Characterizing Lived Experiences of Highly Vulnerable Populations Through COVID-19

• Activity Number: 41 - Storytelling on COVID-19 Impact Using Experts' Prior Knowledge and Data from Social Media, Official Clinical Data, Digital Phenotype from Smartphones' Raw Sensor Data, and Emergency Departments
• Type: Invited
• Date/Time: Sunday, August 8, 2021 : 3:30 PM to 5:20 PM
• Sponsor: International Society for Bayesian Analysis (ISBA)
• Author(s): Jukka-Pekka Onnela*
• Companies: Harvard University
• Keywords: digital phenotyping; smartphone; Gaussian processes; high-dimensional data; spatial data; imputation

Abstract

The COVID-19 outbreak has affected lives and taken lives everywhere in the world. The pandemic has had an outsize impact on highly vulnerable populations, but its effects on people with serious illness has received relatively little attention. Smartphone-based digital phenotyping refers to the collection and analysis of raw sensor data collected from subjects on their smartphones. Before the pandemic emerged, we had several ongoing digital phenotyping studies in highly vulnerable populations: adults with amyotrophic lateral sclerosis (ALS), a nervous system disease that weakens muscles and impacts physical function; adults with glioblastoma, the most common primary brain tumor; and adults and adolescents who have presented with suicidal thinking or recent suicide attempt. Use of such temporally dense high-dimensional data, when combined with appropriate statistical methods, enables us to understand the lived experiences of these individuals before, during, and after the pandemic, making it possible to tell their stories, at the individual level, during this exceptional time.