Hindsight is 20/20: Retrospective Lessons for Conducting Longitudinal Wearable Sensing Studies [Best Paper Award]

Salaar Liaqat, Daniyal Liaqat, Tatiana Son, Andrea Gershon, Moshe Gabel, Robert Wu, Eyal de Lara

First International Workshop on Negative Results in Pervasive Computing, Cyberspace, March 2022



Pervasive sensing using wearables for health monitoring presents a promising and unique opportunity to widely manage illnesses and conditions. To better understand the capabilities and limitations of using wearable devices for health monitoring, systems need to be developed and studies conducted. We conducted one such study for monitoring patients with Chronic Obstructive Pulmonary Disease (COPD), in which we aim to understand the disease and predict patient outcomes. However, despite a carefully well-planned and well-conducted study that resulted in a very large dataset, some non-obvious design oversights meant the data was much less useful. We analyze the shortcomings of our study to construct lessons and concrete actions to avoid these pitfalls. We ratify these lessons by briefly discussing a second iteration of our study, in which we apply these lessons and obtain much better outcomes. Real-world sensing studies are time consuming and expensive investments, for a promising research area. By sharing our failure and proposing actionable lessons, we hope to minimize the risk for others aiming to run such studies.