Dataset Information

Mobile phone-based pattern recognition and data analysis for patients with type 1 diabetes.

ABSTRACT: Persons with type 1 diabetes who use electronic self-help tools, most commonly blood glucose meters, record a large amount of data about their personal condition. Mobile phones are powerful and ubiquitous computers that have a potential for data analysis, and the purpose of this study is to explore how self-gathered data can help users improve their blood glucose management.Thirty patients with insulin-regulated type 1 diabetes were equipped with a mobile phone application for 3-6 months, recording blood glucose, insulin, dietary information, physical activity, and disease symptoms. The data were analyzed in terms of usage of the different modules and which data processing and visualization tools could be constructed to support the use of these data.Eighteen patients (denoted "adopters") recorded complete data for over 80 consecutive days, up to 247 days. Among those who withdrew or did not use the application extensively, the most common reasons given were outdated or difficult-to-use phone. Data analysis using period finding and scale-space trends was found to yield significant patterns for most adopters. Pattern recognition methods to predict low or high blood glucose were found to be performing poorly.Minimally intrusive mobile applications enable users with type 1 diabetes to record data that can provide data-driven feedback to the user, potentially providing relevant insight into their disease.

SUBMITTER: Skrovseth SO

PROVIDER: S-EPMC3521145 | biostudies-other | 2012 Dec

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Mobile phone-based pattern recognition and data analysis for patients with type 1 diabetes.

Skrøvseth Stein Olav SO Årsand Eirik E Godtliebsen Fred F Hartvigsen Gunnar G

Diabetes technology & therapeutics 20121004 12

<h4>Background</h4>Persons with type 1 diabetes who use electronic self-help tools, most commonly blood glucose meters, record a large amount of data about their personal condition. Mobile phones are powerful and ubiquitous computers that have a potential for data analysis, and the purpose of this study is to explore how self-gathered data can help users improve their blood glucose management.<h4>Subjects and methods</h4>Thirty patients with insulin-regulated type 1 diabetes were equipped with a ...[more]

PMID: 23035775

Similar Datasets

Project description:BACKGROUND:Filipino Americans have a high prevalence of obesity, type 2 diabetes (T2D), and cardiovascular disease compared with other Asian American subgroups and non-Hispanic whites. Mobile health (mHealth) weight loss interventions can reduce chronic disease risks, but these are untested in Filipino Americans with T2D. OBJECTIVE:The objective of this study was to assess feasibility and potential efficacy of a pilot, randomized controlled trial (RCT) of a culturally adapted mHealth weight loss lifestyle intervention (Pilipino Americans Go4Health [PilAm Go4Health]) for overweight Filipino Americans with T2D. METHODS:This was a 2-arm pilot RCT of the 3-month PilAm Go4Health intervention (phase 1) with an active waitlist control and 3-month follow-up (phase 2). The waitlist control received the PilAm Go4Health in phase 2, whereas the intervention group transitioned to the 3-month follow-up. PilAm Go4Health incorporated a Fitbit accelerometer, mobile app with diary for health behavior tracking (steps, food/calories, and weight), and social media (Facebook) for virtual social support, including 7 in-person monthly meetings. Filipino American adults ?18 years with T2D were recruited from Northern California. Feasibility was measured by rates of recruitment, engagement, and retention. Multilevel regression analyses assessed within and between group differences for the secondary outcome of percent weight change and other outcomes of weight (kg), body mass index (BMI), waist circumference, fasting plasma glucose, HbA1c, and steps. RESULTS:A total of 45 Filipino American adults were enrolled and randomized. Mean age was 58 (SD 10) years, 62% (28/45) were women, and mean BMI was 30.1 (SD 4.6). Participant retention and study completion were 100%, with both the intervention and waitlist group achieving near-perfect attendance at all 7 intervention office visits. Groups receiving the PilAm Go4Health in phase 1 (intervention group) and phase 2 (waitlist group) had significantly greater weight loss, -2.6% (-3.9 to -1.4) and -3.3% (-1.8 to -4.8), respectively, compared with the nonintervention group, resulting in a moderate to small effect sizes (d=0.53 and 0.37, respectively). In phase 1, 18% (4/22) of the intervention group achieved a 5% weight loss, whereas 82% (18/22) maintained or lost 2% to 5% of their weight and continued to maintain this weight loss in the 3-month follow-up. Other health outcomes, including waist circumference, BMI, and step counts, improved when each arm received the PilAm Go4Health, but the fasting glucose and HbA1c outcomes were mixed. CONCLUSIONS:The PilAm Go4Health was feasible and demonstrated potential efficacy in reducing diabetes risks in overweight Filipino Americans with T2D. This study supports the use of mHealth and other promising intervention strategies to reduce obesity and diabetes risks in Filipino Americans. Further testing in a full-scale RCT is warranted. These findings may support intervention translation to reduce diabetes risks in other at-risk diverse populations. TRIAL REGISTRATION:Clinicaltrials.gov NCT02290184; https://clinicaltrials.gov/ct2/show/NCT02290184 (Archived by WebCite at http://www.webcitation.org/6vDfrvIPp).

Dataset Information

Mobile phone-based pattern recognition and data analysis for patients with type 1 diabetes.

Publications

Mobile phone-based pattern recognition and data analysis for patients with type 1 diabetes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets