In the United States, about 610,000 people die of heart disease every year, accounting for one in every four deaths.[i] Heart disease is the leading cause of death for both men and women.[ii] Dr. Amir Lerman, director of the Cardiovascular Research Center at Mayo has focused his research on coronary physiology. He conducted a two-year study ending in February 2017 to see if voice analysis was capable of detecting coronary-artery disease. Dr. Lerman said, “Every person’s voice has different frequencies that can be analysed.”[iii]
Mayo has been collaborating with Beyond Verbal, a Tel Aviv, Israel, and Newton, MA based company which is developing voice-enabled AI to create voice biomarkers. Biomarkers are normally thought of as biological molecules found in tissues, blood, or other body fluids which indicate a normal or abnormal bodily process or the presence of a specific condition or disease. Researchers at Beyond Verbal have discovered the human voice can also be a biomarker, specifically for coronary artery disease. The company believes the voice biomarkers can be used for personalized healthcare screening and continuous remote monitoring of heart health.[iv] In collaboration with Mayo, Beyond Verbal, used machine learning to identify specific voice biomarkers, and then tested groups of people who were scheduled to get angiograms.
Participants in the study recorded their voices using a smartphone app provided by Beyond Verbal. An analysis of the voices showed patients who had evidence of coronary-artery disease based on their angiograms also displayed voice biomarkers which could show presence of the disease.[v] The implication of the study is heart disease can be detected without intrusive and expensive tests. The combination of a patient’s voice plus AI will be able to do the job.
[i] “Heart Disease Facts,” Centers for Disease Control and Prevention (2019), https://www.cdc.gov/heartdisease/facts.htm
[ii] Ibid.
[iii] “Amir Lerman, M.D.,” Mayo Clinic (2019), https://www.mayo.edu/research/faculty/lerman-amir-m-d/bio-00078051
[iv] “Beyond Verbal,” Beyond Verbal (2019), https://beyondverbal.com/
[v] McCormick, “What Ai Can Tell from Listening to You”.