Objective: Digital therapeutics manage chronic diseases by leveraging structured data like blood glucose/pressure, diet, etc. Addition of free-text notes associated with this data may help patients/providers make sense of trends by tracking unique concerns, providing the benefits of deeper cognitive processing. We explored the impact of contextual annotation in a digital therapeutic on A1C.

Method and Results: Free-text note usage from 3,142 users of BlueStar® digital therapeutic was summarized using NLP techniques. 941 users (29.9%) recorded 31,443 notes. A lexicon of note content was generated from the most common words (Table 1). We tested if note usage was associated with A1C reduction in a subgroup (N = 378) with two lab A1C values. A repeated measures ANCOVA, controlling for demographics and usage, showed the highest note takers exhibiting significantly larger declines in A1C (-2.13%) compared with those who took no notes (-0.86%) or very few notes (-0.79%), F(3,357) = 3.55, p =.02.

Conclusions: A substantial subgroup used free-text notes in BlueStar reflecting a diverse range of self-management themes from nondiabetes physical/mental health issues to core diabetes concerns like BG, medication, diet, and activity. Contextual annotation was associated with greater A1C improvement, suggesting that note-taking may offer unique benefit to digital therapeutic users; future studies should address causality.

M. Dugas: None. K. Crowley: None. W. Wang: None. A.K. Iyer: Employee; Self; WellDoc, Inc. M.M. Peeples: Employee; Self; WellDoc, Inc. M. Shomali: Consultant; Self; WellDoc, Inc. G. Gao: None.

Readers may use this article as long as the work is properly cited, the use is educational and not for profit, and the work is not altered. More information is available at http://www.diabetesjournals.org/content/license.