Big Data Analytics, Social Determinants Reveal Heart Health Risks

November 09, 2020 - To learn more about how socioeconomic factors impact heart health, researchers are increasingly leveraging big data analytics technologies and examining social determinants data at the individual and population level.

Researchers from the University of Illinois at Chicago recently developed a machine learning algorithm to accurately predict out-of-hospital cardiac arrest survival rates. The model uses neighborhood and local data in combination with existing information sources.

According to the American Heart Association, there are almost 424,000 EMS-assessed out-of-hospital cardiac arrests every year in the US, and most of them are fatal.

Researchers developed and tested the machine learning algorithms on nearly 10,000 cases of out-of-hospital cardiac arrests that occurred in Chicago’s 77 neighborhoods between 2014 and 2019.

The team used out-of-hospital cardiac arrest information from the existing Cardiac Arrest Registry to Enhance Survival (CARES) database to identify incidents that happened outside a health system or a nursing home facility around the Chicago area. Researchers then added social determinants information from the Chicago Health Atlas (CHA) about individual communities, including crime rates, access to healthcare, and education.

READ MORE: 4 Emerging Strategies to Advance Big Data Analytics in Healthcare

Researchers combined the CARES and CHA data to train a machine learning model to predict out-of-hospital cardiac arrest survival. After adding the social determinants information from the CHA, the team found that the average recall of out-of-hospital cardiac arrests survival predictions increased from 84.5 percent to nearly 87 percent.

The researchers noted that the study was limited because more information needs to be examined and could impact results, such as weather, traffic, EMS routes, and socioeconomic status. However, the team stated that the results demonstrate the potential for social determinants data and analytics algorithms to accurately predict patient outcomes.

“This is exciting,” said Samuel Harford, MS, a PhD candidate in the department of mechanical and industrial engineering at the University of Illinois at Chicago and lead author of the study.

“We were able to provide a machine learning model with information from publicly available, real-world sources that helped us find patterns that might be otherwise unseen, therefore, yielding better results. This strategy has the potential to be helpful in more accurately predicting other clinical outcomes in future studies.”

At Penn Medicine, researchers also analyzed social determinants data to better understand heart health. A team recently discovered that increasing rates of food insecurity in counties across the US are independently associated with an increase in cardiovascular death rates among adults aged 20 to 64.

READ MORE: How Big Data Analytics Can Mitigate COVID-19 Health Disparities

Researchers analyzed data from the National Center for Health Statistics and the Map the Meal Gap study to examine county-level cardiovascular death rates and food insecurity rates from 2011 to 2017.

The team found that although overall food insecurity rates for the entire country declined between 2011 and 2017, the counties that had the most increase in food insecurity levels had cardiovascular death rates that increased from 82 to 87 per 100,000 individuals.

Additionally, for every one percent increase in food insecurity, there was a similar increase in cardiovascular mortality among non-elderly adults, at 0.83 percent.

“This research gives us a better understanding of the connection between economic distress and cardiovascular disease,” said Sameed Khatana, MD, MPH, senior author of the study and instructor of Cardiovascular Medicine in the Perelman School of Medicine at the University of Pennsylvania.

“What’s going on outside the clinic has significant impact on patients’ health. There are many factors beyond the medications we may be prescribing that can influence their wellbeing, food insecurity being one of them.”

READ MORE: Addressing the Social Determinants of Health with AI, Partnerships

The study’s results offer evidence of the link between food insecurity and increased risk of cardiovascular death. Researchers also noted that this is one of the first national analyses to evaluate changes in both food security and cardiovascular mortality over time, and to see if changes in food security affect cardiovascular health.

“There has been a growing disparity when it comes to food insecurity, and this data demonstrates that parts of the country are being left behind. Unfortunately, this may only get worse as the country grapples with the ramifications of the COVID-19 pandemic,” Khatana said.

“However, interventions that improve a community’s economic wellbeing could potentially lead to improved community cardiovascular health.”

In Pennsylvania, leaders have implemented one such intervention to mitigate the impact of the pandemic. A team from Carnegie Mellon University’s Metro21: Smart City Institute is using machine learning algorithms to create cost-effective bus routes to deliver meals to individuals in need.

“We originally talked to Allies for Children about a plan that would use machine learning to develop cost-effective bus routes transporting charter and private school students across school districts,” said Karen Lightman, Metro21’s executive director.

“When COVID closed schools in March and disrupted meal programs around the region, we pivoted. Instead of buses carrying students, we developed a program to have drivers bring lunches to families most in need.”