Segmenting Clinicians’ Usage Patterns of a Digital Health Tool in Resource-Limited Settings: Clickstream Data Analysis and Survey Study (Preprint)

Abstract

BACKGROUND Digital health tools allow clinicians to keep up with the expanding evidence base and to provide safer and more accurate care. However, even when cost is removed as a barrier, digital health tools require active, iterative implementation based on a nuanced understanding of the diverse needs of the health care workforce. OBJECTIVE To maximize the impact of a digital health tool, we aimed to understand clinicians’ usage patterns. Here, we present our method for segmenting clinicians based on their online behaviors. METHODS We collected 12 months of clickstream data (a record of users’ clicks within the tool) as well as repeated surveys. Our program collaborates with a digital tool, UpToDate, to facilitate free subscriptions to clinicians serving vulnerable populations globally. We enrolled 1,681 clinicians from 75 countries who applied to our program over a 9-week period. We calculated the total number of sessions, time spent online, type of activity (navigating, reading, or account management), calendar period of use, percent of days active on the site, and minutes of use per active day. We defined behavioral segments based on the distributions of these statistics. RESULTS A little more than half of clinicians (54%) used UpToDate for essentially the full year. On days when users logged on, they spent a median of 4.4 minutes on the site and an average of 71% of their time reading medical content. Based on period of use and minutes online, we defined five behavioral segments of users: short-term, light users (25%); short-term, heavy users (15%); long-term, heavy users (24%); long-term, light users (22%); and never-users (15%). CONCLUSIONS We believe these new behavioral segments can help inform the implementation of digital health tools, identify users who may need assistance, tailor training and messaging for users, and support research on digital health efforts. Methods combining clickstream with demographic and survey data have the potential to inform global health implementation. Our forthcoming analysis will use these methods to better elucidate what drives use.