Michael Barbella, Managing Editor07.17.23
An algorithm developed using artificial intelligence (AI) could soon be used by doctors to diagnose heart attacks with improved speed and accuracy, according to new research from the University of Edinburgh, funded by the British Heart Foundation charity and the U.K.’s National Institute for Health and Care Research, and published in Nature Medicine.1
The effectiveness of the algorithm, named CoDE-ACS,2 was tested on 10,286 patients in six countries globally. The data showed that, compared to current testing methods, CoDE-ACS ruled out a heart attack in more than double the number of patients, with a 99.6% accuracy rate.
This ability to quickly rule out a heart attack could help significantly reduce hospital admissions. Clinical trials are now underway in Scotland with support from the Wellcome Leap, to assess whether the tool can help doctors reduce pressure on overcrowded emergency departments.
“For patients with acute chest pain due to a heart attack, early diagnosis and treatment saves lives. Unfortunately, many conditions cause these common symptoms, and the diagnosis is not always straight forward,"said Nicholas Mills, BHF Professor of Cardiology at the Centre for Cardiovascular Science, University of Edinburgh, who led the research. "Harnessing data and artificial intelligence to support clinical decisions has enormous potential to improve care for patients and efficiency in our busy emergency departments.”
Reducing Health Inequalities
Besides quickly ruling out heart attacks, CoDE-ACS could also help doctors to identify patients whose abnormal troponin levels were due to a heart attack rather than another condition. The AI tool performed well regardless of age, sex, or pre-existing health conditions, showing its potential for reducing misdiagnosis and inequalities across the population.
CoDE-ACS could potentially to make emergency care more efficient and effective by rapidly identifying patients who can be discharged, and by highlighting those who need further tests.
The current gold standard for diagnosing a heart attack is measuring levels of the protein troponin in the blood. But the same threshold is used for every patient, thus factors such as age, sex and other health problems that affect troponin levels are not considered, affecting the accuracy of diagnoses. Consequently, this can lead to inequalities in diagnosis. Previous research has shown that women are 50% more likely to receive a wrong diagnosis initally. People who are initially misdiagnosed have a 70% higher risk of dying. The new algorithm can potentially prevent these deaths.
CoDE-ACS was developed using data from 10,038 patients in Scotland who had arrived at hospital with a suspected heart attack. It uses routinely collected patient information, such as age, sex, ECG findings and medical history, as well as troponin levels, to predict the probability that an individual has had a heart attack. The result is a probability score from 0 to 100 for each patient.
The intellectual property underpinning the CoDE-ACS algorithm has been developed and protected with support from the university’s commercialization service, Edinburgh Innovations. Routes into clinical settings are currently being explored and developed.
“We are proud to be supporting Nick and his team as they take their research and invention out of the university and into clinical settings where it can really make a difference to healthcare outcomes,” stated Dr. John Lonsdale, head of Enterprise at Edinburgh Innovations.
References
1 Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations. Nature Medicine 2023. DOI: 10.1038/s41591-023-02325-4. URL: https://www.nature.com/articles/s41591-023-02325-4
2 CoDE-ACS stands for Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome. https://decision-support.shinyapps.io/code-acs/
The effectiveness of the algorithm, named CoDE-ACS,2 was tested on 10,286 patients in six countries globally. The data showed that, compared to current testing methods, CoDE-ACS ruled out a heart attack in more than double the number of patients, with a 99.6% accuracy rate.
This ability to quickly rule out a heart attack could help significantly reduce hospital admissions. Clinical trials are now underway in Scotland with support from the Wellcome Leap, to assess whether the tool can help doctors reduce pressure on overcrowded emergency departments.
“For patients with acute chest pain due to a heart attack, early diagnosis and treatment saves lives. Unfortunately, many conditions cause these common symptoms, and the diagnosis is not always straight forward,"said Nicholas Mills, BHF Professor of Cardiology at the Centre for Cardiovascular Science, University of Edinburgh, who led the research. "Harnessing data and artificial intelligence to support clinical decisions has enormous potential to improve care for patients and efficiency in our busy emergency departments.”
Reducing Health Inequalities
Besides quickly ruling out heart attacks, CoDE-ACS could also help doctors to identify patients whose abnormal troponin levels were due to a heart attack rather than another condition. The AI tool performed well regardless of age, sex, or pre-existing health conditions, showing its potential for reducing misdiagnosis and inequalities across the population.
CoDE-ACS could potentially to make emergency care more efficient and effective by rapidly identifying patients who can be discharged, and by highlighting those who need further tests.
The current gold standard for diagnosing a heart attack is measuring levels of the protein troponin in the blood. But the same threshold is used for every patient, thus factors such as age, sex and other health problems that affect troponin levels are not considered, affecting the accuracy of diagnoses. Consequently, this can lead to inequalities in diagnosis. Previous research has shown that women are 50% more likely to receive a wrong diagnosis initally. People who are initially misdiagnosed have a 70% higher risk of dying. The new algorithm can potentially prevent these deaths.
CoDE-ACS was developed using data from 10,038 patients in Scotland who had arrived at hospital with a suspected heart attack. It uses routinely collected patient information, such as age, sex, ECG findings and medical history, as well as troponin levels, to predict the probability that an individual has had a heart attack. The result is a probability score from 0 to 100 for each patient.
The intellectual property underpinning the CoDE-ACS algorithm has been developed and protected with support from the university’s commercialization service, Edinburgh Innovations. Routes into clinical settings are currently being explored and developed.
“We are proud to be supporting Nick and his team as they take their research and invention out of the university and into clinical settings where it can really make a difference to healthcare outcomes,” stated Dr. John Lonsdale, head of Enterprise at Edinburgh Innovations.
References
1 Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations. Nature Medicine 2023. DOI: 10.1038/s41591-023-02325-4. URL: https://www.nature.com/articles/s41591-023-02325-4
2 CoDE-ACS stands for Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome. https://decision-support.shinyapps.io/code-acs/