Evaluation of Risk Prediction Models of Atrial Fibrillation (From the Multi-Ethnic Study of Atherosclerosis [MESA])

Abstract

Atrial fibrillation (AF) is prevalent and strongly associated with higher cardiovascular disease (CVD) risk. Machine learning is increasingly used to identify novel predictors of CVD risk, but prediction improvements beyond established risk scores are uncertain. We evaluated improvements in predicting 5-year AF risk when adding novel candidate variables identified by machine learning to the CHARGE-AF Enriched score, which includes age, race/ethnicity, height, weight, systolic and diastolic blood pressure, current smoking, use of antihypertensive medication, diabetes, and NT-proBNP. We included 3534 participants (mean age, 61.3 years; 52.0% female) with complete data from the prospective Multi-Ethnic Study of Atherosclerosis (MESA). Incident AF was defined based on study electrocardiograms and hospital discharge diagnosis ICD-9 codes, supplemented by Medicare claims. Prediction performance was evaluated using Cox regression and a parsimonious. model was selected using LASSO. Within 5 years of baseline, 124 participants had incident AF. Compared with the CHARGE-AF Enriched model (c-statistic, 0.804), variables identified by machine learning, including biomarkers, cardiac magnetic resonance imaging variables, electrocardiogram variables, and subclinical CVD variables, did not significantly improve prediction. A 23-item score derived by machine learning achieved a c-statistic of 0.806, while a parsimonious model including the clinical risk factors age, weight, current smoking, NT-proBNP, coronary artery calcium score, and cardiac troponin-T achieved a c-statistic of 0.802. This analysis confirms that the CHARGE-AF Enriched model and a parsimonious 6-item model performed similarly to a more extensive model derived by machine learning. In conclusion, these simple models remain the gold standard for risk prediction of AF, although addition of the coronary artery calcium score should be considered.

Atrial fibrillation (AF) is the most common clinically-significant cardiac arrhythmia and is strongly associated with higher risk of stroke and other cardiovascular disease (CVD) outcomes.^1–5 Risk prediction scores for incident AF could be useful clinically to identify high-risk patients for additional surveillance or for participation in prevention trials.^6–10 The validated Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) AF consortium model includes several important demographic and clinical variables.^8,9,11,12 Machine learning techniques are becoming increasingly common and are proposed to improve risk prediction.¹³ In a machine learning study within the Multi-Ethnic Study of Atherosclerosis (MESA), researchers included >700 baseline variables in an attempt to improve risk prediction for several CVD outcomes, including AF. However, their potential prediction benefits beyond previous AF risk scores are unknown. The objectives of the current analysis are two-fold: to evaluate whether novel candidate variables improve prediction of 5-year risk of AF in MESA participants when added to the CHARGE-AF models and develop a parsimonious model in MESA.

Methods

The MESA is a prospective, population-based observational cohort study of 6814 men and women representing 4 racial/ethnic groups (Caucasian, African-American, Hispanic and Chinese-American), aged 45–84 years and free of clinical CVD at enrollment.¹⁵ As part of the baseline examination (2000–2002), study participants were recruited at 6 field centers in the US (Baltimore, MD; Chicago, IL; Forsyth County, NC; Los Angeles, CA; New York, NY; and St. Paul, MN). A total of 3534 participants with complete data on all candidate variables were included in the analysis. Institutional review boards of all field centers approved the study protocol, and all participants gave written informed consent.

Information on assessment of risk factors within MESA has been described previously,¹⁵ and a detailed description is provided in the Online Methods. We included biomarkers and measurements from questionnaires, demographics, anthropometry, medication use, blood biochemistry, magnetic resonance imaging (MRI) of the heart and aorta, coronary computed tomography, carotid ultrasound, and electrocardiography (ECG).

