Japanese medical technology company Simplex Quantum has developed an AI system that can accurately assess heart failure (HF) severity and track disease progression using single-lead ECG data from commonly available devices, including the Apple Watch.

Working with the University of Tokyo Hospital, the peer-reviewed clinical study has been published in the International Journal of Cardiology.

At the core of this breakthrough is the HF-index, an AI-derived metric that enables on-demand monitoring of heart failure severity from home. This technology has the potential to reduce hospitalisations by enabling earlier clinical intervention.

“This AI model may support on-demand, non-invasive heart failure monitoring, even before symptoms appear,” said Katsuhito Fujiu, project professor at the University of Tokyo (www.u-tokyo.ac.jp) and senior author of the study. “It could fundamentally change how we care for patients at risk of worsening heart failure by empowering both clinicians and patients with timely insights.”

Ryu Saito, CEO of Simplex Quantum, added: “These results validate the clinical foundation of our solution and show how AI can turn familiar devices into powerful medical tools. We are proud to collaborate with top-tier institutions to bring this technology into everyday practice.”

Heart failure affects over 64 million people globally and is a leading cause of hospital readmissions and rising healthcare costs. Existing monitoring options, such as implantable devices or in-hospital diagnostics, can be invasive, expensive or unavailable to many patients. This AI-powered option could provide a scalable, at-home alternative using devices already in wide consumer use.

The AI model, trained on ECG data from 9518 individuals, achieved 91.6% accuracy in classifying heart failure severity across healthy, NYHA I–II (mild) and NYHA III–IV (moderate to severe) categories. The model demonstrated AUC values up to 0.993, with sensitivity and specificity between 89–97%. The HF-index showed a strong correlation with plasma B-type natriuretic peptide (BNP) levels (R = 0.74), a widely accepted biomarker for heart failure.

To read the study, go to www.internationaljournalofcardiology.com/article/S0167-5273(25)00246-3/fulltext.

The AI system described in the study powers NIHA-HF, Simplex Quantum’s investigational software platform for heart failure risk detection and monitoring. Regulatory submissions are underway in Japan and the USA, with product approvals targeted for 2026.

Headquartered in Tokyo, Simplex Quantum (simplex-q.com) is a medical AI company focused on cardiovascular diagnostics. Its flagship product, NIHA-HF, applies neural networks to detect and monitor heart failure via ECG, bridging clinical-grade insights with consumer-friendly technology.