JMIR Publications

ABSTRACT

Background:

Complications due to Type 2 Diabetes (T2D) can be mitigated through proper self-management which can positively change health behaviours. Technological tools are available to help people living with, or at risk of developing, T2D manage their condition and such tools provide a large repository for patient-generated health data (PGHD). Analytics can provide insights about the health behaviours of people living with T2D.

Objective:

The objective of this review was to investigate what can be learned about the health behaviours of those living with, or at risk of developing, T2D through analytics from PGHD.

Methods:

A scoping review using the Arksey & O’Malley framework was conducted in which a comprehensive search of the literature was conducted by two reviewers. Three electronic databases (PubMed, IEEE, ACM) were searched using keywords associated with diabetes, behaviours, and analytics. Several rounds of screening using predetermined inclusion and exclusion criteria were conducted and studies were selected. Critical examination took place through a descriptive-analytical narrative method and data extracted from the studies was classified into thematic categories. These categories reflect the findings of this study as per our objective.

Results:

We identified 43 studies that met the inclusion criteria for this review. While 70% of the studies examined PGHD independently, 30% of the studies combined PGHD with other data sources. The majority of these studies used machine learning algorithms to perform their analysis. Themes identified through this review include 1) predicting diabetes / obesity, 2) factors that contribute to diabetes / obesity, 3) insights from social media & online forums, 4) predicting glycemia, 5) improved adherence / outcomes, 6) analysis of sedentary behaviours, 7) deriving behavioural patterns, 8) discovering clinical correlations from behaviours, and 9) developing design principles.

Conclusions:

The increased volume and availability of PGHD has the potential to derive analytical insights regarding the health behaviours of people living with T2D. From the literature, we determined that analytics can predict outcomes and identify granular behavioural patterns from PGHD. This review determined the broad range of insights that can be examined through PGHD, which constitutes a unique source of data for these applications, that would not be possible through the use of other data sources.