Several risk prediction models for AF are compared in Online Table 1.^6–10 Candidate variables considered in this analysis included the individual components of the CHARGE-AF models:^8,9 age, race/ethnicity, height, weight, systolic and diastolic blood pressure (BP), current smoking, use of antihypertensive medication, diabetes, and NT-proBNP. Because MESA enrolled participants without a history of CVD, history oi heart failure and history of myocardial infarction were not evaluated, consistent with previous validation of CHARGE-AF in MESA.¹⁰ We additionally considered variables identified as highly predictive of incident AF in a previous machine learning analysis in MESA, which used the random survival forests method:¹⁴ coronary artery calcium (CAC) score, ankle-brachial index, common carotid intima media thickness, internal carotid intima media thickness, serum creatinine, cardiac troponin-T, R amplitude in lead V₄, STJ amplitude in lead V₅, heart rate, estimate of overall heart rate variability (standard deviation of all normal-to-normal R-R intervals), QRS axis, end-systolic basal lateral wall thickness, and end-systolic midventricular anterior wall thickness. Variables identified as predictive in the machine learning analysis but missing at baseline among >30% of participants (left atrial ejection fraction, interleukin-2, and tumor necrosis factor-α) were not evaluated.

The primary end-point for the prediction models was incident AF. MESA participants or a proxy were contacted by telephone every 9 to 12 months to identify all new hospitalizations. Medical records were obtained, and trained staff abstracted discharge diagnostic and procedure codes from these hospitalizations. Incident AF was defined as presence of International Classification of Diseases, Ninth Revision (ICD-9) diagnosis codes for AF (427.31) or atrial flutter (427.32). We additionally included Medicare inpatient, outpatient, and carrier claims for participants enrolled in fee-for-service Medicare.¹⁶ Participants newly found to have AF by 12-lead ECG at the 2010–2012 study visit were classified as having AF as of the visit date. AF that occurred during a hospitalization with open cardiac surgery was not counted as an event.

We used Cox proportional hazards models to construct prediction models of 5-year risk of incident AF, including baseline traditional and non-traditional candidate variables. Time of follow-up was defined as time from the baseline exam to the first occurrence of incident AF, death, or last available contact through December 2014. Maximum follow-up time was censored at 5 years. In a secondary analysis, we evaluated the prediction performance of the models using all available follow-up time (mean 11.4 years; maximum 14.5 years).

The enriched CHARGE-AF model, which was previously validated in MESA,¹⁰ was selected as the base model to which novel candidate variables were added. We used MESA variable coefficients rather than CHARGE-AF coefficients to facilitate unbiased model comparisons within this cohort. Linearity of continuous variables was assessed visually using plots of Martingale residuals, and deviations were addressed with appropriate transformations (e.g. natural log). The LASSO (“least absolute shrinkage and selection operator”) method was used to identify a parsimonious set of predictors.¹⁷ Interactions of candidate variables with age, sex, and race/ethnicity were also considered in the LASSO analysis.

We evaluated the performance of sequential models using measures of discrimination and calibration.¹⁸ Discrimination refers to the ability of a model to correctly identify those with and without the outcome and was assessed by estimating Harrell’s c-statistic¹⁹ and plotting survival receiver operating characteristic (ROC) curves.²⁰ Discrimination performance of sequential models was compared using the likelihood ratio test.²¹ Calibration refers to the agreement between observed outcomes and predictions provided by a given model and was assessed by calculating the Greenwood-Nam-D’Agostino (GND) statistic.²² Additionally, calibration plots were created to visualize the observed vs. predicted risk across categories of predicted risk, defined according to recommended guidelines.²² We additionally conducted a post-hoc analysis to evaluate performance of the parsimonious model in an expanded analytic sample including all MESA participants with complete data for the candidate predictors selected in this model (age, weight, current smoking, NT-proBNP, CAC, and troponin-T; n=5502).

