Transfering Targeted Maximum Likelihood Estimation for Causal Inference into Sports Science.

Although causal inference has shown great value in estimating effect sizes in, for instance, physics, medical studies, and economics, it is rarely used in sports science. Targeted Maximum Likelihood Estimation (TMLE) is a modern method for performing causal inference. TMLE is forgiving in the misspecification of the causal model and improves the estimation of effect sizes using machine-learning methods. We demonstrate the advantage of TMLE in sports science by comparing the calculated effect size with a Generalized Linear Model (GLM). In this study, we introduce TMLE and provide a roadmap for making causal inference and apply the roadmap along with the methods mentioned above in a simulation study and case study investigating the influence of substitutions on the physical performance of the entire soccer team (i.e., the effect size of substitutions on the total physical performance). We construct a causal model, a misspecified causal model, a simulation dataset, and an observed tracking dataset of individual players from 302 elite soccer matches. The simulation dataset results show that TMLE outperforms GLM in estimating the effect size of the substitutions on the total physical performance. Furthermore, TMLE is most robust against model misspecification in both the simulation and the tracking dataset. However, independent of the method used in the tracking dataset, it was found that substitutes increase the physical performance of the entire soccer team.

Individual differences in the temporal relationship between sleep and agitation: a single-subject study in nursing home residents with dementia experiencing sleep disturbance and agitation.

OBJECTIVES: Previous studies on the interrelationship between sleep and agitation relied on group-aggregates and so results may not be applicable to individuals. This proof-of-concept study presents the single-subject study design with time series analysis as a method to evaluate the association between sleep and agitation in individual nursing home residents using actigraphy. METHOD: To record activity, three women and two men (aged 78-89 years) wore the MotionWatch 8© (MW8) for 9 consecutive weeks. Total sleep time and agitation were derived from the MW8 data. We performed time series analysis for each individual separately. To gain insight into the experiences with the actigraphy measurements, care staff filled out an investigator-developed questionnaire on their and participants' MW8 experiences. RESULTS: A statistically significant temporal association between sleep and agitation was present in three out of five participants. More agitation was followed by more sleep for participant 1, and by less sleep for participant 4. As for participants 3 and 4, more sleep was followed by more agitation. Two-thirds of the care staff members (16/24) were positive about the use of the MW8. Acceptability of the MW8 was mixed: two residents refused to wear the MW8 thus did not participate, one participant initially experienced the MW8 as somewhat unpleasant, while four participants seemed to experience no substantial problems. CONCLUSION: A single-subject approach with time series analysis can be a valuable tool to gain insight into the temporal relationship between sleep and agitation in individual nursing home residents with dementia experiencing sleep disturbance and agitation.

Time to get personal? The impact of researchers choices on the selection of treatment targets using the experience sampling methodology.

OBJECTIVE: One of the promises of the experience sampling methodology (ESM) is that a statistical analysis of an individual's emotions, cognitions and behaviors in everyday-life could be used to identify relevant treatment targets. A requisite for clinical implementation is that outcomes of such person-specific time-series analyses are not wholly contingent on the researcher performing them. METHODS: To evaluate this, we crowdsourced the analysis of one individual patient's ESM data to 12 prominent research teams, asking them what symptom(s) they would advise the treating clinician to target in subsequent treatment. RESULTS: Variation was evident at different stages of the analysis, from preprocessing steps (e.g., variable selection, clustering, handling of missing data) to the type of statistics and rationale for selecting targets. Most teams did include a type of vector autoregressive model, examining relations between symptoms over time. Although most teams were confident their selected targets would provide useful information to the clinician, not one recommendation was similar: both the number (0-16) and nature of selected targets varied widely. CONCLUSION: This study makes transparent that the selection of treatment targets based on personalized models using ESM data is currently highly conditional on subjective analytical choices and highlights key conceptual and methodological issues that need to be addressed in moving towards clinical implementation.

The u-can-act Platform: A Tool to Study Intra-individual Processes of Early School Leaving and Its Prevention Using Multiple Informants.

