Using daily voice recordings to spot pulmonary artery pressure changes in people with heart failure

Voice Analysis Using Artificial Intelligence to Detect Changes in Pulmonary Arterial Pressure in Patients With Heart Failure and an Implanted Pressure Sensor

We will test whether daily voice recordings from people with heart failure and implanted pulmonary artery pressure sensors can help an AI detect rises in lung blood pressure.

Quick facts

• Study type: Observational
• Enrollment: 60 (estimated)
• Ages: 18 Years and up
• Sex: All
• Sponsor: Noah Labs (Industry-sponsored)
• Locations: 3 sites (San Francisco, California and 2 other locations)
• Trial ID: NCT07443670 on ClinicalTrials.gov

What this trial studies

This is a prospective, multi-center observational study in which participants with implanted pulmonary artery (PA) pressure sensors provide daily voice recordings via a mobile app for 12 weeks while continuing standard PA pressure monitoring and heart failure care. Voice samples include sustained vowel sounds and a standardized reading passage and are collected on participants' smartphones or tablets. PA pressure readings obtained as part of routine care are paired with the voice data and analyzed retrospectively using classical machine learning and deep learning methods. The primary endpoint is the sensitivity and specificity of the AI-based voice analysis in detecting PA pressure changes at prespecified thresholds, and no clinical decisions are made based on voice results during the study.

Who should consider this trial

Good fit: Adults with heart failure who already have an implanted PA pressure sensor, can read aloud in English or German, and can use a smartphone or tablet to record daily voice samples are ideal candidates.

Not a fit: People without implanted PA sensors, those with pathological voice changes, COPD on home oxygen, dialysis-dependent kidney failure, pregnancy, or inability to reliably use a smartphone are unlikely to benefit from this approach.

Why it matters

Potential benefit: If successful, this approach could provide a low-cost, non-invasive way to detect pulmonary congestion earlier and reduce reliance on invasive sensors.

How similar studies have performed: Early research has suggested voice features can reflect respiratory and fluid status, but applying AI to detect PA pressure changes in patients with implanted sensors is a novel and not yet validated strategy.

Eligibility criteria

Inclusion Criteria:

* Age 18 years or older
* Successful implantation of a PA pressure sensor and monitored by a participating study center
* Willingness to record a short predefined text daily for 3 months using a smartphone or tablet
* Ability to comfortably read aloud the study passage in English or German
* Written informed consent obtained

Exclusion Criteria:

* Pregnant, breastfeeding, or unwilling to practice birth control during participation
* Condition that in the opinion of the investigator would compromise patient safety or data quality
* Pathological voice changes due to surgery or injury
* Planned invasive cardiac procedures during the study period
* COPD requiring home oxygen therapy
* Chronic kidney disease requiring dialysis
* Cognitive dysfunction limiting ability to perform daily voice recording
* Inability to read English or German
* Physical inability to use the recording device

Where this trial is running

San Francisco, California and 2 other locations

• University of California, San Francisco (UCSF) — San Francisco, California, United States (Recruiting)
• BG Klinikum Unfallkrankenhaus Berlin, Dept. of Cardiology — Berlin, State of Berlin, Germany (Completed)
• University Hospital Frankfurt, Dept. of Cardiology and Angiology — Frankfurt, Germany (Completed)

Study contacts

• Study coordinator: Leonhard Riehle, MD

Conditions Heart Failure