A clinical study by Abbott has shown that its artificial intelligence (AI) technology can accurately identify patients having a heart attack in emergency rooms.
The machine learning algorithm leverages a combination of high sensitive troponin testing, as well as additional patient details, including age and sex, for diagnosing a heart attack.
During the clinical study, researchers assessed the technology for its ability to quickly and accurately determine if a heart attack is occurring or not.
Results have shown the AI solution offers a better probability analysis, specifically in patients admitted to the hospital within the first three hours of the beginning of their symptoms.
The technology should facilitate a personalised risk assessment option for doctors.
Abbott Diagnostics global medical and scientific affairs senior medical director said: “As doctors are bombarded with data and information, this new algorithm takes several of these variables and uses computational power to more accurately provide a probability of that person having a heart attack.
“In the future, you could imagine using this technology to develop algorithms that help doctors not only better determine if their patient is having a heart attack or not but potentially before a heart attack occurs.”
Existing clinical assessment approaches for heart attack do not consider personal factors of a patient.
The company designed its new algorithm to look for variables that are most predictive of a cardiac event, such as age, sex, troponin levels and blood sample timing.
Abbott said that the combination of this information with computational analysis could enable more informed decisions, faster treatments or safe discharge from hospital.
The algorithm leverages the company’s High Sensitive Troponin-I blood test for predicting heart disease risks in individuals without any symptoms.