Precision health using wearables

Postdoctoral Researcher & NIH Fellow – Snyder Lab – Stanford Genetics. Andrew completed his doctorate in Human Genetics at Vanderbilt University focusing on host-microbiome assembly across species by establishing the framework of phylosymbiosis and across ethnicities as a mediation target for health disparities. Over five years in the Snyder lab has cultivated expertise in study design, high throughput wet-lab and computational processing, advanced analytical methods for multiomics and wearables, mentoring / teaching Stanford Grant Writing Academy courses, and is a project leader for four multiomic human-subjects studies: 

1. Fitbit/Google & Pac12 Wearables Collaboration – Project Lead: https://snyderlabs.stanford.edu/pac12/
2. Phase I (N=6,171) & Phase II (N=5,608) COVID-19 Wearables – Co-Lead: https://innovations.stanford.edu/wearables/
3. Multiomic Antarctica Expedition – Project Lead: https://snyderlabs.stanford.edu/antarctica/
4. iPOP – Microbiome Lead: https://med.stanford.edu/snyderlab/ipop.html

The COVID-19 pandemic led us to develop algorithms for infection prediction and a real-time alerting system (Phase I: N=6,171; Nature Biomedical Engineering PMC9020268) & (Phase II: N=5,608; Nature Medicine PMID34845389), but these studies were limited in diversity, regular testing schema, and surveyed lifestyle predictors. In a 2021-2023 collaboration with Fitbit/Google and the PAC12 Sports Conference we provided Fitbit smartwatches and collected wearable data and surveys from 761 student athletes for up to two years. This seminar will examine existing algorithms as well as novel anomaly detection and machine learning approaches on 121 COVID-19 infections and 458 other illnesses, while controlling for effects of ~70k periods of exercise, ~2k weeks of significant travel, ~7k weeks annotated with 10 symptoms, ~74k nightly sleep profiles with HRV, as well as sports activity and living situation.

 

Zeinab is an algorithm research scientist with a focus on using consumer technologies to empower people to manage and improve their health. At Google, Zeinab works on algorithm developments and clinical studies using wearables for illness detection and monitoring. 

Zeinab obtained her Ph.D. in Biomedical Engineering from City University of New York. She has spent much of her career in the intersection of health, biological signal processing and machine learning.

Wearable devices can provide insight on health and well-being using longitudinal physiological signals. We report on the prospective performance of a consumer wearable physiology-based respiratory infection detection algorithm. The system used resting heart rate, respiratory rate and heart rate variability measures during the sleeping period to predict the presence of COVID-19 or other respiratory infections. In a cohort of 559 participants from January 6th to July 20th 2022, 31 instances of COVID-19 infection were confirmed by polymerase chain reaction (PCR) testing, 14 instances of COVID-19 confirmed by home test and in total 80 instances of respiratory virus (COVID-19 or other respiratory viruses confirmed with PCR or home test) were observed. For the 31 confirmed cases of COVID-19 infection, 28 received a positive alert within 8 days prior to the PCR test. For the larger set of confirmed respiratory infections (i.e., COVID-19 or other respiratory infections using PCR or home test), 63 received a positive alert within the 8 day window. Across all the cases, the estimated false positive rate on a prediction per day basis was 2% and positive predictive value ranged from 4% to 10% on this specific population with an observed incidence rate of 198 cases per week per 100k. Detailed examination of questionnaires filled out after receiving an alert revealed physical or emotional stress events such as intense exercise, poor sleep, stress or excessive alcohol consumption could result in a false positive. Thus, the real-time alerting system provides advance warning on respiratory viral infections as well as other physical or emotional stress events that could lead to physiological signal changes. This study shows the potential of wearables with embedded alerting systems to provide information on wellness measures. Link to paper