Associations Between Engagement with the BitHabit Digital Lifestyle Intervention and Changes in Type 2 Diabetes Risk Factors.

Type 2 diabetes (T2D) can be prevented or delayed through a healthy lifestyle. Digital behavior change interventions (DBCIs) may offer cost-effective and scalable means to support lifestyle changes. This study investigated associations between user engagement with a habit-formation-based DBCI, the BitHabit app, and changes in T2D risk factors over 12 months in 963 participants at risk of T2D. User engagement was characterized by calculating use metrics from the BitHabit log data. User ratings were used as a subjective measure of engagement. The use metrics and user ratings were the strongest associated with improvements in diet quality. Weak positive associations were observed between the use metrics and changes in waist circumference and body mass index. No associations were found with changes in physical activity, fasting plasma glucose, or plasma glucose two hours after an oral glucose tolerance test. To conclude, increased use of the BitHabit app can have beneficial impacts on T2D risk factors, especially on diet quality.

Transformers for cardiac patient mortality risk prediction from heterogeneous electronic health records.

With over 17 million annual deaths, cardiovascular diseases (CVDs) dominate the cause of death statistics. CVDs can deteriorate the quality of life drastically and even cause sudden death, all the while inducing massive healthcare costs. This work studied state-of-the-art deep learning techniques to predict increased risk of death in CVD patients, building on the electronic health records (EHR) of over 23,000 cardiac patients. Taking into account the usefulness of the prediction for chronic disease patients, a prediction period of six months was selected. Two major transformer models that rely on learning bidirectional dependencies in sequential data, BERT and XLNet, were trained and compared. To our knowledge, the presented work is the first to apply XLNet on EHR data to predict mortality. The patient histories were formulated as time series consisting of varying types of clinical events, thus enabling the model to learn increasingly complex temporal dependencies. BERT and XLNet achieved an average area under the receiver operating characteristic curve (AUC) of 75.5% and 76.0%, respectively. XLNet surpassed BERT in recall by 9.8%, suggesting that it captures more positive cases than BERT, which is the main focus of recent research on EHRs and transformers.

The Cognitive Function at Work Questionnaire (CFWQ): A new scale for measuring cognitive complaints in occupational population.

Cognitive functioning is a relevant work and health related topic, however, validated methods to assess subjective cognitive complaints (SCC) at work are lacking. We introduce the Cognitive Function at Work Questionnaire (CFWQ) for measuring SCC in occupational settings. 1-year follow-up data of 418 employees from a Finnish public media service company was analyzed. Participants completed web-based CFWQ, cognitive tests and a broad set of questionnaires for evaluating depression, anxiety, insomnia, daytime sleepiness, burnout, stress, mental job burden, work ability, cognitive errors, and perceived health. The factor analysis yielded a model with the CFWQ subdomains: Memory, Language, Executive Function, Speed of Processing, Cognitive Control and Name Memory. The internal consistency (Cronbach's alpha = .87) and the test-retest constancy (ICC = .84) reflected good reliability. Correlation between the CFWQ and cognitive errors at work ranged from .25 to .64 indicating adequate concurrent validity. Employees with depression, insomnia and burnout symptoms had higher (p < .001) CFWQ scores than participants without these symptoms. Depression and burnout symptom severity as well as accumulation of mood, sleep, and psychosocial stressors were associated with higher CFWQ scores (p < .001 in all). The CFWQ appears psychometrically sound measure for the assessment of SCC in occupational population.

System Architecture of a European Platform for Health Policy Decision Making: MIDAS.

Background: Healthcare data is a rich yet underutilized resource due to its disconnected, heterogeneous nature. A means of connecting healthcare data and integrating it with additional open and social data in a secure way can support the monumental challenge policy-makers face in safely accessing all relevant data to assist in managing the health and wellbeing of all. The goal of this study was to develop a novel health data platform within the MIDAS (Meaningful Integration of Data Analytics and Services) project, that harnesses the potential of latent healthcare data in combination with open and social data to support evidence-based health policy decision-making in a privacy-preserving manner. Methods: The MIDAS platform was developed in an iterative and collaborative way with close involvement of academia, industry, healthcare staff and policy-makers, to solve tasks including data storage, data harmonization, data analytics and visualizations, and open and social data analytics. The platform has been piloted and tested by health departments in four European countries, each focusing on different region-specific health challenges and related data sources. Results: A novel health data platform solving the needs of Public Health decision-makers was successfully implemented within the four pilot regions connecting heterogeneous healthcare datasets and open datasets and turning large amounts of previously isolated data into actionable information allowing for evidence-based health policy-making and risk stratification through the application and visualization of advanced analytics. Conclusions: The MIDAS platform delivers a secure, effective and integrated solution to deal with health data, providing support for health policy decision-making, planning of public health activities and the implementation of the Health in All Policies approach. The platform has proven transferable, sustainable and scalable across policies, data and regions.

