Interpreting Health Events in Big Data Using Qualitative Traditions

Abstract

The training of artificial intelligence requires integrating real-world context and mathematical computations. To achieve efficacious smart health artificial intelligence, contextual clinical knowledge serving as ground truth is required. Qualitative methods are well-suited to lend consistent and valid ground truth. In this methods article, we illustrate the use of qualitative descriptive methods for providing ground truth when training an intelligent agent to detect Restless Leg Syndrome. We show how one interdisciplinary, inter-methodological research team used both sensor-based data and the participant’s description of their experience with an episode of Restless Leg Syndrome for training the intelligent agent. We make the case for clinicians with qualitative research expertise to be included at the design table to ensure optimal efficacy of smart health artificial intelligence and a positive end-user experience.

Smart moves for an aging population

“…Conceptualized in various ways, unobtrusive smart home technology takes on many forms in the minds of its developers with almost every aspect of life becoming a measurable observation datapoint. 10,11 With an integrated smart home health monitoring care model, access to healthcare becomes easier than ever, pandemic exposure risks can be reduced, and care plans can become even more targeted to older adults' individual needs.…”