Prediction models for atrial fibrillation applicable in the community: a systematic review and meta-analysis

Abstract

Aims: Atrial fibrillation (AF) is a common arrhythmia associated with an increased stroke risk. The use of multivariable prediction models could result in more efficient primary AF screening by selecting at-risk individuals. We aimed to determine which model may be best suitable for increasing efficiency of future primary AF screening efforts.

Methods and results: We performed a systematic review on multivariable models derived, validated, and/or augmented for AF prediction in community cohorts using Pubmed, Embase, and CINAHL (Cumulative Index to Nursing and Allied Health Literature) through 1 August 2019. We performed meta-analysis of model discrimination with the summary C-statistic as the primary expression of associations using a random effects model. In case of high heterogeneity, we calculated a 95% prediction interval. We used the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist for risk of bias assessment. We included 27 studies with a total of 2 978 659 unique participants among 20 cohorts with mean age ranging from 42 to 76 years. We identified 21 risk models used for incident AF risk in community cohorts. Three models showed significant summary discrimination despite high heterogeneity: CHARGE-AF (Cohorts for Heart and Aging Research in Genomic Epidemiology) [summary C-statistic 0.71; 95% confidence interval (95% CI) 0.66-0.76], FHS-AF (Framingham Heart Study risk score for AF) (summary C-statistic 0.70; 95% CI 0.64-0.76), and CHA2DS2-VASc (summary C-statistic 0.69; 95% CI 0.64-0.74). Of these, CHARGE-AF and FHS-AF had originally been derived for AF incidence prediction. Only CHARGE-AF, which comprises easily obtainable measurements and medical history elements, showed significant summary discrimination among cohorts that had applied a uniform (5-year) risk prediction window.

Conclusion: CHARGE-AF appeared most suitable for primary screening purposes in terms of performance and applicability in older community cohorts of predominantly European descent.

Keywords: Atrial fibrillation; Community; Meta-analysis; Risk model; Screening; Systematic review.

Figure 1

Literature flow diagram. AF, atrial fibrillation; AFl, atrial flutter; CINAHL, Cumulative Index to Nursing and Allied Health Literature; NA, not applicable.

Figure 2

Primary analysis: meta-analysis of C-statistics. 95% CI, 95% confidence interval; AF, atrial fibrillation; AGES, Age, Gene and Environment-Reykjavik Study; ARIC, Atherosclerosis Risk In Communities; CHADS_2, Congestive heart failure, Hypertension, Age >75, Diabetes mellitus, prior Stroke or transient ischaemic attack (2 points); CHA₂DS₂-VASc, Congestive HF, Hypertension, Age >75 (2 points), Stroke/transient ischaemic attack/thromboembolism (2 points), Vascular disease, Age 65–74, Sex category; CHARGE-AF, Cohorts for Heart and Aging Research in Genomic Epidemiology; CI, confidence interval; EPIC, European Prospective Investigation into Cancer and Nutrition; FHS, Framingham Heart Study; FHS-AF, Framingham Heart Study score for Atrial Fibrillation; HATCH, Hypertension, Age, stroke or Transient ischaemic attack, Chronic obstructive pulmonary disease, Heart failure; IV, inverse variance; MPP-RES, Malmö Preventive Project Re-examination Study; NHIS, National Health Insurance Service; NHIRD, National Health Insurance Research Database; PIVUS, Prospective Investigation of the Vasculature in Uppsala Seniors; RS, Rotterdam Study; YMID, Yunnan Medical Insurance Database. ^aDerivation cohort.

Figure 3

Comparison of the three models that resulted in significant 95% prediction intervals in the primary meta-analysis. 95% CI, 95% confidence interval; 95% PI, 95% prediction interval; AF, atrial fibrillation; AGES, Age, Gene and Environment-Reykjavik Study; ARIC, Atherosclerosis Risk In Communities; BMI, body mass index; CHA₂DS₂-VASc, Congestive HF, Hypertension, Age >75 (2 points), Stroke/transient ischaemic attack/thromboembolism (2 points), Vascular disease, Age 65–74, Sex category; CHARGE-AF, Cohorts for Heart and Aging Research in Genomic Epidemiology; C-stat., C-statistic; ECG, electrocardiogram; EPIC, European Prospective Investigation into Cancer and Nutrition; FHS, Framingham Heart Study; FHS-AF, Framingham Heart Study score for Atrial Fibrillation; MPP-RES, Malmö Preventive Project Re-examination Study; NA, not applicable; NHIS, National Health Insurance Service; PIVUS, Prospective Investigation of the Vasculature in Uppsala Seniors; RS, Rotterdam Study; YMID, Yunnan Medical Insurance Database. The meta-analyses of C-statistics for the outcome incident AF are grouped by cohort from which C-statistics were reported, allowing for a comparison of multiple models’ performance within one cohort insofar as data are available.

Figure 4

Secondary analysis: meta-analysis of C-statistics grouped according to application of a uniform prediction window within a model. AGES, Age, Gene and Environment-Reykjavik Study; ARIC, Atherosclerosis Risk In Communities; CHARGE-AF, Cohorts for Heart and Aging Research in Genomic Epidemiology; CI, confidence interval; EPIC, European Prospective Investigation into Cancer and Nutrition; FHS, Framingham Heart Study; FHS-AF, Framingham Heart Study score for Atrial Fibrillation; IV, inverse variance; MPP-RES, Malmö Preventive Project Re-examination Study; PIVUS, Prospective Investigation of the Vasculature in Uppsala Seniors; RS, Rotterdam Study; 95% CI, 95% confidence interval. ^aDerivation cohort.