Internet-Based Lifestyle Intervention to Prevent Type 2 Diabetes Through Healthy Habits: Design and 6-Month Usage Results of Randomized Controlled Trial.

BACKGROUND: Type 2 diabetes can be prevented through lifestyle changes, but sustainable and scalable lifestyle interventions are still lacking. Habit-based approaches offer an opportunity to induce long-term behavior changes. OBJECTIVE: The purposes of this study were to describe an internet-based lifestyle intervention for people at risk for type 2 diabetes targeted to support formation of healthy habits and explore its user engagement during the first 6 months of a randomized controlled trial (RCT). METHODS: The app provides an online store that offers more than 400 simple and contextualized habit-forming behavioral suggestions triggered by daily life activities. Users can browse, inspect, and select them; report their performances; and reflect on their own activities. Users can also get reminders, information on other users' activities, and information on the prevention of type 2 diabetes. An unblended parallel RCT was carried out to evaluate the effectiveness of the app in comparison with routine care. User engagement is reported for the first 6 months of the trial based on the use log data of the participants, who were 18- to 70-year-old community-dwelling adults at an increased risk of type 2 diabetes. RESULTS: Of 3271 participants recruited online, 2909 were eligible to participate in the RCT. Participants were randomized using a computerized randomization system to the control group (n=971), internet-based intervention (digital, n=967), and internet-based intervention with face-to-face group coaching (F2F+digital, n=971). Mean age of control group participants was 55.0 years, digital group 55.2 years, and F2F+digital 55.2 years. The majority of participants were female, 81.1% (787/971) in the control group, 78.3% (757/967) in the digital group, and 80.7% (784/971) in the F2F+digital group. Of the participants allocated to the digital and F2F+digital groups, 99.53% (1929/1938) logged in to the app at least once, 98.55% (1901/1938) selected at least one habit, and 95.13% (1835/1938) reported at least one habit performance. The app was mostly used on a weekly basis. During the first 6 months, the number of active users on a weekly level varied from 93.05% (1795/1929) on week 1 to 51.79% (999/1929) on week 26. The daily use activity was not as high. The digital and F2F+digital groups used the app on a median of 23.0 and 24.5 days and for 79.4 and 85.1 minutes total duration, respectively. A total of 1,089,555 habit performances were reported during the first 6 months. There were no significant differences in the use metrics between the groups with regard to cumulative use metrics. CONCLUSIONS: Results demonstrate that internet-based lifestyle interventions can be delivered to large groups including community-dwelling middle-aged and older adults, many with limited experience in digital app use, without additional user training. This intermediate analysis of use behavior showed relatively good engagement, with the percentage of active weekly users remaining over 50% at 6 months. However, we do not yet know if the weekly engagement was enough to change the lifestyles of the participants. TRIAL REGISTRATION: ClinicalTrials.gov NCT03156478; https://clinicaltrials.gov/ct2/show/NCT03156478.

A Decision Support System for Diagnostics and Treatment Planning in Traumatic Brain Injury.

Traumatic brain injury (TBI) occurs when an external force causes functional or structural alterations in the brain. Clinical characteristics of TBI vary greatly from patient to patient, and a large amount of data is gathered during various phases of clinical care in these patients. It is hard for clinicians to efficiently integrate and interpret all of these data and plan interventions in a timely manner. This paper describes the technical architecture and functionality of a web-based decision support system (DSS), which not only provides advanced support for visualizing complex TBI data but also predicts a possible outcome by using a state-of-the-art Disease State Index machine-learning algorithm. The DSS is developed by using a three-layered architecture and by employing modern programming principles, software design patterns, and using robust technologies (C#, ASP.NET MVC, HTML5, JavaScript, Entity Framework, etc.). The DSS is comprised of a patient overview module, a disease-state prediction module, and an imaging module. After deploying it on a web-server, the DSS was made available to two hospitals in U.K. and Finland. Afterwards, we conducted a validation study to evaluate its usability in clinical settings. Initial results of the study indicate that especially less experience clinicians may benefit from this type of decision support software tool.