Precision Health Analytics With Predictive Analytics and Implementation Research: JACC State-of-the-Art Review.

Emerging data science techniques of predictive analytics expand the quality and quantity of complex data relevant to human health and provide opportunities for understanding and control of conditions such as heart, lung, blood, and sleep disorders. To realize these opportunities, the information sources, the data science tools that use the information, and the application of resulting analytics to health and health care issues will require implementation research methods to define benefits, harms, reach, and sustainability; and to understand related resource utilization implications to inform policymakers. This JACC State-of-the-Art Review is based on a workshop convened by the National Heart, Lung, and Blood Institute to explore predictive analytics in the context of implementation science. It highlights precision medicine and precision public health as complementary and compelling applications of predictive analytics, and addresses future research and training endeavors that might further foster the application of predictive analytics in clinical medicine and public health.

Relation of Carotid Intima-Media Thickness to Cardiovascular Events in Black Americans (From the Jackson Heart Study).

Although several prospective studies have reported independent relations between carotid intima-media thickness (CIMT) and risk of incident cardiovascular diseases (CVD) in primarily non-African-American (AA) cohorts, the utility of CIMT values for the prediction of incident coronary heart disease and stroke events in blacks remain unclear. At the baseline examination (2000 to 2004) of the Jackson Heart Study, AA adults 21 to 94 years of age (mean 54) underwent bilateral far-wall CIMT measurement (mean 0.76 mm). Incident CVD events were then assessed over 7 to 11 years of follow-up (2000 to 2011) from samples of 2,463 women (107 CVD events) and 1,338 men (64 CVD events) who were free of clinical CVD at baseline. Each 0.2-mm increase in CIMT was associated with age-adjusted incident CVD hazard ratios of 1.4 (95% confidence interval 1.2, 1.5) for women and 1.3 (1.1, 1.6) for men. Classification accuracy improved only slightly when comparing multivariable models that used traditional risk factors alone with models that added CIMT: C-statistics 0.837 (0.794, 0.881) versus 0.842 (0.798, 0.886) in women and 0.754 (0.683, 0.826) versus 0.763 (0.701, 0.825) in men. Similarly, risk reclassification was only mildly improved by adding CIMT: Net Reclassification Index 0.13 (p = 0.05) and 0.05 (p = 0.50) for women and men, respectively; Integrated Discrimination Improvement 0.02 (p = 0.02) and 0.01 (p = 0.26) for women and men, respectively. In conclusion, CIMT was associated with incident CVD but provided modest incremental improvement in risk reclassification beyond traditional risk factors in a community-based AA cohort.

Decline in Cardiovascular Mortality: Possible Causes and Implications.

If the control of infectious diseases was the public health success story of the first half of the 20th century, then the decline in mortality from coronary heart disease and stroke has been the success story of the century's past 4 decades. The early phase of this decline in coronary heart disease and stroke was unexpected and controversial when first reported in the mid-1970s, having followed 60 years of gradual increase as the US population aged. However, in 1978, the participants in a conference convened by the National Heart, Lung, and Blood Institute concluded that a significant recent downtick in coronary heart disease and stroke mortality rates had definitely occurred, at least in the US Since 1978, a sharp decline in mortality rates from coronary heart disease and stroke has become unmistakable throughout the industrialized world, with age-adjusted mortality rates having declined to about one third of their 1960s baseline by 2000. Models have shown that this remarkable decline has been fueled by rapid progress in both prevention and treatment, including precipitous declines in cigarette smoking, improvements in hypertension treatment and control, widespread use of statins to lower circulating cholesterol levels, and the development and timely use of thrombolysis and stents in acute coronary syndrome to limit or prevent infarction. However, despite the huge growth in knowledge and advances in prevention and treatment, there remain many questions about this decline. In fact, there is evidence that the rate of decline may have abated and may even be showing early signs of reversal in some population groups. The National Heart, Lung, and Blood Institute, through a request for information, is soliciting input that could inform a follow-up conference on or near the 40th anniversary of the original landmark conference to further explore these trends in cardiovascular mortality in the context of what has come before and what may lie ahead.

Differences in Hemoglobin A1c Between Hispanics/Latinos and Non-Hispanic Whites: An Analysis of the Hispanic Community Health Study/Study of Latinos and the 2007-2012 National Health and Nutrition Examination Survey.

OBJECTIVE: To determine whether, after adjustment for glycemia and other selected covariates, hemoglobin A1c (HbA1c) differed among adults from six Hispanic/Latino heritage groups (Central American, Cuban, Dominican, Mexican, Puerto Rican, and South American) and between Hispanic/Latino and non-Hispanic white adults without self-reported diabetes. RESEARCH DESIGN AND METHODS: We performed a cross-sectional analysis of data from 13,083 individuals without self-reported diabetes from six Hispanic/Latino heritage groups, enrolled from 2008 to 2011 in the Hispanic Community Health Study/Study of Latinos, and 2,242 non-Hispanic white adults enrolled during the 2007-2012 cycles of the National Health and Nutrition Examination Survey. We compared HbA1c levels among Hispanics/Latinos and between Hispanics/Latinos and non-Hispanic whites before and after adjustment for age, sex, fasting (FPG) and 2-h post-oral glucose tolerance test (2hPG) glucose, anthropometric measurements, and selected biochemical and hematologic variables and after stratification by diabetes status: unrecognized diabetes (FPG ≥7.1 mmol/L or 2hPG ≥11.2 mmol/L), prediabetes (FPG 5.6-7.0 mmol/L or 2hPG 7.8-11.1 mmol/L), and normal glucose tolerance (FPG <5.6 mmol/L and 2hPG <7.8 mmol/L). RESULTS: Adjusted mean HbA1c differed significantly across all seven groups (P < 0.001). Non-Hispanic whites had significantly lower HbA1c (P < 0.05) than each individual Hispanic/Latino heritage group. Upon stratification by diabetes status, statistically significant differences (P < 0.001) in adjusted mean HbA1c persisted across all seven groups. CONCLUSIONS: HbA1c differs among Hispanics/Latinos of diverse heritage groups and between non-Hispanic whites and Hispanics/Latinos after adjustment for glycemia and other covariates. The clinical significance of these differences is unknown.

Trends in overweight and obesity among 18-year-old applicants to the United States military, 1993-2006.

We examined trends in overweight and obesity among 756,269 18-year-old civilian applicants to the United States military from 1993-2006. The prevalence of overweight increased from 22.8% in 1993 to 27.1% in 2006, and obesity increased from 2.8% to 6.8%. We conclude the U.S. military is recruiting from an increasingly overweight population.