Understanding Device Integrations Within Diabetes Apps: Mixed Methods Analysis of App Features and User Reviews
Bibliographic record
Abstract
Background: Diabetes management involves a large degree of data collection and self-care in order to accurately administer insulin. Several mobile apps are available that allow people to track and record various factors that influence their blood sugar levels. Existing diabetes apps offer features that enable integrations with various devices that streamline diabetes management, such as continuous glucose monitors, insulin pumps, or regular activity trackers. While this reduces the tracking burden on the users, the research highlighted several issues with diabetes apps, including issues with reliability and trustworthiness. As pumps and continuous glucose monitors are safety-critical systems-where issues can result in serious harm or fatalities-it is important to understand what issues and vulnerabilities could be introduced by relying on popular diabetes apps as an interface for interacting with such devices. Objective: As there is a lack of research examining in detail the integrations and potential suitability of apps as part of a wider self-management ecosystem, our goal was 2-fold. First, we aimed to understand the current landscape of device integrations within diabetes apps and how well they meet users' needs. Second, we identified the key issues users of the most popular apps face currently and what features are the source of these issues. Methods: Through searches in Android and iPhone app stores, we systematically identified 21 diabetes apps that offer integrations. We conducted a detailed analysis of 602 user reviews. For each review, we recorded its sentiment, features and issues, and additional contextual information provided by the review writers. We used descriptive statistics to analyze the features and issues. We also analyzed the reviews thematically to identify additional trends related to the context of use and the consequences of issues reported by the users. Results: The reviews focused on key features that users found the most important, including device integrations (n=259, 43%), tracking (n=194, 32.2%), data logging (n=86, 14.3%), and notifications (n=70, 11.6%). We found that 327 (54.3%) of the reviews were negative versus 187 (31.1%) positive and 88 (14.6%) neutral or mixed, and the majority of reviews (n=378, 62.8%) mentioned issues. The biggest issues related to device integrations included inability to connect with external devices (n=95, 25.1%), inability to store, manage, or access data (n=49, 22%), unreliable notifications and alerts (n=35, 9.2%), issues caused by or related to software updates (n=31, 8.5%), hardware issues (n=24, 6.4%), and issues with accessing the app, related services, or associated hardware (n=12, 3.2%). Conclusions: Apps for diabetes management are a useful part of self-care only if they are reliable and trustworthy, reduce burden, and increase health benefits. Our results provide a useful overview of desired features for diabetes apps alongside key issues for existing integrations and highlight the future challenges for artificial pancreas system development.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".