Delve Health and UW Medicine are announcing a collaboration to provide new insights into endemic Type 2 Diabetes research, through artificial intelligence and machine learning (i.e., AI/ML) and remote data capture via Delve Health’s digital healthcare platform.
Delve Health’s Clinical StudyPal, a mobile and web-based platform that enables decentralized clinical trial research and remote patient monitoring, has been configured to capture patient data, 24-hours a day, through a wearable device (i.e., smart watch), procured and delivered via Delve Health’s extensive network of services. The app will not only gather quality data, such as the collection of the patient’s heart rate at 15 second intervals, activity level and SpO2 levels at those same intervals—simultaneously. Delve Health’s digital health solution will monitor, track, analyze and report the patient’s data analytics to the clinical study staff team.
“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 & Founder, Delve Health.  He continued, “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 (RWE) 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.”
The UW Medicine researchers hope to use AI to identify factors that promote and preserve wellbeing, an approach to health called salutogenesis from the Latin salus (meaning health) and the Greek genesis (meaning origin).
“Our NIH-funded Bridge2AI project called Artificial Intelligence Ready Equitable Atlas for Diabetes Insight (AI-READI; award project number 1OT2OD032644-01) 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,” said Dr. Aaron Lee, an associate professor in Ophthalmology at the University of Washington School of Medicine. “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.”
UW Medicine’s approach to this novel clinical trial is to collect a cross-sectional dataset of more than 4,000 people across the United States, with dual-balancing for self-reported race/ethnicity (e.g., White, Black, Asian-American and Hispanic) and four stages of diabetes severity (e.g., no diabetes, lifestyle controlled, oral medication controlled, and insulin dependent). Building balanced training datasets is critical for the development of unbiased ML models. Thus, rather than targeting the demographic distribution of the U.S. population, we intentionally will recruit equal numbers of four racial/ethnic groups. The same rationale applies for balancing diabetic severity.
Due to the large number of patient participants volunteering for this study, and the goal of equal numbers, patient recruitment will be key. Delve Health’s Clinical StudyPal platform will help decentralize the study, allowing UW Medicine to recruit patients from all over the United States, regardless of a patient’s geographical location—also allowing historically underrepresented patient populations access to participate.
