Cardiovascular disease is becoming increasingly common in young people aged 20 to 29, according to the World Health Organization, due to the rise in metabolic conditions such as obesity, hypertension, hyperlipidemia, and diabetes among young populations worldwide.

Meanwhile, advanced heart assessments that could help with early detection and treatment usually require high-tech diagnostic equipment and specialized care, often only available in major hospitals in big cities. This makes detailed yet non-invasive heart monitoring difficult, particularly for at-risk individuals who could benefit from such evaluations.

Today, researchers are exploring how artificial intelligence (AI) can help overcome these barriers.

A team of international scientists led by Patricia Angela R. Abu of Ateneo de Manila University Department of Information Systems and Computer Science (DISCS) have developed an AI model that accurately predicts how effectively the heart pumps blood—a metric known as the cardiac index (CI), which includes physiological indicators such as heart rate, stroke volume index, and cardiac output. Clinicians use CI to evaluate heart function and guide treatment decisions.

Like an artificial brain, this new AI model ponders physiological indicators from non-invasive sensor stickers placed on the patient's skin. With a classification accuracy of 97.78%, the system demonstrates the potential for a simpler and more accessible approach to monitoring heart health.

This innovative use of AI is a promising alternative to conventional monitoring procedures that require specialized hemodynamic analyzers, controlled clinical settings, and specialized healthcare professionals.

By leveraging modern algorithms to analyze basic health data collected from non-invasive sensors, the AI researchers are helping make advanced monitoring more practical and widely available even in healthcare settings that lack specialized equipment and expertise.

These findings point to a future in which advanced cardiovascular assessment is no longer confined to the walls of large hospitals and specialized clinics. They suggest that reliable cardiovascular assessment may not always require complex or resource-intensive procedures, as shown by the model's strong performance with fewer inputs. The researchers plan to validate the approach in more diverse populations, and are also looking into even further reducing the number of measurements required.

Source:

Journal reference:

Chang, C.-H., et al. (2026). Robust Non-Invasive Cardiac Index Prediction via Feature Integration and Data-Augmented Neural Networks. Bioengineering. DOI: 10.3390/bioengineering13040477. https://www.mdpi.com/2306-5354/13/4/477