My research program is dedicated to extracting new forms of knowledge from data generated through clinical and scientific activities and delivering insights from this data to clinicians. Our research includes the development of technology for real-time data extraction, processing, and integration of prediction models into the clinical information technology infrastructure. Additionally, we develop and test new strategies and methods to create digital biomarkers and prediction models, particularly with overlooked data sources and in the context of rare diseases. Finally, we study how prediction models get deployed and implemented in the healthcare system and through innovative clinical trials, study how they are used by clinicians and whether they improve patient outcomes. Our team selects projects with a special emphasis on those that will result in the design and implementation of functional tools and end-to-end solutions.
Current research focus:
1) Development of an EHR-integrated, AI-powered digital platform for the diagnosis, personalized management, and early warning for complications in patients with Kawasaki disease. This work is done in association with the International Kawasaki Disease Registry which is hosted at SickKids. (NIH)
2) Developing new methods and digital tools to integrate exposome information in epidemiological and clinical prediction models (KD epidemiology – Sci Rep)
3) Simulating the effect of predictive allocation (selection therapy/management based on the results of a prediction model) on patient outcomes (Pilot study – JAMIA)
4) Creation of a wearable-devices powered, early warning system for declining cardiac function in stable patients with congenital heart disease (Simulation study – JMIR Cardio)
Each of these areas of focus include multiple projects and we also work on many projects outside of focus areas, to see some of our recently published projects: Pubmed
We offer a variety of opportunities for students at all levels (including undergraduate students) in medicine, public health, data sciences and computer sciences to contribute to research projects. There are many ways to contribute to projects and previous coding or data analytics experience is not necessary for all projects. The only prerequisite is previous completion of a biostatistics course at the undergraduate level.
ICAI2N: AI-Powered Clinical Decision Support for Pediatric Cardiac Care
Overview: Children with congenital heart disease face significant risks during hospital stays, with unplanned ICU readmissions occurring in 4-20% of pediatric cardiac patients, rates are substantially higher than the general pediatric population. These deterioration events lead to increased length of […]
Lead: Cedric Manlhiot
Wearable Technology for Personalized Cardiac Monitoring
Overview: Adolescents with congenital heart disease are at risk of decline in cardiac function that can follow unpredictable time courses, from sudden deterioration to gradual progression. Current clinical scheduling relies on fixed intervals with minimal individualization, leading to suboptimal timing […]
Lead: Cedric Manlhiot
Foundation Models for Kawasaki Disease Diagnosis and Management
Overview: Kawasaki disease is the leading cause of acquired heart disease in children, with potentially devastating cardiac consequences including coronary artery aneurysms. The disease presents significant clinical challenges: delayed diagnosis is common due to non-specific early symptoms, treatment response is […]
Lead: Cedric Manlhiot