BackgroundMobile phone use and the adoption of healthy lifestyle software apps (“health apps”) are rapidly proliferating. There is limited information on the users of health apps in terms of their social demographic and health characteristics, intentions to change, and actual health behaviors.ObjectiveThe objectives of our study were to (1) to describe the sociodemographic characteristics associated with health app use in a recent US nationally representative sample; (2) to assess the attitudinal and behavioral predictors of the use of health apps for health promotion; and (3) to examine the association between the use of health-related apps and meeting the recommended guidelines for fruit and vegetable intake and physical activity.MethodsData on users of mobile devices and health apps were analyzed from the National Cancer Institute’s 2015 Health Information National Trends Survey (HINTS), which was designed to provide nationally representative estimates for health information in the United States and is publicly available on the Internet. We used multivariable logistic regression models to assess sociodemographic predictors of mobile device and health app use and examine the associations between app use, intentions to change behavior, and actual behavioral change for fruit and vegetable consumption, physical activity, and weight loss.ResultsFrom the 3677 total HINTS respondents, older individuals (45-64 years, odds ratio, OR 0.56, 95% CI 0.47-68; 65+ years, OR 0.19, 95% CI 0.14-0.24), males (OR 0.80, 95% CI 0.66-0.94), and having degree (OR 2.83, 95% CI 2.18-3.70) or less than high school education (OR 0.43, 95% CI 0.24-0.72) were all significantly associated with a reduced likelihood of having adopted health apps. Similarly, both age and education were significant variables for predicting whether a person had adopted a mobile device, especially if that person was a college graduate (OR 3.30). Individuals with apps were significantly more likely to report intentions to improve fruit (63.8% with apps vs 58.5% without apps, P=.01) and vegetable (74.9% vs 64.3%, P<.01) consumption, physical activity (83.0% vs 65.4%, P<.01), and weight loss (83.4% vs 71.8%, P<.01). Individuals with apps were also more likely to meet recommendations for physical activity compared with those without a device or health apps (56.2% with apps vs 47.8% without apps, P<.01).ConclusionsThe main users of health apps were individuals who were younger, had more education, reported excellent health, and had a higher income. Although differences persist for gender, age, and educational attainment, many individual sociodemographic factors are becoming less potent in influencing engagement with mobile devices and health app use. App use was associated with intentions to change diet and physical activity and meeting physical activity recommendations.

Citizens are increasingly using Internet-based resources to obtain and understand health information at the point of need. The ability to locate, evaluate and use online health information may be influenced by an individual's level of health literacy and eHealth literacy. Those with advanced eHealth literacy skills may utilise more efficient online search strategies and identify higher quality health information resources. This paper describes a study which investigated the associations between health literacy, eHealth literacy and actual online health information seeking behavior. Accurately quantifying online health information seeking behavior can be difficult, which is why we integrated software into the web browser to objectively monitor online interactions, search queries and Uniform Resource Locators. We recruited 54 participants to search for information related to common health topics. We received 307 answers, of which 75.2% were correct. However, despite having adequate health and eHealth literacies, participants relied on search engine results as a guide to locating information resources. Furthermore 96.3% of participants utilised unaccredited health information to answer some questions. The findings suggest that eHealth literate individuals may not always utilise effective online searching strategies. Pearson's product-moment correlation indicated that the relationship between the health and eHealth literacy scores was not statistically significant.

The aim of this qualitative study was to explore the impact of a home-based, personalised reminiscence programme facilitated through an iPad app on people living with dementia and their family carers. Semi-structured interviews were used to collect data from 15 people living with dementia and 17 family carers from a region of the United Kingdom. The interviews were recorded, transcribed and analysed using thematic analysis. Six key themes emerged related to usability ('It's part of my life now'); revisiting the past ('Memories that are important to me'); home use ('It was homely'); impact on the person living with dementia ('It helped me find myself again'); gains and abilities ('There is still so much inside') and impact on relationships ('It's become very close'). These themes highlighted the impact of the reminiscence experience at an individual and relationship level for people living with dementia and their carers. The reminiscence experience also appeared to facilitate the development of new insights among participants that emphasised abilities and gains rather than disabilities and losses. The significance of personal memories was a core theme although this was not without its challenges, particularly if memories were distressing. The reminiscence experience was differentiated by individual roles. Carers tended to become more relationship-focused, whereas people living with dementia highlighted the significance of learning new skills. The study concluded that individual specific reminiscence supported by an iPad app can have a positive impact on people living with dementia and their carers at an individual and relationship level.

