BACKGROUND AND AIM
Atrial fibrillation (AF) affects over 37 million people internationally and confers increased risk of cardiovascular conditions. Prediction algorithms have attempted to predict incident AF, but other cardio-renal diseases could also provide targets for earlier intervention.
METHOD
We derived a random forest classified for incident AF within 5 years (Future Innovations in Novel Detection of Atrial Fibrillation [FIND-AF] Taiwan) using routinely collected data from the National Taiwan University Hospital database. We compared this to congestive heart failure, hypertension, age >75 years (two points), diabetes mellitus, stroke/transient ischaemic attack/thromboembolism (two points), vascular disease, age 65-74 years, sex category (CHA2DS2-VASc) and coronary artery disease/chronic obstructive pulmonary disease (one point each), hypertension, elderly (age ≥75 years, two points), systolic heart failure, thyroid disease (hyperthyroidism) (C2HEST). Youden's Index was calculated to determine optimal threshold for higher versus lower predicted AF risk. We calculated cumulative incident curves and hazard ratios for incident AF, heart failure hospitalisation, or development of moderate-to-severe renal impairment, stroke or transient ischaemic attack and cardiovascular and all-cause mortality.
RESULTS
Overall, 103,321 patients were included, with an average age of 64.6 years and 52.8% women. Overall, 4.4% had incident AF over the 5-year follow-up period. FIND-AF Taiwan had better discrimination (area under received operating characteristic 0.792, 95% confidence interval [CI] 0.777-0.807) than CHA2DS2-VASc (0.737; 0.721-0.754) and C2HEST (0.750; 0.733-0.766). After adjustment, individuals at higher risk were at increased hazard for heart failure hospitalisation (hazard ratio 15.32; 95% CI 9.19-25.54), transient ischaemic attack or ischaemic stroke (28.4; 21.01-38.47), progression to moderate or severe chronic kidney disease (1.18; 1.09-1.27), cardiovascular mortality (1.32; 0.88-1.98), and all-cause mortality (1.23; 1.11-1.36).
CONCLUSIONS
We derived a supervised machine learning algorithm for AF in a Western Pacific population and demonstrated that higher risk was associated with hospitalisation for other cardio-renal diseases and death. This tool could be used to target interventions to reduce hospitalisation.
J. Hsu, C. Hayward, Tobin Joseph et al.· Heart, Lung and Circulation· 0 citations
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. 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.
R. Nadarajah, Jianhua Wu, A. Wahab et al.· Circulation· 0 citations