YouTube Video Analytics for Health Literacy and Chronic Care Management: An Augmented Intelligence Approach to Assess Content and Understandability
Trustees Professor of Management Science and Healthcare Informatics
Heinz College of Information Systems and Public Policy
Carnegie Mellon University
Friday, Apr 16
10 – 11 am | Zoom
(send an email to email@example.com to get the Zoom link)
Video sharing social media platforms, such as YouTube, offer an effective way to deliver medical information that may be more understandable for the public, with the potential to improve health literacy, patient-physician interactions, self-care and outcomes. Few studies have identified scalable, replicable and efficient technology-enabled interventions, delivered as evidence-backed digital therapeutics, to improve the ease with which patients and health professionals can retrieve understandable medical information to manage chronic conditions. We propose an augmented intelligence approach that synthesizes annotations from domain experts, deep learning and co-training methods from machine learning and a systematic approach to extract patient education constructs on understandability and encoded medical information to develop an automated, generalizable video classification solution. We further examine the simultaneous impact of understandability and validated medical information in a video on several dimensions of collective engagement by conducting a multiple-treatment propensity score based matching approach that allows us to implement a quasi-randomization research design. While confirming common assessments of the relationship between user engagement and patient education materials, our analysis quantifies the nuanced effects using actual viewing data in the specific context of understandability of complex medical information encoded in patient education videos found on YouTube, with implications for research and practice.