 weeks using a handheld ECG recorder, with a primary outcome of newly diagnosed AF. We estimated stroke risk associated with nonanticoagulated AF in patients with high FIND-AF 2.0 risk in the FinACAF (Finnish Anticoagulation in Atrial Fibrillation) registry of patients with AF (n=229 565). RESULTS: FIND-AF 2.0 was applicable to all EHRs and showed good to excellent prediction performance (United Kingdom: area under the receiver operating characteristic curve [AUROC], 0.819 [95% CI, 0.809-0.829]; Israel: AUROC, 0.835 [95% CI, 0.828-0.842]; Japan: AUROC, 0.751 [95% CI, 0.745-0.757]; Canada: AUROC, 0.747 [95% CI, 0.741-0.753]; China: AUROC, 0.753 [95% CI, 0.725-0.771]), with AUROC>0.7 in men and women in all cohorts, and improved performance compared with CHA2DS2-VASc and C2HEST (coronary artery disease or chronic obstructive pulmonary disease [1 point each]; hypertension [1 point]; elderly [age ≥75 years, 2 points]; systolic HF [2 points]; thyroid disease [hyperthyroidism, 1 point]). Of 1923 participants from 15 sites in the prospective study (mean age, 70.2 [SD 9.4] years), with a mean of 74.8 (SD, 19.4) ECG recordings, AF was diagnosed in 5 of 902 (0.6%) with low FIND-AF 2.0 risk and 46 of 1021 (4.5%) with high FIND-AF 2.0 risk (odds ratio, 8.46 [95% CI, 3.35-21.40], P<0.001). Median AF burden among high FIND-AF 2.0 risk-detected cases was 33.4% (interquartile range, 5.1%-91.6%), and 96.1% initiated oral anticoagulants. In the FinACAF registry, the rate of ischemic stroke for patients with high FIND-AF 2.0 risk, AF, and no anticoagulants was 6.0 events per 100 patient-years. CONCLUSIONS: The EHR-based machine learning model, FIND-AF 2.0, identifies a high-risk subpopulation for AF diagnosis among patients at elevated risk of stroke and could enable scalable, EHR-driven, risk-guided AF screening."}