Significantly higher sensitivity seen, while specificity was lower for AI-augmented system versus standard of care of analog auscultation
TUESDAY, Feb. 10, 2026 (HealthDay News) — Artificial intelligence (AI)-enabled digital stethoscopes can significantly improve detection of valvular heart disease (VHD), according to a study published in the March issue of the European Heart Journal: Digital Health.
Moshe Rancier, M.D., from Mass General Brigham Community Physicians in Lawrence, Massachusetts, and colleagues examined whether an AI-enabled digital stethoscope can augment primary care providers” ability to detect clinically significant VHD compared with analog auscultation (standard of care [SOC]) in a prospective study involving 357 patients aged 50 years and older at risk for heart disease.
The researchers found that sensitivity was significantly higher with the AI-augmented system versus SOC (92.3 versus 46.2 percent), while specificity was significantly lower (86.9 versus 95.6 percent). Twelve cases of previously undiagnosed moderate- or worse-severity VHD were identified with the AI-augmented system compared with six that were identified with routine auscultation.
“We have shown that an AI-enabled stethoscope is much better at spotting which patients have moderate-to-severe valvular disease than a traditional stethoscope in real-world clinical settings,” senior author Rosalie V. McDonough, M.D., from Eko Health in Emeryville, California, said in a statement. “We hope this technology will allow patients to get faster access to an echocardiogram to formally diagnose their condition and then access treatment more quickly. At a population level, this technology could reduce hospital admissions and the overall cost of health care.”
Several authors disclosed current or former employment with Eko Health.
Screening + Online Cognitive Behavioral Therapy Program Aids Nurses" Mental Health
Autism Spectrum Disorder Diagnoses Increased for Females Since 2020
2005 to 2023 Saw More U.S. Women Never Screened for Cervical Cancer
Machine Learning Model IDs Heart Failure With Reduced Ejection Fraction Using Routine Lab Indicators
Use of SAMA, SABA Linked to Cardiovascular Events, Mortality in Asthma, COPD
2011 to 2021 Saw Heart Failure-Related Hospitalization Rise in CKD
Addition of CAC to PREVENT-ASCVD Equations May Improve Predictive Utility in Certain Patients
Central Adiposity Reclassifies Cardiovascular Risk Across BMI Spectrum