Results

Of the 6814 total participants in MESA, we excluded those with pre-baseline AF (n=66) and those missing data for the outcome (n=29) and candidate predictors (MRI variables, n=1958; serum biomarkers, n=819; ECG variables, n=238; subclinical CVD variables, n=119; traditional risk factors, n=51). Thus, a total of 3534 participants (mean age, 61.3 years; 52.0% female) with complete data were included in the analyses and were, on average, healthier compared with the full MESA cohort (Online Table 2). During an average 11.4-year follow-up, 436 participants had an AF event (incidence rate, 10.8 per 1000 person-years), 124 of which occurred during the first 5 years of follow-up (7.3 per 1000 person-years). Table 1 shows the prevalence and mean values of baseline characteristics by incident AF status within 5 years. Those who had an AF event were more likely to be older and taking antihypertensive medication. Additionally, those who had an AF event had, on average, higher systolic BP, CAC, cIMT, serum creatinine, NT-proBNP, troponin-T, and cardiac MRI wall thickness; and lower ankle-brachial index, STJ amplitude in lead V5, and QRS axis. Similar results were observed when comparing those who had an AF event over all follow-up with those who did not, although additional differences were noted, including for sex, race/ethnicity, and diabetes status (Online Table 3).

Table 1.

Baseline Participant Characteristics in the Multi-Ethnic Study of Atherosclerosis by Incident Atrial Fibrillation within Five Years

	Atrial Fibrillation
Variables	No (n = 3410)	Yes (n = 124)	P Value
Age (years)	60.9 (10.0)	70.9 (7.3)	<0.001
Men	1646 (48%)	70 (56%)	0.09
Non-Hispanic white	1311 (38%)	59 (48%)
Chinese American Non-Hispanic black	524 (15%) 762 (22%)	14 (11%) 25 (20%)	0.21
Non-Hispanic black	762 (22%)	25 (20%)
Hispanic	813 (24%)	26 (21%)
Current smoker	416 (12%)	17 (14%)	0.72
Body mass index (kg/m2)	27.5 (4.9)	28.0 (4.8)	0.36
Systolic blood pressure (mm Hg)	124.8 (21.1)	133.3 (21.1)	<0.001
Diastolic blood pressure (mm Hg)	71.8 (10.2)	71.2 (10.4)	0.51
Pulse pressure (mm Hg)	53.0 (16.6)	62.1 (17.4)	<0.001
Antihypertensive medication use	1118 (33%)	64 (52%)	<0.001
Diabetes mellitus	380 (11%)	13 (10%)	0.93
Coronary artery calcium (Agatston units)
0	1812 (53%)	32 (26%)	<0.001
1–99	885 (26%)	39 (31%)
100–399	438 (13%)	25 (20%)
400+	275 (8%)	28 (23%)
Ankle-brachial index	1.12 (0.11)	1.09 (0.16)	0.002
Common carotid intima-media thickness (mm)	0.85 (0.18)	0.95 (0.21)	<0.001
Internal carotid intima-media thickness (mm)	1.02 (0.56)	1.27 (0.75)	<0.001
Serum creatinine (mg/dL)	0.96 (0.24)	1.04 (0.29)	<0.001
N-terminal pro-B-type natriuretic peptide (pg/mL)	50.1 [22.0, 97.6]	106.9 [51.3, 233.5]	<0.001
Detectable cardiac troponin-T	34 (1%)	5 (4%)	0.006
R amplitude in lead V4 (uV)	1429.8 (545.5)	1478.5 (660.3)	0.33
STJ amplitude in lead V5 (uV)	18.5 (35.3)	8.37 (42.56)	0.002
Heart rate (beats per minute)	62.7 (9.1)	62.3 (10.7)	0.64
Heart rate variability (ms)	22.6 (16.0)	20.2 (15.2)	0.10
QRS axis (degrees)	21.9 (31.4)	12.1 (31.2)	0.001
End-systolic basal superior lateral wall thickness (mm)	15.6 (3.0)	16.4 (3.4)	0.003
End-systolic mid-ventricular anterior wall thickness (mm)	15.9 (3.1)	17.3 (3.7)	<0.001

Values are mean (standard deviation), median [interquartile range]

