Enhancing self-management in type 1 diabetes with wearables and deep learning.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhu T
PROVIDER: S-EPMC9237131 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:AimsMeasurement tools to evaluate self-management behavior are useful for diabetes research and clinical practice. The Diabetes Self-Management Questionnaire (DSMQ) was introduced in 2013 and has become a widely used tool. This article presents a revised and updated version, DSMQ-R, and evaluates its properties in assessing self-management practices in type 1 diabetes (T1D) and type 2 diabetes (T2D).MethodsThe DSMQ-R is a multidimensional questionnaire with 27 items regarding essential self-management practices for T1D and T2D (including diabetes-adjusted eating, glucose testing/monitoring, medication taking, physical activity and cooperation with the diabetes team). For the revised form, the original items were partially amended and the wording was updated; eleven items were newly added. The tool was applied as part of health-related surveys in five clinical studies (two cross-sectional, three prospective) including a total of 1,447 people with T1D and T2D. Using this data base, clinimetric properties were rigorously tested.ResultsThe analyses showed high internal and retest reliability coefficients for the total scale and moderate to high coefficients for the subscales. Reliability coefficients for scales including the new items were consistently higher. Correlations with convergent criteria and related variables supported validity. Responsiveness was supported by significant short to medium term changes in prospective studies. Significant associations with glycemic outcomes were observed for DSMQ-R-assessed medication taking, glucose monitoring and eating behaviors.ConclusionsThe results support good clinimetric properties of the DSMQ-R. The tool can be useful for research and clinical practice and may facilitate the identification of improvable self-management practices in individuals.
| S-EPMC10012087 | biostudies-literature
Project description:BackgroundAlthough supported self-management is a well-recognised part of chronic disease management, it has not been routinely used as part of healthcare for adults with a learning disability. We developed an intervention for adults with a mild or moderate learning disability and type 2 diabetes, building on the principles of supported self-management with reasonable adjustments made for the target population.MethodsIn five steps, we:Clarified the principles of supported self-management as reported in the published literatureIdentified the barriers to effective self-management of type 2 diabetes in adults with a learning disabilityReviewed existing materials that aim to support self-management of diabetes for people with a learning disabilitySynthesised the outputs from the first three phases and identified elements of supported self-management that were (a) most relevant to the needs of our target population and (b) most likely to be acceptable and useful to themImplemented and field tested the intervention.ResultsThe final intervention had four standardised components: (1) establishing the participant's daily routines and lifestyle, (2) identifying supporters and their roles, (3) using this information to inform setting realistic goals and providing materials to the patient and supporter to help them be achieved and (4) monitoring progress against goals.Of 41 people randomised in a feasibility RCT, thirty five (85%) completed the intervention sessions, with over three quarters of all participants (78%) attending at least three sessions.Twenty-three out of 40 (58%) participants were deemed to be very engaged with the sessions and 12/40 (30%) with the materials; 30 (73%) participants had another person present with them during at least one of their sessions; 15/41 (37%) were reported to have a very engaged main supporter, and 18/41 (44%) had a different person who was not their main supporter but who was engaged in the intervention implementation.ConclusionsThe intervention was feasible to deliver and, as judged by participation and engagement, acceptable to participants and those who supported them.Trial registrationCurrent Controlled Trials ISRCTN41897033 (registered 21/01/2013).