We present the u-can-act platform, a tool that we developed to study the individual processes of early school leaving and the preventative actions that mentors take to steer these processes in the right direction. Early school leaving is a significant problem, particularly in vocational education, and can have severe consequences for both the individual and society. However, the prevention of early school leaving is hampered by a mismatch between research and practice: research tends to focus on identifying risk factors using group averages and cross-sectional studies, while practitioners focus on intervening in individual processes. We aim to help solve this mismatch with our project u-can-act. In this project we have developed a platform that helps to gain insight into both the individual processes that precede early school leaving as well as the actions that mentors take to prevent it. In this paper we introduce the u-can-act platform, which consists of three technology-based, reusable methodological innovations. Specifically, our innovations concern: (i) an open source web application for longitudinal personalized data-collection, (ii) an automated study protocol that optimizes adherence in a difficult target group (adolescents at risk for early school leaving), and (iii) a technologically assisted coupling between mentor and student that allows us to study dyadic interactions over time. We present performance results of our platform, including participant adherence, the behavior of the questionnaire items over time, and the way that our web application is experienced by the participants. We conclude that our innovative platform is successful in collecting multi-informant time-series data on intervention processes among students in vocational education, both for at-risk students and control students, and for their mentors. Moreover, our platform is suitable for broader applications: it can be used to study any malleable individual process including the efforts of a second individual who aims to influence this process. Because of the unique insights that the u-can-act platform is able to generate, the platform may ultimately contribute to solving the mismatch between research and practice, and to more effective interventions in individual processes.

Personalized Physical Activity Coaching: A Machine Learning Approach.

Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88-0.99, and mean F1-score = 0.90, range = 0.87-0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.

Temporal Dynamics of Health and Well-Being: A Crowdsourcing Approach to Momentary Assessments and Automated Generation of Personalized Feedback.

OBJECTIVE: Recent developments in research and mobile health enable a quantitative idiographic approach in health research. The present study investigates the potential of an electronic diary crowdsourcing study in the Netherlands for (1) large-scale automated self-assessment for individual-based health promotion and (2) enabling research at both the between-persons and within-persons level. To illustrate the latter, we examined between-persons and within-persons associations between somatic symptoms and quality of life. METHODS: A website provided the general Dutch population access to a 30-day (3 times a day) diary study assessing 43 items related to health and well-being, which gave participants personalized feedback. Associations between somatic symptoms and quality of life were examined with a linear mixed model. RESULTS: A total of 629 participants completed 28,430 assessments, with a mean (SD) of 45 (32) assessments per participant. Most participants (n = 517 [82%]) were women and 531 (84%) had high education. Almost 40% of the participants (n = 247) completed enough assessments (t = 68) to generate personalized feedback including temporal dynamics between well-being, health behavior, and emotions. Substantial between-person variability was found in the within-person association between somatic symptoms and quality of life. CONCLUSIONS: We successfully built an application for automated diary assessments and personalized feedback. The application was used by a sample of mainly highly educated women, which suggests that the potential of our intensive diary assessment method for large-scale health promotion is limited. However, a rich data set was collected that allows for group-level and idiographic analyses that can shed light on etiological processes and may contribute to the development of empirical-based health promotion solutions.

HowNutsAreTheDutch (HoeGekIsNL): A crowdsourcing study of mental symptoms and strengths.

HowNutsAreTheDutch (Dutch: HoeGekIsNL) is a national crowdsourcing study designed to investigate multiple continuous mental health dimensions in a sample from the general population (n = 12,503). Its main objective is to create an empirically based representation of mental strengths and vulnerabilities, accounting for (i) dimensionality and heterogeneity, (ii) interactivity between symptoms and strengths, and (iii) intra-individual variability. To do so, HowNutsAreTheDutch (HND) makes use of an internet platform that allows participants to (a) compare themselves to other participants via cross-sectional questionnaires and (b) to monitor themselves three times a day for 30 days with an intensive longitudinal diary study via their smartphone. These data enable for personalized feedback to participants, a study of profiles of mental strengths and weaknesses, and zooming into the fine-grained level of dynamic relationships between variables over time. Measuring both psychiatric symptomatology and mental strengths and resources enables for an investigation of their interactions, which may underlie the wide variety of observed mental states in the population. The present paper describes the applied methods and technology, and presents the sample characteristics. Copyright © 2015 John Wiley & Sons, Ltd.