Table 2 provides discrimination and calibration statistics for several models. Compared with the CHARGE-AF Simple model, the CHARGE-AF Enriched model, which additionally included NT-proBNP, showed statistically-significant discrimination improvement and was well-calibrated. Further addition of biomarkers, MRI measurements, ECG measurements, and subclinical CVD variables did not significantly improve discrimination or calibration, nor did the addition of all potential predictors. A parsimonious model derived using LASSO included only age, weight, current smoking, NT-proBNP, CAC, and troponin-T (the “Novel MESA” score), and performed similarly to the model with all predictors. No interactions with age, sex, nor race/ethnicity were retained in the model. Compared with the CHARGE-AF Simple model, ROC curves for the CHARGE-AF Enriched, All Predictors, and Novel MESA models show improved discrimination, but largely overlapped (Figure 1).

Table 2.

Discrimination and Calibration for Sequential Five-year Atrial Fibrillation Risk Prediction Models

Model		Discrimination		Calibration
		C-statistic (95% CI)	P Value	GND X2value	P Value
1	CHARGE-AF Simple*	0.795 (0.764–0.827)	-	6.2	0.28
2	CHARGE-AF Enriched†	0.804 (0.771–0.837)	<0.001	2.4	0.80
3	+ Biomarkers‡	0.804 (0.771–0.837)	0.71	2.4	0.79
4	+ MRI§	0.803 (0.770–0.837)	0.13	4.2	0.53
5	+ ECG∥	0.805 (0.773–0.837)	0.86	4.0	0.55
6	+ Subclinical CVD#	0.805 (0.772–0.837)	0.82	3.2	0.67
7	All Predictors**	0.806 (0.774–0.839)	0.81	4.3	0.51
8	Novel MESA††	0.802 (0.769–0.835)	0.93	3.9	0.57

Higher values for C-statistic indicate better models. Discrimination P values are for a likelihood ratio test comparing each model with Model 2, except for 1) Model 2, which is compared with Model 1; and 2) Model 8, which is compared with Model 7. Calibration P values >0.05 indicate adequate fit.

^*Model 1: age, white race, height, weight, systolic BP, diastolic BP, current smoking, antihypertensive medication use, diabetes

^†Model 2: Model 1 + ln(NT-proBNP)

^‡Model 3: Model 2 + serum creatinine, cardiac troponin-T

^§Model 4: Model 2 + end-systolic basal superior lateral wall thickness, end-systolic mid-ventricular anterior wall thickness

^∥Model 5: Model 2 + heart rate, heart rate variability, R amplitude in lead V4, STJ amplitude in lead V5, QRS axis

^#Model 6: Model 2 + ln(CAC + 1), ankle-brachial index, common cIMT, internal cIMT

^**Model 7: all candidate variables

^††Model 8: age, weight, current smoking, ln(NT-proBNP), ln(CAC+1), and cardiac troponin-T

Abbreviations: BP = blood pressure; CAC = coronary artery calcium; CI = confidence interval; cIMT = carotid intima-media thickness; CVD = cardiovascular disease; ECG = electrocardiography; GND = Greenwood-Nam-D’Agostino; LRT = likelihood ratio test; MRI = magnetic resonance imaging; NT-proBNP = N-terminal pro-B-type natriuretic peptide

Figure 1. Discrimination of Atrial Fibrillation 5-year Risk Scores in MESA.

ROC curves for 4 AF risk prediction models based on 23 candidate predictor variables included in previous risk prediction models of AF and a machine learning analysis in MESA. Higher values of the c-statistic indicate better performance.

MESA = Multi-Ethnic Study of Atherosclerosis; ROC = receiver operating characteristic

Observed and predicted risks were close across the range of the scores for the CHARGE-AF Simple, CHARGE-AF Enriched, All Predictors, and Novel MESA models (Figure 2) and none showed evidence of poor calibration based on the GND statistics. However, the CHARGE-AF Simple model did not perform as well in intermediate predicted probability groups compared with other groups, resulting in poorer calibration overall compared with the other models. The CHARGE-AF Enriched model showed the best calibration (GND X² statistic, 2.4 [p=0.80]).

