SickKids Research Institute

Scientific research, studies, and explorations in artificial intelligence, machine learning theory, and across the domains of biomedical informatics applications to decipher human disease heterogeneity for sick kids.


What We Do

We aim to conduct translational studies for children with rare and high risk diseases for the care and cure of sick (children) kids.

CiDrep SickKids Research Institute (CSRI) focus on artificial intelligence (AI), translational research (TR) and biomedical informatics (BMI), funded by income therefrom to support research in basic science to leverage heterogeneity to accelerate translational medicine to decipher disease. Our research is a data-driven cloud laboratory thats applying deep learning techniques to develop diagnostics and therapies to improve child health. In 2018, we begun collecting and storing available datasets that emanate from pediatric phenotypic and research studies. We have stored terabytes of data points in cyberinfrastructure (cloud repository and data vaults), and continuing to develop machine learning methods and tools to embrace heterogeneity in data that can accelerate translational medicine for diagnostics and therapies to improve health.

CSRI Deep Learning with EHR and Biomedical Data
CSRI Deep Learning with EHR and Biomedical Data

EHR Deep Learning

We are developing "AI" supervised and unsupervised machine learning (ML) methods to detect and decipher human disease heterogeneity.

CSRI Decoding Genomic "Dirty" Data
CSRI Decoding Genomic "Dirty" Data

Decoding "Dirty" Data

We are decode pediatric phenotypic and genomic datasets using algorithm to understand their role in human diseases.

CSRI Translational Medicine Contribution
CSRI Translational Medicine Contribution

Translational Science

We are linking “clinical and genomic data” and applying machine learning to develop diagnostics and therapies to improve child health.

Looking for a new challenge?

We are building a diverse team of clinical informaticians, computer scientists, computational biologists, bioinformaticians, data engineers, statisticians and AI scientists, to work closely together to better understand and study human disease heterogeneity, by applying deep learning techniques to elucidate relationships between diseases by integrating multiple types of data (from EHRs to high-throughput genes sequencing) and ultimately to draw connections and conclusions about factors that impact patient health.