| S-EPMC5975532 | biostudies-literature
Project description:BackgroundIt has been established that careful diabetes self-management is essential in avoiding chronic complications that compromise health. Disciplined diet control and regular exercise are the keys for the type 2 diabetes self-management. An ability to maintain one's blood glucose at a relatively flat level, not fluctuating wildly with meals and hypoglycemic medical intervention, would be the goal for self-management. Hemoglobin A1c (HbA1c or simply A1c) is a measure of a long-term blood plasma glucose average, a reliable index to reflect one's diabetic condition. A simple regimen that could reduce the elevated A1c levels without altering much of type 2 diabetic patients' daily routine denotes a successful self-management strategy.MethodsA relatively simple model that relates the food impact on blood glucose excursions for type 2 diabetes was studied. Meal is treated as a bolus injection of glucose. Medical intervention of hypoglycaemic drug or injection, if any, is lumped with secreted insulin as a damping factor. Lunch was used for test meals. The recovery period of a blood glucose excursion returning to the pre-prandial level, the maximal reach, and the area under the excursion curve were used to characterize one's ability to regulate glucose metabolism. A case study is presented here to illustrate the possibility of devising an individual-based self-management regimen.ResultsResults of the lunch study for a type 2 diabetic subject indicate that the recovery time of the post-prandial blood glucose level can be adjusted to 4 hours, which is comparable to the typical time interval for non-diabetics: 3 to 4 hours. A moderate lifestyle adjustment of light supper coupled with morning swimming of 20 laps in a 25 m pool for 40 minutes enabled the subject to reduce his A1c level from 6.7 to 6.0 in six months and to maintain this level for the subsequent six months.ConclusionsThe preliminary result of this case study is encouraging. An individual life-style adjustment can be structured from the extracted characteristics of the post-prandial blood glucose excursions. Additional studies are certainly required to draw general applicable guidelines for lifestyle adjustments of type 2 diabetic patients.
| S-EPMC546416 | biostudies-literature
Project description:BackgroundFor adolescents living with type 1 diabetes (T1D), completion of multiple daily self-management tasks, such as monitoring blood glucose and administering insulin, can be challenging because of psychosocial and contextual barriers. These barriers are hard to assess accurately and specifically by using traditional retrospective recall. Ecological momentary assessment (EMA) uses mobile technologies to assess the contexts, subjective experiences, and psychosocial processes that surround self-management decision-making in daily life. However, the rich data generated via EMA have not been frequently examined in T1D or integrated with machine learning analytic approaches.ObjectiveThe goal of this study is to develop a machine learning algorithm to predict the risk of missed self-management in young adults with T1D. To achieve this goal, we train and compare a number of machine learning models through a learned filtering architecture to explore the extent to which EMA data were associated with the completion of two self-management behaviors: mealtime self-monitoring of blood glucose (SMBG) and insulin administration.MethodsWe analyzed data from a randomized controlled pilot study using machine learning-based filtering architecture to investigate whether novel information related to contextual, psychosocial, and time-related factors (ie, time of day) relate to self-management. We combined EMA-collected contextual and insulin variables via the MyDay mobile app with Bluetooth blood glucose data to construct machine learning classifiers that predicted the 2 self-management behaviors of interest.ResultsWith 1231 day-level SMBG frequency counts for 45 participants, demographic variables and time-related variables were able to predict whether daily SMBG was below the clinical threshold of 4 times a day. Using the 1869 data points derived from app-based EMA data of 31 participants, our learned filtering architecture method was able to infer nonadherence events with high accuracy and precision. Although the recall score is low, there is high confidence that the nonadherence events identified by the model are truly nonadherent.ConclusionsCombining EMA data with machine learning methods showed promise in the relationship with risk for nonadherence. The next steps include collecting larger data sets that would more effectively power a classifier that can be deployed to infer individual behavior. Improvements in individual self-management insights, behavioral risk predictions, enhanced clinical decision-making, and just-in-time patient support in diabetes could result from this type of approach.
| S-EPMC8931646 | biostudies-literature
Project description:AimsWe studied the association between fear of hypoglycaemia (FoH) and various diabetes self-management practices.MethodsData from 798 individuals with type 1 diabetes participating in the FinnDiane Study were included. Self-reported questionnaires were used to assess FoH and self-management practices (e.g. dietary intake, insulin administration, physical activity). For glycaemic control, we used both the latest HbA1c measurements and the serial HbA1c measurements from the medical files. Factor analysis was used to reveal underlying constructs within the food frequency section of the diet questionnaire.ResultsIn all, 44% and 63% of men and women reported FoH, respectively. In men, FoH was associated with higher mean serial HbA1c levels, higher number of reported self-monitoring of blood glucose (SMBG), higher carbohydrate intake, and lower scores in the "high-fat" factor. In women, FoH was associated with a higher number of reported SMBGs and higher energy intake. No difference was observed in physical activity and insulin administration.ConclusionsFoH has various implications for the self-management of diabetes. More studies are however needed to assess on one hand the association between FoH and diabetes self-management, and on the other hand, FoH and its long term consequences, such as the emergence of diabetic complications and mortality.