Figure 2. Observed vs Predicted Probability of Atrial Fibrillation at 5 Years.

The predicted and observed event probability estimates represent the mean predicted probability from the Cox regression model and the mean observed probability from the population divided into categories of predicted probability. Panel A, Calibration of the CHARGE-AF Simple model; Panel B, Calibraron of the CHARGE-AF Enriched model; Panel C, Calibration of the All Predictors Model; Panel D, Calibration of the Novel MESA Model.

CHARGE = Cohorts for Heart and Aging Research in Genomic Epidemiology; MESA = Multi-Ethnic Study of Atherosclerosis

Table 3 provides estimated hazard ratios for the variables included in the CHARGE-AF Enriched, All Predictors, and Novel MESA models. Additionally, the baseline survival function and beta coefficients are provided that allow calculation of the predicted risk of AF within 5 years. Across all 3 models, baseline age, weight, current smoking, and NT-proBNP were significantly associated with AF risk. After employing LASSO, these variables were retained in the Novel MESA model along with CAC and troponin-T. While mid-ventricular anterior wall thickness was also a statistically-significant predictor in the All Predictors model, it was not retained in the Novel MESA model after LASSO selection.

When expanding AF risk prediction through all available follow-up (mean, 11.4 years; maximum, 14.5 years; 436 AF events), discrimination and calibration were reduced compared with 5-year risk prediction (Online Table 4). Similar to the 5-year risk analyses, most novel variables did not add significantly to prediction performance. However, the addition of subclinical CVD markers, including CAC, ankle-brachial index, common cIMT, and internal cIMT, significantly improved discrimination compared with CHARGE-AF Enriched. In particular, the addition of CAC alone achieved equivalent discrimination to the model including the other subclinical CVD markers (c-statistic, 0.784; 95% CI 0.765–0.803). Online Table 5 provides estimated hazard ratios and risk score calculation information for the variables included in the models for the expanded follow-up period.

We conducted a post-hoc analysis among the 5502 participants with complete data for the predictors included in the Novel MESA model. A total of 746 incident AF events were identified over a mean follow-up of 11.3 years, 224 of which occurred within the first 5 years (Online Table 6). Results were mostly similar compared with those in the derivation sample of 3534 participants, although the association of current smoking with AF risk was weaker.

Discussion

In this analysis of 3534 participants from a multi-ethnic cohort, we found that the addition of novel blood biomarkers, MRI measurements, ECG measurements, and subclinical CVD variables identified by machine learning to the base CHARGE-AF Enriched model did not significantly increase 5-year AF risk prediction ability. A parsimonious model including only age, weight, current smoking, NT-proBNP, CAC, and troponin-T performed as well as the 23-item risk score including all candidate predictor variables. These findings provide important guidance on the utility of novel measurements in risk prediction and implicate several important variables in predicting the risk of AF. This study also provides useful insights into the value of machine learning techniques for risk prediction in the clinical setting.

The CHARGE-AF consortium developed a simple score for predicting 5-year risk of AF by pooling individual-level data from 18556 participants from 3 US cohorts and validated the score in 7672 participants from 2 European cohorts.⁸ The simple model, which includes several traditional CVD risk factors, discriminated AF events well in the current analysis, but was not as well calibrated compared with the other models. A follow-up analysis in CHARGE-AF reflected the importance of including NT-proBNP in the model, forming the CHARGE-AF Enriched model,⁹ which was previously validated in MESA.¹⁰ We corroborated evidence that the biomarker-enriched model performed better than the simple model in terms of both discrimination aid calibration in the diverse MESA sample. Because the CHARGE-AF Enriched model was developed in a large, pooled cohort and has been validated in several other populations, it remains valuable in predicting the risk of AF in various settings, such as the clinic or for study recruitment. Additionally, it is an appropriate standard to which novel measurements can be compared for improvement in prediction ability, such as in the current analysis.

In 2017, an analysis in MESA used the random survival forests machine learning method to identify the 20 most predictive variables for several cardiovascular diseases, including AF.¹⁴ Ambale-Venkatesh et al. ranked the relative importance of >700 variables in predicting the risk of AF. Most of the top-20 variables identified are not included in risk prediction models of AF.^6–10 Thus, our goal was to directly compare these findings to established risk scores to evaluate potential improvements in risk prediction. Ambale-Venkatesh et al. compared their results with traditional scores for the prediction of coronary heart disease and heart failure, and found performance improvements defined by higher c-statistics and lower Brier scores. However, their findings were not directly compared with previously-validated risk scores for AF. Our findings indicate that the novel variables identified by machine learning within the MESA cohort did not improve prediction performance beyond the CHARGE-AF Enriched model. Importantly, the machine learning methods successfully identified several key predictors that were retained in our novel LASSO-selected model, including. NT-proBNP, CAC, and troponin-T. Future work should continue to evaluate new predictors as data become available.

Our findings offer several implications, both for the burgeoning field of machine learning within the context of clinical CVD research and for AF risk prediction. As noted by Ambale-Venkatesh et al, machine learning techniques may offer a robust variable selection method when facing a large number of potential predictors.¹⁴ However, it is important to evaluate findings from such data-driven techniques against previously-developed and validated risk scores already employed by clinicians, especially when potentially recommending measurements not routinely collected in a clinical setting. Findings from both our analyses complement previous work demonstrating that NT-proBNP is strongly and independently associated with higher risk of AF.^23–26 Additionally, subclinical CVD markers, particularly CAC, afforded prediction performance improvements beyond CHARGE-AF Enriched when expanding the analysis to all available follow-up time. While CAC is primarily considered a subclinical marker of atherosclerosis,²⁷ it has been associated with AF in previous studies.^28–30 It is possible that CAC may represent an accumulation of CVD risk factor burden or cardiac structural changes and vascular injury that may directly explain its role in higher risk of AF. In populations free of clinical CVD at baseline, such as MESA participants, CAC may be particularly valuable for AF risk prediction in lieu of history of myocardial infarction and history of heart failure, which are included in the CHARGE-AF scores.

Several potential limitations must be considered. First, a large amount of data was missing for many of the novel risk factor groups, particularly cardiac MRI measurements. Thus, our complete case analysis may decrease generalizability, since inclusion in the analysis required participants to be able and willing to have biomarker, MRI, ECG, and computed tomography measurements. However, the sample included in this analysis still represents a population of clinical and public health relevance. Furthermore, evaluation of the parsimonious model in an expanded sample of participant revealed similar prediction performance. Second, ascertainment of AF relied on hospitalization and CMS claims data. Thus, undiagnosed AF or AF in those not seeking treatment is not identified, but these same limitations apply to all previous AF prediction studies. Additionally, a diagnosis of AF may arise because of various biologic mechanisms. Further research is warranted to investigate prediction of specific subtypes of AF, which was not possible in the current analysis. Third, relatively few AF events occurred within 5 years (N=124), which may limit statistical power to identify significant improvements in prediction performance. However, results and conclusions were similar when expanding the prediction horizon to all available follow-up (mean, 11.4 years; 436 AF events). Finally, we chose to focus our analysis on 5-year risk of AF, which is a short-term prediction. However, short-term risk prediction may be particularly attractive for screening and primary prevention purposes.

In conclusion, compared with the CHARGE-AF score, novel candidate variables identified by machine learning did not add significantly to AF risk prediction. We also found that a parsimonious score containing only age, weight, current smoking, NT-proBNP, CAC, and troponin-T performed as well as the 23-item score including risk factors identified by machine learning. These findings confirm the utility of existing risk scores for AF prediction.

Table 3.

