Sunil Kalmady Vasu, PhD, MSc (Med. Biotech), MSc (Comp. Sci)

Area of Study / Keywords

Medical AI Machine Learning Clinical decision support Biostatistics Electrocardiogram Computational Psychiatry Medical Imaging Schizophrenia functional MRI

About

With the aim of advancing personalized treatment options for complex medical disorders, my professional goal centers around the application of data science and artificial intelligence. My educational background encompasses a master's degree in medical biotechnology specializing in human genetics, a master's degree in computer science, and a Ph.D. in neuropsychiatry focusing on brain imaging in mental disorders. Additionally, I have undergone extensive post-doctoral training at the Alberta Machine Intelligence Institute (AMII), recognized as one of Canada's leading centers of excellence in artificial intelligence. This diverse foundation provides me with a unique perspective and expertise in tackling medical problems through data analytical techniques, while also fostering effective collaboration with experts across disciplines. Over the past decade, I have had the privilege of co-supervising graduate students and international interns in both computing science and biomedical domains. This experience has allowed me to nurture the growth of aspiring researchers while contributing to the development of cutting-edge projects. During this time, my team and I have successfully developed, evaluated, and deployed machine learning models using a wide range of structured and unstructured real-world healthcare datasets.

By combining my expertise in medical biotechnology, neuroscience, data science, and artificial intelligence, along with my fervor for interdisciplinary collaboration and mentoring, I am well-equipped to address biomedical challenges with innovative and data-driven approaches.

Research

In my current role as an Adjunct Professor of Computing Science and a Senior Machine Learning Specialist in the Department of Medicine at the University of Alberta, Canada, I lead a dedicated team focused on developing learning tools for predicting diagnostic and prognostic outcomes in cardiovascular diseases. Leveraging large-scale datasets, including electronic medical records, electrocardiograms, and echocardiograms comprising over a million records, our recent research has made significant contributions to the field, with publications in journals such as Nature Digital Medicine. Furthermore, my previous work has demonstrated substantial advancements in the domain of psychiatric disorders, where I successfully utilized multimodal imaging and artificial intelligence methods to predict symptom clusters and treatment responses in conditions like Schizophrenia and OCD. These contributions have been published in reputable journals, including Nature Schizophrenia, and have received recognition through media coverage.