Prediction of incident atrial fibrillation in community-based electronic health records: a systematic review with meta-analysis

Abstract

Objective: Atrial fibrillation (AF) is common and is associated with an increased risk of stroke. We aimed to systematically review and meta-analyse multivariable prediction models derived and/or validated in electronic health records (EHRs) and/or administrative claims databases for the prediction of incident AF in the community.

Methods: Ovid Medline and Ovid Embase were searched for records from inception to 23 March 2021. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation.

Results: Eleven studies met inclusion criteria, describing nine prediction models, with four eligible for meta-analysis including 9 289 959 patients. The CHADS (Congestive heart failure, Hypertension, Age>75, Diabetes mellitus, prior Stroke or transient ischemic attack) (summary c-statistic 0.674; 95% CI 0.610 to 0.732; 95% PI 0.526-0.815), CHA₂DS₂-VASc (Congestive heart failure, Hypertension, Age>75 (2 points), Stroke/transient ischemic attack/thromboembolism (2 points), Vascular disease, Age 65-74, Sex category) (summary c-statistic 0.679; 95% CI 0.620 to 0.736; 95% PI 0.531-0.811) and HATCH (Hypertension, Age, stroke or Transient ischemic attack, Chronic obstructive pulmonary disease, Heart failure) (summary c-statistic 0.669; 95% CI 0.600 to 0.732; 95% PI 0.513-0.803) models resulted in a c-statistic with a statistically significant 95% PI and moderate discriminative performance. No model met eligibility for inclusion in meta-analysis if studies at high risk of bias were excluded and certainty of effect estimates was 'low'. Models derived by machine learning demonstrated strong discriminative performance, but lacked rigorous external validation.

Conclusions: Models externally validated for prediction of incident AF in community-based EHR demonstrate moderate predictive ability and high risk of bias. Novel methods may provide stronger discriminative performance.

Systematic review registration: PROSPERO CRD42021245093.

Keywords: atrial fibrillation; electronic health records; meta-analysis; primary care.

Figure 1

Flow diagram of literature search. AF, atrial fibrillation; AFl, atrial flutter; EHR, electronic health record.

Figure 2

An overview of the ten predictors most frequently incorporated in the prediction models in this study. IHD, ischaemic heart disease; MI, myocardial infarction; SBP, systolic blood pressure.

Figure 3

Judgements on the four PROBAST risk of bias domains and three PROBAST applicability domains presented as percentages across all included studies. PROBAST, Prediction model Risk of Bias ASsessment Tool; ROB, risk of bias.

Figure 4

Forest plot of primary analysis of c-statistics. C₂HEST, Coronary artery disease/chronic obstructive pulmonary disease (one point each), Hypertension, Elderly (Age ≥75, 2 points), Systolic heart failure, Thyroid disease (hyperthyroidism); CHADS₂, Congestive Heart failure, hypertension, Age>75, Diabetes mellitus, prior Stroke or transient ischaemic attack (two points); CHA₂DS₂-VASc, Congestive heart failure, Hypertension, Age >75 (2 points), Stroke/transient ischaemic attack/thromboembolism (two points), Vascular disease, Age 65–74, sex category; ClalitHS, Clalit health services; HATCH, Hypertension, Age, stroke or Transient ischemic attack, Chronic obstructive pulmonary disease, and Heart failure; NHIRD, National Health Insurance Research Database; NHIS-HEALS, National Health Insurance Service - Health screening Cohort; NHIS-NSC, National Health Insurance Service-based National Sample Cohort; Nivel-PCD, Netherlands Institute for Health Services Research Primary Care Database; YMID, Yunnan Medical Insurance Database.