Problem Solution Science Roadmap Clinical Studies Team Demo → Get in Touch

Your voice
knows your heart.

Lub Dub Lab is building a voice-based AI platform that turns a daily voice interaction on a smartphone into early heart disease insights — for any patient, anywhere.

Simple. Universal. Scalable.

See How It Works View Demo Get in Touch
Scroll

The Problem

Universal screening for the world's #1 killer is missing.

Despite being the leading cause of death globally, heart disease still lacks a simple, universal, and scalable screening approach. Current evaluation requires multiple complex tests — making screening fragmented, costly, and inaccessible.

20 million
deaths from heart disease globally each year
#1
cause of death worldwide — ahead of cancer, COVID, and stroke
40 seconds
a heart attack occurs somewhere every 40 seconds
1 in 5
heart attacks are silent — the patient has no warning symptoms

Fragmented Screening

No single universal test exists. Blood pressure, cholesterol, ECG, echocardiogram, and coronary calcium scan — all required.

Rising Costs

Heart failure costs projected to exceed $160B per year by 2030. Hospitals are financially penalized for preventable readmissions.

Specialist Shortage

Many communities are severely underserved — both in the U.S. and across the developing world.

The Solution

View Demo

Voice as a new modality for heart disease screening and monitoring — How It Works

A daily AI phone call, a patient companion app, and wearable integration — multiple ways for patients to stay connected on their own terms, and one platform for care teams to monitor, triage, and act before deterioration becomes a hospitalisation.

Patient enrolling at hospital discharge
Step 1 — Enroll

Every voice is unique. Theirs becomes their baseline.

At discharge, the patient completes a brief voice call to establish their personal voice baseline — a physiological fingerprint tied to their health at that moment.

AI agent calling patient at home
Step 2 — Call

The AI calls them. They just pick up.

Each day, an AI agent calls the patient on their schedule — capturing a voice recording, blood pressure, weight, and a wellbeing check-in. All in one familiar phone call.

Patient logging blood pressure and weight
Step 3 — Listen

Some of the most valuable data comes from conversations that already happen.

With consent, Lub Dub Lab passively listens to everyday calls with family and friends — WhatsApp, FaceTime, and more. Voice features only. Never the content. Your words stay private.

AI voice analysis visualization
Step 4 — Analyze

AI detects what the patient can't feel — yet.

Every voice interaction is processed in real time — machine learning scans breathing and acoustic features for shifts linked to fluid overload and cardiopulmonary stress, then scores them against the patient's personal baseline.

Nurse receiving risk-graded alert on dashboard
Step 5 — Track

Every signal, in one place. Nothing missed.

Risk scores, vitals, and wellbeing data flow into a single care team dashboard — a complete, longitudinal picture of every patient.

Nurse intervening early with patient
Step 6 — Intervene

Earlier is everything.

Risk-graded alerts with guided next steps reach the care team the moment deviation is detected. They escalate when needed — before deterioration becomes a hospitalization.

View Demo

For Patients

Built for the patients who need it most.

Voice Signal
Cardiac stress alters the voice before symptoms surface. The AI hears the signal days before a crisis.
Personal Baseline
Baseline captured at discharge. Every daily reading is measured against that patient's own healthy voice, not a population norm.
Proactive Outreach
The AI calls patients on their schedule. No reminders, no apps to open — for high-risk patients, that's the difference between daily monitoring and none.
Multilingual
Calls run in the patient's language. Biomarker analysis reads acoustics — not words — so language is never a barrier.
Multi-modal
AI call, companion app, or wearable sync — patients choose. The care team sees one complete picture regardless.

For Care Teams

Built for the teams who have no time to waste.

Effortless at Scale
The AI calls every patient, every day. Nurses skip the routine outreach and act only when it matters.
Richer Signal
Three streams, one patient profile — AI agent calls, passive family and friends phone call monitoring, and wearable or app-synced vitals. More data, more often.
Trajectory
Deterioration doesn't happen overnight. Lub Dub Lab tracks each patient's risk score over time — so a gradual climb never goes unnoticed.
Actionable Alert
Risk-graded alerts with guided next steps — not just a flag, but a recommended action so nurses know exactly what to do.
Panel View
Risk scores, vitals, wellbeing, and alerts across every patient in one view. Know who's declining without pulling a chart.

Scientific Foundation

Grounded in peer-reviewed research.

Our platform builds on a growing body of published evidence linking vocal biomarkers to cardiovascular disease. When heart failure worsens, fluid accumulates in the lungs and throat — subtly altering speech patterns detectable by machine learning.

Voice characteristics changed during acute heart failure decompensation and improved with clinical stabilization.

Remote Speech Analysis in Acute Decompensated Heart Failure
JACC: Heart Failure · 2022

A 30-second voice biomarker predicted a 2.6× higher risk of future major cardiac events at follow-up.

