Diabetes Management Experience and the State of Hypoglycemia: National Online Survey Study

Hypoglycemia Detection Using Hand Tremors: A Home Study in Patients with Type 1 Diabetes (Preprint)

BACKGROUND

Diabetes affects millions of people worldwide and is steadily increasing. A serious condition associated with diabetes is low glucose levels (hypoglycemia). Monitoring blood glucose is usually performed by invasive methods or intrusive devices, and these devices are currently not available to all patients with diabetes. Hand tremor is a significant symptom of hypoglycemia, as nerves and muscles are powered by blood sugar. However, to our knowledge, no validated tools or algorithms exist to monitor and detect hypoglycemic events via hand tremors.

OBJECTIVE

In this paper, we propose a noninvasive method to detect hypoglycemic events based on hand tremors using accelerometer data.

METHODS

We analyzed triaxial accelerometer data from a smart watch recorded from 33 patients with type 1 diabetes for 1 month. Time and frequency domain features were extracted from acceleration signals to explore different machine learning models to classify and differentiate between hypoglycemic and nonhypoglycemic states.

RESULTS

The mean duration of the hypoglycemic state was 27.31 (SD 5.15) minutes per day for each patient. On average, patients had 1.06 (SD 0.77) hypoglycemic events per day. The ensemble learning model based on random forest, support vector machines, and k-nearest neighbors had the best performance, with a precision of 81.5% and a recall of 78.6%. The results were validated using continuous glucose monitor readings as ground truth.

CONCLUSIONS

Our results indicate that the proposed approach can be a potential tool to detect hypoglycemia and can serve as a proactive, nonintrusive alert mechanism for hypoglycemic events.

Using mHealth applications for self-care - An integrative review on perceptions among adults with type 1 diabetes

BACKGROUND

Individually designed interventions delivered through mobile health applications (mHealth apps) may be able to effectively support diabetes self-care. Our aim was to review and synthesize available evidence in the literature regarding perception of adults with type 1 diabetes on the features of mHealth apps that help promote diabetes self-care, as well as facilitators and barriers to their use. An additional aim was to review literature on changes in patient reported outcome measures (PROMs) in the same population while using mHealth apps for diabetes self-care.

METHODS

Quantitative and qualitative studies focusing on adults aged 18 years and over with type 1 diabetes in any context were included. A systematic literature search using selected databases was conducted. Data was synthesised using narrative synthesis.

RESULTS

We found that features of mHealth apps designed to help promote and maintain diabetes self-care could be categorized into self-care data monitoring, app display, feedback & reminders, data entry, data sharing, and additional features. Factors affecting the use of mHealth apps reported in the literature were personal factors, app design or usability factors, privacy and safety factors, or socioeconomic factors. Quality of life and diabetes distress were the most commonly reported PROMs in the included studies.

CONCLUSION

We are unable to reach a conclusive result due to the heterogeneity of the included studies as well as the limited number of studies reporting on these areas among adults with type 1 diabetes. We therefore recommend further large-scale studies looking into these areas that can ultimately improve mHealth app use in type 1 diabetes self-care.

SYSTEMATIC REVIEW REGISTRATION

Prospero CRD42020157620 .