Delve Health and UW Medicine announce collaboration to generate AI-ready real-world evidence for diabetes research through remote data capture
Delve Health and the University of Washington School of Medicine announce they are joining forces in the NIH-funded AI-READI project — Artificial Intelligence Ready Equitable Atlas for Diabetes Insight — to use remote capture of real-world data designed for AI analysis to advance research in Type 2 diabetes.
Minneapolis-based healthcare technology company Delve Health has issued a press release announcing they are teaming up with the University of Washington School of Medicine (UW Medicine) for a project entitled Artificial Intelligence Ready Equitable Atlas for Diabetes Insight (AI-READI). AI-READI is being funded by the National Institute of Health as part of its Bridge to Artificial Intelligence (Bridge2AI) program, a new initiative to expand the use of artificial intelligence (AI) in biomedical and behavioral research. Delve Health’s mobile and web-based platform Clinical StudyPal will be deployed for real-world remote patient monitoring using wearable smartwatch devices in a decentralized study of over 4000 participants with diverse racial/ethnic backgrounds who represent all stages of Type 2 diabetes (T2D).
Principal investigator and Associate Professor in Ophthalmology at UW Medicine, Aaron Lee, stated: “Our project AI-READI… will collect and release a flagship medical dataset for salutogenesis that will hopefully accelerate machine learning applications and generate novel hypotheses about Type 2 diabetes mellitus.” Aaron explained: “As part of this dataset, we are collecting wearable fitness tracking data along with continuous glucose monitoring to build a biophysical profile of each participant. The smart watches used in this study will hopefully provide both activity monitoring and heart rate measurements that will be critical for achieving this aim.”
Delve Health has configured the Clinical StudyPal platform to capture participant data 24 hours a day from the wearable smart devices. The app will gather measurements of heart rate, activity level and SpO2 level at 15 second intervals. Collection and AI enhanced analysis of this range of health data will allow researchers to better investigate health outcomes associated with T2D.
UW Medicine will use Clinical StudyPal to decentralize the study in recruiting over 4000 people with T2D from all over the US, regardless of participants’ geographical locations, allowing historically underrepresented patient populations access to participate. A critical aspect of amassing data well-suited for AI analysis is building balanced datasets in order to achieve unbiased machine learning (ML) models. To accomplish this, the team will deliberately recruit equal numbers of individuals representing four stages of diabetes severity (no diabetes, lifestyle controlled, oral medication controlled, and insulin dependent) and four self-reported racial/ethnic groups (White, Black, Asian-American, and Hispanic).
“This endeavor with UW Medicine, focused on AI/ML, will provide clinical insights captured through remote patient monitoring and, therefore, will advance diabetes research” said Wessam Sonbol, CEO and Founder of Delve Health “we are excited to collaborate with UW to increase not only the amount of data collected, but improve the quality of data collected. Having real-world evidence in near real-time will not only assist our collective efforts to ultimately improve diabetes clinical research trials and the overall patient experience, but we will also retain actionable data that additional diabetes studies can learn from and build upon.”