| S-EPMC5680451 | biostudies-literature
Project description:While the advanced diagnostic tools and healthcare management protocols have been struggling to contain the COVID-19 pandemic, the spread of the contagious viral pathogen before the symptom onset acted as the Achilles' heel. Although reverse transcription-polymerase chain reaction (RT-PCR) has been widely used for COVID-19 diagnosis, they are hardly administered before any visible symptom, which provokes rapid transmission. This study proposes PCovNet, a Long Short-term Memory Variational Autoencoder (LSTM-VAE)-based anomaly detection framework, to detect COVID-19 infection in the presymptomatic stage from the Resting Heart Rate (RHR) derived from the wearable devices, i.e., smartwatch or fitness tracker. The framework was trained and evaluated in two configurations on a publicly available wearable device dataset consisting of 25 COVID-positive individuals in the span of four months including their COVID-19 infection phase. The first configuration of the framework detected RHR abnormality with average Precision, Recall, and F-beta scores of 0.946, 0.234, and 0.918, respectively. However, the second configuration detected aberrant RHR in 100% of the subjects (25 out of 25) during the infectious period. Moreover, 80% of the subjects (20 out of 25) were detected during the presymptomatic stage. These findings prove the feasibility of using wearable devices with such a deep learning framework as a secondary diagnosis tool to circumvent the presymptomatic COVID-19 detection problem.
| S-EPMC9170596 | biostudies-literature
Project description:ObjectivesSignificant problems with patients engaging with diabetes self-management education (DSME) exist. The role of healthcare professionals (HCPs) has been highlighted, with a lack of enthusiasm, inadequate information provision and poor promotion of available programmes all cited as affecting patients' decisions to attend. However, little is known about HCPs' views towards DSME. This study investigates the views of HCPs towards self-management generally and self-management in the context of DSME more specifically.DesignA qualitative study using semi-structured interviews to investigate HCPs views of type 2 diabetes self-management and DSME. Data were analysed thematically and emergent themes were mapped on to the constructs of Normalisation Process Theory (NPT).SettingTwo boroughs in London, UK.ParticipantsSampling was purposive to recruit a diverse range of professional roles including GPs, practice nurses, diabetes specialist nurses, healthcare assistants (HCAs), receptionists and commissioners of care.ResultsInterviews were conducted with 22 participants. The NPT analysis demonstrated that while a self-management approach to diabetes care was viewed by HCPs as necessary and, in principle, valuable, the reality is much more complex. HCPs expressed ambivalence about pushing certain patients into self-managing, preferring to retain responsibility. There was a lack of awareness among HCPs about the content of DSME and benefits to patients. Commitment to and engagement with DSME was tempered by concerns about suitability for some patients. There was little evidence of communication between providers of group-based DSME and HCPs or of HCPs engaging in work to follow-up non-attenders.ConclusionsHCPs have concerns about the appropriateness of DSME for all patients and discussed challenges to engaging with and performing the tasks required to embed the approach within practice. DSME, as a means of supporting self-management, was considered important in theory, but there was little evidence of HCPs seeing their role as extending beyond providing referrals.
