2023 Health Data Nexus Dataset Grants
The Health Data Nexus is T-CAIREM’s flagship health data and analytics platform in Canada, uniquely combining a data publishing platform with a cloud-based analytics solution.
We offered two $50,000 grants to encourage the creation of large de-identified datasets for use by a broad range of AI researchers that will be housed on the Health Data Nexus.
Dr. Mark I. Boulos
Dr. Boulos is the Principal Investigator of this research project. He will use his grant to create a large dataset of aggregated sleep studies, including polysomnography data with associated comorbidities and health questionnaire data, for use in analyzing a variety of research topics such as predicting disease states.
Proposal
“Advancing Clinical Outcomes Using Comprehensive Sleep Health and Polysomnography Data”
"The Sleep Laboratory at Sunnybrook Health Sciences Centre collects a rich dataset of overnight physiological polysomnography and health questionnaire data from participants who are referred by their physicians for a sleep study. There are ~1000 sleep studies conducted per year, representing the opportunity for the generation of a large and diverse dataset.
"We propose to collect data from all consenting participants who are tested at the sleep laboratory and create a de-identified dataset containing raw polysomnography data, aggregated sleep study metrics, medical comorbidities and health questionnaire data, as well as medication information.
"This extensive sleep and health data will allow for a large variety of research topics that can be explored by future T-CAIREM users, such as predicting disease states like Parkinson’s disease through the analysis of sleep signals. We will implement a sustainable pipeline for data collection, and periodically update the dataset as new data becomes available."
Dr. William T. Tran
Dr. Tran is assembling a high-resolution imaging database for pre-treatment breast cancer tumors to develop AI techniques for predicting chemotherapy resistance.
Proposal
“Advancing Artificial Intelligence Applications Using High-Resolution Digital Tumor Biopsies of High-Risk Breast Cancer”
"This project aims to assemble a multi-institutional breast tumor database comprising clinical information and digital pathology samples of high-risk cancer. Neoadjuvant (pre-operative) chemotherapy (NAC) is given to patients with high-risk breast cancer. NAC has several clinical advantages, including reducing the risk of micrometastatic spread, permitting definitive pathologic evaluation, enabling long-term prognostication, and steering additional treatments.
"Patients who achieve a pathological complete response (pCR) after receiving NAC (i.e., complete eradication of invasive tumor cells) have a significantly lower risk of breast cancer recurrence and better disease-free survival compared to those with residual disease.
"However, up to 50% of patients exhibit residual disease after completing NAC1. We are curating a high-resolution digital tumor repository of pretreatment breast cancer biopsies in this patient population to develop artificial intelligence techniques to yield imaging biomarkers and characterize tumor characteristics and spatial parameters to predict the risk of NAC resistance."