UIC researcher using AI to help communities improve cardiac arrest survival rates
1
Advances in resuscitation science have improved survival rates for out-of-hospital cardiac arrest (OHCA) in some communities, but wide variability in incidences and survival outcomes persists.
In an effort to increase survival rates, MIE Department Head and Professor Houshang Darabi is collaborating with Marina Del Rios at the University of Chicago to investigate the development of an artificial intelligence (AI) application for population-level risk prediction and management of OHCA.
Darabi is the AI lead on a multidisciplinary team that includes physicians, public health experts, and emergency management leaders across four states for a project supported by an NIH R01 grant, with approximately $1 million in direct funding to UIC for the project titled “Community OHCA Risk Prediction Using Machine Learning: A Multi-Domain Approach to Prevention and Preparedness.”
Out-of-hospital cardiac arrest continues to be a major cause of death in the United States, and contributing factors include multiple health conditions, location, access to healthcare, poverty, community resources, and variation in clinical care policies.
“Given the substantial public health burden of OHCA and marked geographic variability in incidence and survival, developing a targeted framework to identify and measure OHCA incident and outcome risks is essential,” Darabi said.
The researchers plan to employ a participatory, mixed-methods approach that integrates machine learning and artificial intelligence with qualitative research methods to develop and evaluate a risk score and a virtual laboratory environment as decision-support tools to inform community-level interventions to improve outcomes for out-of-hospital cardiac arrest.
The researchers will engage community representatives and officials involved in the OHCA system of care – community service organizations, emergency medical service providers, hospital quality assurance officers, public health officials, and cardiac arrest survivors – to participate in focus groups and key informant interviews to identify optimal and efficient data elements to define a scalable and usable risk score.
“We will use this information to employ machine learning methods to develop a risk score and virtual laboratory environment, which community representatives will evaluate,” Darabi said. “These elements will provide important context for data interpretation while building trust in the risk score and virtual laboratory as pre-implementation tools to diagnose local delivery capabilities and develop strategies to overcome any barriers.”
The risk score and virtual laboratory could help public health departments, hospitals, and government agencies identify neighborhoods that need additional resources, strengthen emergency response systems, and improve public education about cardiac arrest. The tools could also help officials decide where to provide funding to improve survival rates.
The researchers say the project is an important step toward helping communities better prepare for cardiac emergencies and giving more people a chance to survive out-of-hospital cardiac arrest.