Noninvasive Voice Biomarker & Incident Coronary Artery Disease
Mayo Clinic Proceedings · 2022

Voice signal characteristics were independently associated with coronary artery disease after adjusting for standard risk factors.

Voice Signal Characteristics & Coronary Artery Disease
Mayo Clinic Proceedings · 2018

Across studies, vocal biomarkers consistently correlated with heart failure severity and outcomes.

Voice Assessment & Vocal Biomarkers in Heart Failure: A Systematic Review
Circulation: Heart Failure · 2025

Voice analytics enabled low-friction, workflow-integrated monitoring of heart failure patients.

Utilizing Conversational Artificial Intelligence, Voice, and Phonocardiography Analytics in Heart Failure Care
Heart Failure Clinics · 2022

Speech and acoustic biomarkers are recognized as scalable tools for cardiovascular risk stratification and monitoring.

Artificial Intelligence in Cardiovascular Medicine: Clinical Applications
European Heart Journal · 2024

Development Roadmap

From validation to FDA clearance and scale.

In Progress
Phase 1a
2026 H1
Validate and Collect
Complete clinical studies; hold FDA pre-sub meeting. Daily AI calls replace manual outreach, drive patient adherence, and build a longitudinal voice dataset.
Phase 1b
2026 H2
Build and Pilot
Build voice analytics engine. First paid pilots under CDS-exempt framing.
Phase 2
2027
Expand and Submit
Scale hospital sales under CDS exemption. De Novo submission as credibility signal.
Phase 3
2028+
Clear and Scale
FDA clearance obtained. Insurance reimbursement codes applied.

Clinical Studies

Build on existing research —
with meaningful enhancements.

~1,000 Participants
5 Sites
3 Countries

Design: Prospective case-control study with single and longitudinal visits (~30–45 min).

Protocol: Demographics, symptoms, optional labs/ECG/echo, and 3×30-second voice recordings per visit.

Primary Endpoint: AUROC ≥ 0.75 for voice risk score vs. confirmed heart failure status.

Secondary Endpoint: Correlation with natriuretic peptides; subgroup robustness.

HCA Florida Largo Medical Center

Largo, Florida
U.S.A.
PI: Dr. C.B. Sai-Sudhakar
Pending

University of Connecticut Health Center

Farmington, Connecticut
U.S.A.
PI: Dr. Yazhini Ravi
Pending

Instituto de Cardiología de Corrientes

Corrientes
Argentina
PI: Dr. Cesar Rodrigo Zoni
IRB Approved

Sri Ramachandra Medical College

Chennai
India
PI: Dr. J.V. Balasubramanium
IRB Approved

Mina Heart Care

Chennai
India
PI: Dr. J.V. Balasubramanium
Pending

What Makes Our Dataset Different

Statistical Power

Recruiting ~1,000 patients vs. Mayo Clinic's 108. A larger dataset enables more robust model training and validation.

Geographic & Linguistic Diversity

Multi-site study across the U.S., India, and Argentina — capturing accents, languages, and cultural speech patterns.

Real-World Recording Conditions

Testing both smartphone-built-in microphones and external mics to compare signal strength & model performance.

Multiple Cardiovascular Indications

Dataset includes both heart failure and coronary artery disease patients, enabling cross-indication signal comparison.

The Team

MIT Sloan Fellows MBA.

We combine physician-scientist depth, operational rigor, and commercial healthcare experience — united by a personal connection to the problem.

Dr. Yazhini Ravi
Primary Founder & CEO
Physician-scientist with 15 years of heart failure and heart transplant research experience. Leads Clinical & Scientific Research.
Lost mother to heart disease at age 15 and father at age 20; became a physician-scientist in heart failure and heart transplant.
Kohei Banno
Co-founder & COO
Banker-turned serial entrepreneur with 5+ years of experience building regulated medical devices. Leads Finance, Operations & Regulatory.
Family history of heart disease inspired his entrepreneurial career in developing vascular stents.
John Law
Co-founder & CPO
Healthcare strategy consultant with a decade of experience commercializing breakthrough therapies. Leads Product & Strategy.
Like his father, John was diagnosed with hypertension. They are on lifelong medications and at elevated risk of developing heart disease.

Get Involved

Follow your voice.
Help us follow yours.

We're looking for clinical partners, research collaborators, and investors who believe the future of cardiac care is non-invasive, accessible, and intelligent.

Email Us

hello@lubdublab.co

Location

MIT Sloan, Cambridge, MA

Open To

Clinical partnerships, research collaboration, seed investment, advisory introductions, and pilot hospital discussions.

Message sent!

Thanks for reaching out. We'll be in touch within 2 business days.