Amruta Pai

I am a Data Scientist working in Abbott Diabetes Care R&D.

I was a member of the Digital Health Labs, where I was advised by Dr. Ashutosh Sabharwal for my MS and PhD dissertation at Rice University. I was a part of the NSF PATHS-UP-ERC research team (Thrust 4) which aims at developing advanced health systems for underserved communities targeted for chronic diseases such as cardiovascular diseases and diabetes.

Email  /  Resume  /  Google Scholar  /  LinkedIn  /  Github

My research interests lie in developing data science and machine learning tools for digital health applications.

We conducted a digital health study and developed biomarkers to capture the impact of meal events and physical activity on daily glycemic control in Hispanic/Latino adults with or at risk of T2D. The findings of our study may offer the opportunity for non-pharmacologic interventions for populations facing a disproportionate burden of T2D.

Self-regulation of food intake is necessary for maintaining a healthy body weight. We leveraged extensive app-based observational food diary data to measure an individual’s calorie compensation profile in free-living conditions.Our methodology could be applied to food diaries to discover behavioral phenotypes of poor compensatory behavior toward forming an early behavioral marker for weight gain.

Longitudinal food diaries contributed by app users are a promising resource to study habitual behavior in food selection. We developed computational measures that leverage recurrence in food choices to describe the habitual component.

We capture a new dataset containing 16 participants with diverse skin tones. We demonstrate that HRVCam reduces the error in camera-based HRV metrics significantly (more than 50% reduction) for videos with dark skin and face motion.

HealthSense is an innovative platform for managing, hosting, and conducting large scale longitudinal studies that gather both behavioral and biological data, for novel bio-behavioral studies.

We developed a new algorithm, CameraHRV, for robustly extracting HRV even in low SNR such as is common with iPPG recordings