Voice Feature Analysis May Predict Incipient Heart Disease
By Daniel Beris Posted on 30 Nov 2016 |
Image: Human voice features could help identify heart disease (Photo courtesy of Beyond Verbal).
A new study suggests a strong correlation between some voice characteristics and the presence of coronary artery disease (CAD).
Researchers at Beyond Verbal (Tel Aviv, Israel) and the Mayo Clinic (Rochester, MN, USA), conducted a double-blind study involving 150 patients, including 120 patients who presented for coronary angiography, 21 apparently healthy control volunteers, and 9 control subjects who were referred to non-cardiac procedures. All subjects had their voice signal recorded prior to coronary angiography using the Beyond Verbal app, downloaded to their personal smartphone device.
Voice was then analyzed for multiple pre-specified features of intensity and frequency by different analytic tools. A total of three 30-second separate baseline voice recordings were documented and analyzed for each participant; first, the participant was asked to read a text; second, the participant was asked to describe a positive experience; and third, the participant was asked to describe a negative experience. Mel Frequency Cepstral Coefficients (MFCCs) were used in order to extract features from the voice signal.
The results identified 13 voice features that were associated with CAD. Stepwise binary logistic regression, with adjustment for age and gender, identified one voice feature that was associated with a 19-fold increased likelihood of CAD. With adjustment for age, gender, and cardiovascular risk factors, this feature was independently associated with a significant 2.6-fold increased likelihood of CAD. The study was presented as a poster session at the American Heart Association (AHA) scientific sessions, held during November 2016 in New Orleans (LA, USA).
“One voice characteristic in particular indicated an almost 20-fold increase in the likelihood of CAD. Since such voice characteristics can even be identified over a phone call, it is even feasible that people will be screened for CAD over the phone,” concluded lead author Elad Maor, MD, PhD, and colleagues of the Mayo Clinic. “Beyond that, identifying more voice biomarkers can produce a comprehensive test that would identify the possibility of a number of different conditions.”
“A patient’s voice is the most readily available, easy to capture, and rich output the body offers. We are very excited to be able to work with Mayo Clinic on such a breakthrough research, studying the potential of using the human voice in healthcare monitoring, and specifically cardiovascular disease,” said Yuval Mor, CEO of Beyond Verbal.
Related Links:
Beyond Verbal
Mayo Clinic
Researchers at Beyond Verbal (Tel Aviv, Israel) and the Mayo Clinic (Rochester, MN, USA), conducted a double-blind study involving 150 patients, including 120 patients who presented for coronary angiography, 21 apparently healthy control volunteers, and 9 control subjects who were referred to non-cardiac procedures. All subjects had their voice signal recorded prior to coronary angiography using the Beyond Verbal app, downloaded to their personal smartphone device.
Voice was then analyzed for multiple pre-specified features of intensity and frequency by different analytic tools. A total of three 30-second separate baseline voice recordings were documented and analyzed for each participant; first, the participant was asked to read a text; second, the participant was asked to describe a positive experience; and third, the participant was asked to describe a negative experience. Mel Frequency Cepstral Coefficients (MFCCs) were used in order to extract features from the voice signal.
The results identified 13 voice features that were associated with CAD. Stepwise binary logistic regression, with adjustment for age and gender, identified one voice feature that was associated with a 19-fold increased likelihood of CAD. With adjustment for age, gender, and cardiovascular risk factors, this feature was independently associated with a significant 2.6-fold increased likelihood of CAD. The study was presented as a poster session at the American Heart Association (AHA) scientific sessions, held during November 2016 in New Orleans (LA, USA).
“One voice characteristic in particular indicated an almost 20-fold increase in the likelihood of CAD. Since such voice characteristics can even be identified over a phone call, it is even feasible that people will be screened for CAD over the phone,” concluded lead author Elad Maor, MD, PhD, and colleagues of the Mayo Clinic. “Beyond that, identifying more voice biomarkers can produce a comprehensive test that would identify the possibility of a number of different conditions.”
“A patient’s voice is the most readily available, easy to capture, and rich output the body offers. We are very excited to be able to work with Mayo Clinic on such a breakthrough research, studying the potential of using the human voice in healthcare monitoring, and specifically cardiovascular disease,” said Yuval Mor, CEO of Beyond Verbal.
Related Links:
Beyond Verbal
Mayo Clinic
Latest Health IT News
- Machine Learning Model Improves Mortality Risk Prediction for Cardiac Surgery Patients
- Strategic Collaboration to Develop and Integrate Generative AI into Healthcare
- AI-Enabled Operating Rooms Solution Helps Hospitals Maximize Utilization and Unlock Capacity
- AI Predicts Pancreatic Cancer Three Years before Diagnosis from Patients’ Medical Records
- First Fully Autonomous Generative AI Personalized Medical Authorizations System Reduces Care Delay
- Electronic Health Records May Be Key to Improving Patient Care, Study Finds
- AI Trained for Specific Vocal Biomarkers Could Accurately Predict Coronary Artery Disease
- First-Ever AI Test for Early Diagnosis of Alzheimer’s to Be Expanded to Diagnosis of Parkinson’s Disease
- New Self-Learning AI-Based Algorithm Reads Electrocardiograms to Spot Unseen Signs of Heart Failure
- Autonomous Robot Performs COVID-19 Nasal Swab Tests
- Statistical Tool Predicts COVID-19 Peaks Worldwide
- Wireless-Controlled Soft Neural Implant Stimulates Brain Cells
- Tiny Polymer Stent Could Treat Pediatric Urethral Strictures
- Human Torso Simulator Helps Design Brace Innovations
- 3D Bioprinting Rebuilds the Human Heart
- Nanodrone Detects Toxic Gases in Hazardous Environments