Hazard Ratios and Predicted Risk Calculation for CHARGE-AF Enriched, All Predictors, and Novel MESA Five-year Atrial Fibrillation Risk Prediction Models

	CHARGE-AF Enriched		All Predictors		Novel MESA
Variables	HR (95% CI)	Beta*	HR (95% CI)	Beta*	HR (95% CI)	Beta*
Age (per 5 years)	1.64	0.0984	1.56	0.0886	1.58
	(1.45–1.85)		(1.36–1.79)		(1.40–1.80)	0.0917
Non-Hispanic white	1.09	0.0875	1.18	0.1665
	(0.75–1.59)		(0.79–1.77)
Non-Hispanic white	1.03	0.0032	1.02	0.0023
	(0.82–1.30)		(0.79–1.32)
Weight (per 15 kg)	1.37	0.0208	1.32	0.0186	1.37
	(1.11–1.69)		(1.05–1.66)		(1.15–1.63)	0.0208
Systolic BP (per 20 mm Hg)	0.93	-	0.93	-
	(0.74–1.18)	0.0034	(0.72–1.20)	0.0038
Diastolic BP (per 10 mm Hg)	1.03	0.0030	1.00	-
	(0.80–1.32)		(0.76–1.31)	0.0004
Current smoker	2.05	0.7184	2.06	0.7231	1.97
	(1.21–3.48)		(1.19–3.58)		(1.17–3.32)	0.6774
Antihypertensive medication use	1.23	0.2036	1.21	0.1932
	(0.84–1.78)		(0.83–1.77)
Diabetes mellitus	0.76	-	0.68	-
	(0.42–1.38)	0.2752	(0.37–1.26)	0.3850
Ln(NT-proBNP) (per 1 SD)	1.54	0.4343	1.55	0.4355	1.51
	(1.27–1.88)		(1.26–1.90)		(1.26–1.82)	0.4148
Serum creatinine (per 0.1 mg/dL)			0.99	-
			(0.93–1.06)	0.0545
Detectable cardiac troponin-T			1.75		0.5596	1.38
			(0.61–4.99)		(0.54–3.52)	0.3221
Basal superior lateral wall thickness (per 5 mm)†			0.87	0.0290
			(0.59–1.26)	0.0290
Mid-ventricular anterior wall thickness (per 5 mm)†			1.42	0.0696
			(1.02–1.97)
Heart rate (per 5 beats per minute)			1.04	0.0074
			(0.94–1.15)
Heart rate variability (per 10 ms)			0.95	-
			(0.85–1.07)	0.0051
R amplitude in lead V4 (per 100 uV)			1.01	0.0001
STJ amplitude in lead V5 (per 10 uV)			1.02	0.0019
			(0.97–1.07)	0.0019
QRS Axis (per 10 degrees)			0.99	-
			(0.93–1.05)	0.0010
Ln(CAC + 1) (per 1 SD)			1.04	0.0432	1.05
			(0.96–1.13)		(0.97–1.13)	0.0448
Ankle-brachial index (per 0.05)			0.99	-
			(0.93–1.06)	0.1251
Common cIMT (per 0.5 mm)			1.07	0.1424
			(0.65–1.77)
Internal cIMT (per 0.5 mm)			0.96
			(0.83–1.11)	0.0810

The 5-year risk for the CHARGE-AF Enriched model can be calculated as 1–0.9819^{exp(ΣbX–9.7729)} where b is the regression coefficient (beta) and X is the level for each risk factor; the risk for the All Predictors model can be calculated as 1–0.9823^{exp(ΣbX–9.6722)}; the risk for the Novel MESA model can be calculated as 1–0.9815^{exp(ΣbX–8.9785)}.

^*Per 1-unit increase

^†Measured during end-s stole

Abbreviations: BP = blood pressure; CAC = coronary artery calcium; CI = confidence interval; cIMT = carotid inĝ. media thickness; NT-proBNP = N-terminal pro-B-type natriuretic peptide