The AI model was compared to three different “gold standards” for assessing cardiac patients: experienced physician interpretation, commercially available ECG algorithms, and HEART scores for major cardiac events. Overall, when combined with the “clinical judgment of trained paramedics,” the authors found that the algorithm outperformed all three of his options, lowering his one in three chest pain patients. We found that it can be accurately reclassified as either risk, intermediate risk, or high risk.
“Our wildest dreams were to match the accuracy of HEART, and we were surprised that a machine learning model based solely on ECG exceeded this score,” said Al-Zaiti. said in the same statement.
“This information can help guide emergency medical services (EMS) medical decisions, such as initiating specific treatments on site or alerting hospitals that high-risk patients are arriving. added co-author Christian Martin Gill, M.D., MPH, Chief of Staff. EMS Department of the University of Pittsburgh. “Conversely, it may also be attractive to help identify low-risk patients who do not need to go to hospitals with specialized cardiac facilities, which may improve prehospital triage.”
The researchers will also study the AI model in more detail, optimize its deployment, and work on integrating it into hospital command centers. The ultimate goal is to evaluate his ECG data collected from an EMS specialist and provide real-time assessments to aid in treatment decisions such as early activation of the cath lab.
Other co-authors include Dr. Ervin Sejdic from the University of Toronto’s Department of Electrical and Computer Engineering. Dr. Stephen Smith of Hennepin Healthcare. There are many others.
Read the full research here.