Background The exploitation of synthetic data in health care is at an early stage. Synthetic data could unlock the potential within health care datasets that are too sensitive for release. Several synthetic data generators have been developed to date; however, studies evaluating their efficacy and generalizability are scarce. Objective This work sets out to understand the difference in performance of supervised machine learning models trained on synthetic data compared with those trained on real data. Methods A total of 19 open health datasets were selected for experimental work. Synthetic data were generated using three synthetic data generators that apply classification and regression trees, parametric, and Bayesian network approaches. Real and synthetic data were used (separately) to train five supervised machine learning models: stochastic gradient descent, decision tree, k-nearest neighbors, random forest, and support vector machine. Models were tested only on real data to determine whether a model developed by training on synthetic data can used to accurately classify new, real examples. The impact of statistical disclosure control on model performance was also assessed. Results A total of 92% of models trained on synthetic data have lower accuracy than those trained on real data. Tree-based models trained on synthetic data have deviations in accuracy from models trained on real data of 0.177 (18%) to 0.193 (19%), while other models have lower deviations of 0.058 (6%) to 0.072 (7%). The winning classifier when trained and tested on real data versus models trained on synthetic data and tested on real data is the same in 26% (5/19) of cases for classification and regression tree and parametric synthetic data and in 21% (4/19) of cases for Bayesian network-generated synthetic data. Tree-based models perform best with real data and are the winning classifier in 95% (18/19) of cases. This is not the case for models trained on synthetic data. When tree-based models are not considered, the winning classifier for real and synthetic data is matched in 74% (14/19), 53% (10/19), and 68% (13/19) of cases for classification and regression tree, parametric, and Bayesian network synthetic data, respectively. Statistical disclosure control methods did not have a notable impact on data utility. Conclusions The results of this study are promising with small decreases in accuracy observed in models trained with synthetic data compared with models trained with real data, where both are tested on real data. Such deviations are expected and manageable. Tree-based classifiers have some sensitivity to synthetic data, and the underlying cause requires further investigation. This study highlights the potential of synthetic data and the need for further evaluation of their robustness. Synthetic data must ensure individual privacy and data utility are preserved in order to instill confidence in health care departments when using such data to inform policy decision-making.

Background The System Usability Scale (SUS) is a widely used scale that has been used to quantify the usability of many software and hardware products. However, the SUS was not specifically designed to evaluate mobile apps, or in particular digital health apps (DHAs). Objective The aim of this study was to examine whether the widely used SUS distribution for benchmarking (mean 68, SD 12.5) can be used to reliably assess the usability of DHAs. Methods A search of the literature was performed using the ACM Digital Library, IEEE Xplore, CORE, PubMed, and Google Scholar databases to identify SUS scores related to the usability of DHAs for meta-analysis. This study included papers that published the SUS scores of the evaluated DHAs from 2011 to 2021 to get a 10-year representation. In total, 117 SUS scores for 114 DHAs were identified. R Studio and the R programming language were used to model the DHA SUS distribution, with a 1-sample, 2-tailed t test used to compare this distribution with the standard SUS distribution. Results The mean SUS score when all the collected apps were included was 76.64 (SD 15.12); however, this distribution exhibited asymmetrical skewness (–0.52) and was not normally distributed according to Shapiro-Wilk test (P=.002). The mean SUS score for “physical activity” apps was 83.28 (SD 12.39) and drove the skewness. Hence, the mean SUS score for all collected apps excluding “physical activity” apps was 68.05 (SD 14.05). A 1-sample, 2-tailed t test indicated that this health app SUS distribution was not statistically significantly different from the standard SUS distribution (P=.98). Conclusions This study concludes that the SUS and the widely accepted benchmark of a mean SUS score of 68 (SD 12.5) are suitable for evaluating the usability of DHAs. We speculate as to why physical activity apps received higher SUS scores than expected. A template for reporting mean SUS scores to facilitate meta-analysis is proposed, together with future work that could be done to further examine the SUS benchmark scores for DHAs.