• Just 10 seconds for advanced diagnosis of heart function! Narayana Health takes giant strides with AI tool
Bengaluru, 5 August 2025 – Narayana Health Clinical Research team and Medha AI – the Advanced Analytics & AI division of Narayana Health, today announced the development of a breakthrough artificial intelligence (AI) model capable of predicting heart function—specifically, left ventricular ejection fraction (EF)—from a standard ECG image in near real-time. Designed for seamless integration into clinical workflows, the model aims to support earlier identification of heart failure and to improve diagnostic access in resource-limited settings.
This innovation addresses a critical gap in the diagnostic pathway for millions of patients. Heart failure affects nearly 10 million people across India and accounts for 1.8 million hospital admissions annually. Yet access to echocardiography (ECHO)—the gold standard for evaluating heart function—remains uneven, especially in rural areas. Narayana Health’s AI model offers a novel, scalable approach to screen patients using widely available ECG machines and cloud-based analytics.
Trained on over 100,000 ECG images paired with echocardiogram reports, the model has demonstrated strong predictive performance. In external validation across 14 tertiary centres involving more than 57,000 patients, it identified 97% of individuals with severely reduced EF (≤35%). On average, these patients were flagged 58 days earlier than when echocardiography was eventually ordered—offering valuable lead time for clinical intervention.
Dr Devi Shetty, Founder and Chairman, Narayana Health, said, “This breakthrough represents much more than an AI model — it is a reflection of what Narayana Health stands for: combining clinical expertise, deep research, and cutting-edge technology to solve real problems at scale. Detecting heart failure through a simple ECG in near real-time is a leap forward in making advanced diagnostics not just efficient but truly accessible to the masses. AI empowers us to extend the reach of high-quality care beyond hospital walls — enabling faster decisions, earlier interventions, and better outcomes. This innovation showcases India’s potential to lead the future of healthcare globally.”
The Medha AI model for LVEF prediction from ECGs, has been integrated into Athma, Narayana Health’s home-built Electronic Medical Record (EMR) system and is currently undergoing rigorous validation at key sites, including Narayana Institute of Cardiac Sciences and Mazumdar Shaw Medical Center in Narayana Health City, as well as select clinics in Bengaluru and at the Rabindranath Tagore International Institute of Cardiac Sciences in Kolkata. The model is designed to deliver results in near real-time, with the goal of supporting triage and care planning without disrupting provider workflows.
During the event, Dr Emmanuel Rupert, Managing Director and Group CEO, Narayana Health said, “What sets Narayana Health apart is not just our ability to innovate, but to translate that innovation into everyday clinical practice. This AI model is a game-changer — it equips frontline clinicians with diagnostic insights that were previously only accessible through advanced infrastructure. The potential impact on early detection, especially in underserved areas, is immense. We are not just leading the race in healthcare AI — we are rewriting what is possible in scalable, patient-centric care.”
Beyond early diagnosis, the platform architecture enables future expansion. Research is underway to broaden its capabilities to include detection of other echocardiographic abnormalities and early signs of coronary artery disease. Narayana Health is also working towards regulatory approvals and open-access distribution for wider adoption.
“What makes this innovation truly novel is its simplicity — our AI model can accurately assess heart function using just an image of an ECG, not complex signal data. In fact, even a mobile phone photo of an ECG strip could be enough to generate a reliable assessment.,” said Dr Pradeep Narayan, Chief Scientific Officer, Narayana Health, and Lead Researcher on this project. “This has the power to transform cardiac care in remote or resource-limited settings. While we are currently validating the model in clinical environments, the early findings are promising. Once fully approved, it could serve as a scalable, real-world solution that brings specialist-level insights to the frontlines of care — helping even the most resource-constrained settings benefit from timely, expert-aligned evaluation,” he added.
To strengthen community outreach, Narayana Health intends to deploy the tool via its mobile medical units, with a focus on underserved geographies. The model’s potential to serve as a population-scale screening tool aligns with the organization’s broader strategy to integrate digital innovation with frontline public health services.
During the event Dr. P M Uthappa, Group Chief Medical Director, Narayana Health emphasized the importance of Responsible AI, stating “Responsible AI in healthcare means more than just innovation — it demands fairness in access, accountability in outcomes, transparency in how decisions are made, and explainability that clinicians can trust. Our ECG-based AI model for heart failure detection embodies these principles, making advanced diagnostics both ethically grounded and clinically actionable across diverse settings.”
“This innovation represents the true democratization of heart failure diagnosis,” said Dr. Deepak Padmanabhan, Senior Consultant, Strategic Lead – Cardiac EP Collegium, Narayana Health. “One of the biggest barriers to treatment is simply that heart failure often goes undiagnosed. Once identified, clinical pathways are relatively well established. But diagnosis itself can be complex and depends heavily on clinical experience. This AI tool is designed to support clinicians by providing reliable insights, even in settings with limited cardiac expertise. Its high accuracy, especially in ruling out heart failure when the algorithm indicates so, makes it an invaluable decision-support tool for managing patients across the country.”
The AI model has been presented at leading conferences including the Heart Rhythm Society Conference (Boston), APHRS (Sydney), IHRSCON (Kolkata), and HRX (Atlanta). It has been published in the Indian Heart Journal and received the BMJ South Asia Award for Digital Innovation.
Beyond the immediate clinical impact, Narayana Health is leveraging AI across its ecosystem to drive clinical, operational, and financial efficiency. Through Medha AI, NH’s dedicated AI division headed by Vivek Rajagopal – Group Chief Analytics & AI Officer, Narayana Health the organization is embedding AI into real-world workflows—from early disease detection and diagnostic support to automated documentation and predictive resource planning. These tools streamline clinician decision-making, reduce administrative burden, and enable timely interventions—especially in resource-limited settings. On the financial side, the Medha AI platform empowers operational efficiency, cost optimization, and efficient supply chain operations. This integrated, ethically guided approach to AI reflects Narayana Health’s commitment to scalable, accessible, and high-quality care—positioning the organization at the forefront of healthcare innovation in India and globally.