Accurate heart attack diagnostics using a machine learning algorithm
The study comes to us from the United Kingdom, a group of researchers have resorted to artificial intelligence (AI) to develop a machine learning algorithm that allows doctors to diagnose heart attacks quickly and accurately, managing to reduce the time needed to make a diagnosis, providing patients with more efficient and effective treatments.
The algorithm was named the Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome (CoDE-ACS) and is based on the analysis of data collected from 10,286 patients from six different countries who had possible heart attacks in their medical history.
Traditional methods focus on measuring troponin protein levels in the blood, unlike CoDE-ACS which uses a broader and more integrative approach, in addition to troponin levels, incorporating key variables such as gender, age, electrocardiogram (ECG) findings and patient medical history, to estimate the likelihood of a heart attack having occurred in an individual patient.
The results are quite satisfactory CoDE-ACS can rule out a heart attack in more than twice as many patients, with an accuracy of 99.6%, effectively identifying those patients who have not suffered a heart attack, prevented unnecessary hospital admissions and optimized emergency care.
Moreover, the algorithm demonstrated accurate predictive ability in different subgroups of patients, including men and women, the elderly, and those with renal problems or who arrived early at the hospital after the onset of symptoms.
The researchers have demonstrated the potential for CoDE-ACS to transform emergency medical care by being an effective and efficient tool for early diagnosis of heart attacks. By ruling out cases of heart attack in patients who have not suffered a heart attack, it would avoid unnecessary admissions and allow physicians to make informed decisions about appropriate treatment, improving patients' quality of life.
It only remains to wait for its mass commercialization, as it could be a tool of great value for medicine and cardiac patients.
To read more, please visit:
