Lunch Talk: Dominik Naumann & Theekshana Dissayanake

Lunch Talk: Dominik Naumann & Theekshana Dissayanake "Toward AI-Enabled Cardiovascular Phenotyping in the Vehicle: The AutoHealth Study"

In this Lunch Talk on "Toward AI-Enabled Cardiovascular Phenotyping in the Vehicle: The AutoHealth Study" Dominik and Theekshana will present the AutoHealth study. This study shows how in-car data collected across five cardiovascular cohorts contains sufficient physiological information to distinguish disease groups which enables AI-driven risk assessment.

Abstract: Cardiovascular diseases require earlier detection and longitudinal monitoring, yet current approaches often depend on dedicated devices, intermittent clinical assessments or active patient engagement. The AutoHealth study investigates whether the everyday vehicle can serve as an unobtrusive, context-rich platform for multimodal cardiovascular monitoring under real-world conditions. AutoHealth prospectively included approximately 120 participants across five cohorts: healthy controls, increased cardiometabolic risk, HFpEF, HFrEF and persistent atrial fibrillation. Participants underwent outpatient phenotyping and a standardized in-vehicle protocol including rest, real-world driving, cognitive stress, emergency braking and recovery. In-car monitoring combined with steering-wheel ECG, remote photoplethysmography, clinical-grade reference biosignals, electrodermal activity and contextual vehicle data. Preliminary analyses show that driving induces distinct hemodynamic and autonomic changes while preserving cohort-specific cardiovascular signatures. Stress and recovery phases further revealed altered response patterns across disease groups. A baseline machine-learning analysis using multimodal ECG-PPG fusion demonstrates that in-car biosignals capture sufficient physiological information to differentiate cardiovascular groups in a rigorous subject-independent setting. These findings support the vehicle as a dynamic digital phenotyping environment for unobtrusive cardiovascular monitoring and future AI-enabled risk assessment.

Dr. Theekshana Dissanayake earned his PhD from Queensland University of Technology (QUT), Brisbane, Australia, where he was affiliated with the Signal Processing, Artificial Intelligence, and Vision Technologies (SAIVT) research group led by Professor Sridha Sridharan. His doctoral research focused on deep machine learning for biosignal analysis and resulted in eight Q1 journal publications addressing learning from medical data, including biomedical signals and medical imaging. He actively contributes to the academic community as a reviewer for leading journals in machine learning and biomedical engineering, including the IEEE Journal of Biomedical and Health Informatics, IEEE Sensors Journal, NPJ Digital Health, NPJ Artificial Intelligence, and Computers in Biology and Medicine. During his PhD, Dr. Dissanayake held research affiliations as a Graduate Research Assistant with Monash University, the AIM for Health Lab, and Alfred Health Neuroscience. He has also collaborated with industry partners such as WearOptimo Pvt Ltd and M3DICINE Pvt Ltd, focusing on the design and development of intelligent biomedical sensing systems. Prior to his doctoral studies, he completed his Bachelor’s degree with First-Class Honours in Computer Engineering from the University of Peradeniya, Sri Lanka.

Dominik Naumann: Doctor of MedicineClinician Scientist at Charité Universitätsmedizin Berlin / IKIM research group (BIFOLD/Charite)

About the BIFOLD Lunch Talk Series

The BIFOLD Lunch Talk series gives BIFOLD members and external partners the opportunity to engage in dialogue about their research in Machine Learning and Big Data. Each Lunch Talk offers BIFOLD members, fellows and colleagues from other research institutes the chance to present their research and to network with each other.

The Lunch Talk takes place at BIFOLD and online. For further information on the Lunch Talks and registration, contact Dr. Laura Wollenweber via email.