Meet our DASH community
DASH is featuring our members and trainees on our newsletter and website to explore the various expertise, interests, and background that each of us brings to our data science and health community.
Name:
Ricky Hu
Title and Affiliation:
Internal Medicine Resident, UBC Department of Medicine
Research Engineer, UBC Robotics and Control Laboratory
Role in DASH:
Trainee
Bio:
Ricky is a resident physician in Internal Medicine at the University of British Columbia. Prior, he completed undergraduate degrees in Engineering Physics and in Mathematics and a Master's degree in Biomedical Engineering developing new artificial intelligence (AI) tools to identify abnormal tissue in ultrasound. He then earned his medical degree at Queen's University School of Medicine.
He has a passion for integrating the complexity of multiple disciplines, namely as an AI engineer and as a future physician, to discover new ways in analyzing medical data to perform previously difficult tasks. His research work is in the domain of image analysis, leveraging a multidisciplinary background to develop mathematical models and program algorithms that are grounded in physiology and physics for interpretable AI. Techniques he has published include new ways to characterize ultrasound acoustic shadows by modeling acoustic scatter, combining carotid plaque measurements and clinical data to predict cardiac events with machine learning, using radiomics for explicit feature generation in computed tomography to prognosticate liver metastases, and predicting renal function from ultrasonic tissue granularity.
As an advocate for ethical and informed use of AI, he has also taught fundamentals of AI to over 300 medical students, residents, and healthcare professionals. His goal is to be a physician that maximizes quality of life by understanding subspecialty knowledge to apply state-of-the-art care while innovating care in the future. He aspires to be a leader in data science and medicine as a technical expert at all levels, whether in treatment planning at the bedside, programming in the laboratory, or in committees to decide how best to apply AI technologies.