| S-EPMC6661639 | biostudies-literature
Project description:BackgroundBeing highly self-efficacious is a key factor in successful chronic disease self-management. In the context of measuring self-efficacy in type 2 diabetes management, the Diabetes Management Self-Efficacy Scale (DMSES) is the most widely used scale. The aim of this study was to adapt the English version of the scale to Italian and to evaluate the psychometric properties of the Italian version of DMSES in type 2 diabetes (IT-DMSES).MethodsWe conducted a cross-sectional study of people with type 2 diabetes attending the Endocrine-Metabolic Disease Care Unit of the Internal Medicine Department of San Marino State Hospital between October 2016 and February 2017. Patients completed a socio-demographic and clinical data form, the IT-DMSES and 3 self-report questionnaires measuring diabetes distress (PAID-5), psychological well-being (WHO-5) and depression (PHQ-9). Psychometric testing included construct validity (principal component analysis), internal consistency (Cronbach's α coefficient) and convergent/discriminant validity (Spearman's correlation coefficient). Decision tree analysis was performed to classify patients into homogeneous subgroups of self-efficacy based on their demographic and clinical characteristics.ResultsParticipants were 110 males and 55 females, mean age of 65.2 years (SD ± 9), 56.9% had been diagnosed for 1-15 years, 63% had HbA1c level > 53 mmol/mol. Two main factors underlain the construct of self-efficacy in diabetes management: 'Disease Management' and "Lifestyles Management". Disease Management had a good reliability (α = .849) and Lifestyle Management had an excellent reliability (α = .902) indicating that the instrument is internally consistent. A negative and weak correlation was found between Lifestyle management, PAID-5 (r = - 0.258, p = < 0.01) and PHQ-9 (r = - 0.274, p = < 0.01) and a positive one with WHO-5 (r = 0.325, p < 0.01) supporting convergent validity. Disease management was uncorrelated with PAID-5 (r = - 0.142, p = 0.083), PHQ-9 (r = - 0.145, p = 0.076) and weekly correlated with WHO-5 (r = 0.170, p = 0.037) confirming discriminant validity. Higher levels of self-efficacy in lifestyle management were found in patients diagnosed for at least 1 year up to 15 years and aged > 65 years and the poorest self-efficacy was found in males < 65 years.ConclusionsResults support the validity and reliability of IT-DMSES. The scale can be used in research and clinical practice to monitor type 2 diabetes self-management over time.
| S-EPMC5914030 | biostudies-literature
Project description:Purpose To describe the impact of family functioning on the self-management of type 2 diabetes (T2DM) and depression in a subsample of women who completed a randomized clinical trial using vitamin D3 (5000 or 50,000 IUs weekly) for depression treatment. Background Women are at higher risk for increased severity of T2DM when experiencing depression. Methods Narrative inquiry was used. A semi-structured interview was conducted to understand helpful strategies and barriers in managing T2DM and depression. In addition, women were asked their meaning of family quality of life (FQOL). Results Twenty-one women participated after completion of the six-month final visit in the randomized clinical trial. The mean age was 55.2 years. Participants were 24% Hispanic, 48% African-American, and 52% Caucasian. The major themes generated related to family issues that impacted their self-management, yet participants did not want to "bring fault" to their families. Three themes emerged: (a) experience of family hardships-"it's been hard for me," (b) lack of disclosure to family about being depressed-"no point in talking to them," and (c) the need for connectedness with family and others-"the way it used to be… close as a family." Conclusion Family-centered approaches could address barriers to self-management. A "family lens" for practice and research may improve health outcomes.
| S-EPMC6107345 | biostudies-other
Project description:BackgroundThe number of type 2 diabetes mellitus (T2DM) patients and related treatment costs are rapidly increasing. Consequentially, more cost-effective and efficient strategies for the treatment of T2DM are needed. One such strategy is improving patients' self-management. As patients are more and more expected to self-manage their disease, it is important to provide them with suitable self-management support. This way, success of self-management will increase and complications and related costs of T2DM can be reduced. Currently, self-management support is developed mainly from the perspective of health professionals and caregivers, rather than patients. This research focused on gaining a better understanding of patients' perspectives on self-management and support.MethodsSemi-structured interviews, preceded by preparatory assignments, were conducted with ten patients with T2DM treated in Dutch primary care.ResultsWe found that patients experience 'active' self-management when recently diagnosed. As time progresses and no problems occur, patients do not experience their disease-related behaviour as self-management. Diabetes has 'just' become part of their daily life, now including new routines taking diabetes into account.ConclusionsWith this knowledge, support solutions can be designed and implemented that better fit the needs, preferences and abilities of patients with T2DM.
| S-EPMC6714441 | biostudies-literature