Embedded Files
Acoustic-Based Technology for Cardio-Respiratory Disease Management
Acoustic-Based Technology for Cardio-Respiratory Disease Management
We develop AI-driven tools that utilize acoustic signals, including voice, snoring, and heart sounds, for the diagnosis and management of cardiometabolic and respiratory diseases, such as sleep apnea, diabetes, and heart failure. Our work involves detecting sleep apnea from voice and snoring patterns, as well as monitoring heart failure through heart sound analysis, to enable accessible, non-invasive, and remote health assessments.
We develop AI-driven tools that utilize acoustic signals, including voice, snoring, and heart sounds, for the diagnosis and management of cardiometabolic and respiratory diseases, such as sleep apnea, diabetes, and heart failure. Our work involves detecting sleep apnea from voice and snoring patterns, as well as monitoring heart failure through heart sound analysis, to enable accessible, non-invasive, and remote health assessments.
Generative AI-Based Technology for Self-Care Management
Generative AI-Based Technology for Self-Care Management
We design and develop generative AI-powered chatbots that support self-care management for chronic diseases, such as heart failure, cancer, and mental disorders. These systems provide personalized education, lifestyle guidance, and symptom support, enabling patients to actively engage in their care and make informed health decisions.
We design and develop generative AI-powered chatbots that support self-care management for chronic diseases, such as heart failure, cancer, and mental disorders. These systems provide personalized education, lifestyle guidance, and symptom support, enabling patients to actively engage in their care and make informed health decisions.
Responsible Multi-Modal AI for Chronic Disease Diagnosis and Monitoring
Responsible Multi-Modal AI for Chronic Disease Diagnosis and Monitoring
We examine the impact of algorithmic biases in machine learning models to ensure trustworthy diagnosis. Our work integrates diverse physiological signals, including EEG, fMRI, ECG, and electronic health records, to improve the prediction of cardiovascular, neurological, and respiratory diseases.
We examine the impact of algorithmic biases in machine learning models to ensure trustworthy diagnosis. Our work integrates diverse physiological signals, including EEG, fMRI, ECG, and electronic health records, to improve the prediction of cardiovascular, neurological, and respiratory diseases.
Page updated
Google Sites
Report abuse