BackgroundSmartphone-assisted technologies potentially provide the opportunity for large-scale, long-term, repeated monitoring of cognitive functioning at home.ObjectiveThe aim of this proof-of-principle study was to evaluate the feasibility and validity of performing cognitive tests in people at increased risk of dementia using smartphone-based technology during a 6 months follow-up period.MethodsWe used the smartphone-based app iVitality to evaluate five cognitive tests based on conventional neuropsychological tests (Memory-Word, Trail Making, Stroop, Reaction Time, and Letter-N-Back) in healthy adults. Feasibility was tested by studying adherence of all participants to perform smartphone-based cognitive tests. Validity was studied by assessing the correlation between conventional neuropsychological tests and smartphone-based cognitive tests and by studying the effect of repeated testing.ResultsWe included 151 participants (mean age in years=57.3, standard deviation=5.3). Mean adherence to assigned smartphone tests during 6 months was 60% (SD 24.7). There was moderate correlation between the firstly made smartphone-based test and the conventional test for the Stroop test and the Trail Making test with Spearman ρ=.3-.5 (P<.001). Correlation increased for both tests when comparing the conventional test with the mean score of all attempts a participant had made, with the highest correlation for Stroop panel 3 (ρ=.62, P<.001). Performance on the Stroop and the Trail Making tests improved over time suggesting a learning effect, but the scores on the Letter-N-back, the Memory-Word, and the Reaction Time tests remained stable.ConclusionsRepeated smartphone-assisted cognitive testing is feasible with reasonable adherence and moderate relative validity for the Stroop and the Trail Making tests compared with conventional neuropsychological tests. Smartphone-based cognitive testing seems promising for large-scale data-collection in population studies.

of outdoor physical play for preschoolers' social success. Moreover, the study suggests that the environment in which children play has an important effect on the adaptive nature of their play.

Background Older adults want to preserve their health and autonomy and stay in their own home environment for as long as possible. This is also of interest to policy makers who try to cope with growing staff shortages and increasing health care expenses. Ambient assisted living (AAL) technologies can support the desire for independence and aging in place. However, the implementation of these technologies is much slower than expected. This has been attributed to the lack of focus on user acceptance and user needs. Objective The aim of this study is to develop a theoretically grounded understanding of the acceptance of AAL technologies among older adults and to compare the relative importance of different acceptance factors. Methods A conceptual model of AAL acceptance was developed using the theory of planned behavior as a theoretical starting point. A web-based survey of 1296 older adults was conducted in the Netherlands to validate the theoretical model. Structural equation modeling was used to analyze the hypothesized relationships. Results Our conceptual model showed a good fit with the observed data (root mean square error of approximation 0.04; standardized root mean square residual 0.06; comparative fit index 0.93; Tucker-Lewis index 0.92) and explained 69% of the variance in intention to use. All but 2 of the hypothesized paths were significant at the P<.001 level. Overall, older adults were relatively open to the idea of using AAL technologies in the future (mean 3.34, SD 0.73). Conclusions This study contributes to a more user-centered and theoretically grounded discourse in AAL research. Understanding the underlying behavioral, normative, and control beliefs that contribute to the decision to use or reject AAL technologies helps developers to make informed design decisions based on users’ needs and concerns. These insights on acceptance factors can be valuable for the broader field of eHealth development and implementation.

A population group that is often overlooked in the recent revolution of self-tracking is the group of older people. This growing proportion of the general population is often faced with increasing health issues and discomfort. In order to come up with lifestyle advice towards the elderly, we need the ability to quantify their lifestyle, before and after an intervention. This research focuses on the task of activity recognition (AR) from accelerometer data. With that aim, we collect a substantial labelled dataset of older individuals wearing multiple devices simultaneously and performing a strict protocol of 16 activities (the GOTOV dataset, $$N=28$$ N = 28 ). Using this dataset, we trained Random Forest AR models, under varying sensor set-ups and levels of activity description granularity. The model that combines ankle and wrist accelerometers (GENEActiv) produced the best results (accuracy $$>80\%$$ > 80 % ) for 16-class classification. At the same time, when additional physiological information is used, the accuracy increased ($$>85\%$$ > 85 % ). To further investigate the role of granularity in our predictions, we developed the LARA algorithm, which uses a hierarchical ontology that captures prior biological knowledge to increase or decrease the level of activity granularity (merge classes). As a result, a 12-class model in which the different paces of walking were merged showed a performance above $$93\%$$ 93 % . Testing this 12-class model in labelled free-living pilot data, the mean balanced accuracy appeared to be reasonably high, while using the LARA algorithm, we show that a 7-class model (lying down, sitting, standing, household, walking, cycling, jumping) was optimal for accuracy and granularity. Finally, we demonstrate the use of the latter model in unlabelled free-living data from a larger lifestyle intervention study. In this paper, we make the validation data as well as the derived prediction models available to the community.

In elite sports, training schedules are becoming increasingly complex, and a large number of parameters of such schedules need to be tuned to the specific physique of a given athlete. In this paper, we describe how extensive analysis of historical data can help optimise these parameters, and how possible pitfalls of under-and overtraining in the past can be avoided in future schedules. We treat the series of exercises an athlete undergoes as a discrete sequence of attributed events, that can be aggregated in various ways, to capture the many ways in which an athlete can prepare for an important test event. We report on a cooperation with the elite speed skating team LottoNLJumbo, who have recorded detailed training data over the last 15 years. The aim of the project was to analyse this potential source of knowledge, and extract actionable and interpretable patterns that can provide input to future improvements in training. We present two alternative techniques to aggregate sequences of exercises into a combined, long-term training effect, one of which based on a sliding window, and one based on a physiological model of how the body responds to exercise. Next, we use both linear modelling and Subgroup Discovery to extract meaningful models of the data.