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.
The objective of this study was to assess relationships between children's physical environment and afterschool leisure time physical activity (PA) and active transport. Methods: Children aged 10-12 years participated in a 7-day accelerometer and Global Positioning Systems (GPS) protocol. Afterschool leisure time PA and active transport were identified based on locationand speed-algorithms based on accelerometer, GPS and Geospatial Information Systems (GIS) data. We operationalized children's exposure to the environment by combining home, school and the daily transport environment in individualized daily activity-spaces. Results: In total, 255 children from 20 Dutch primary schools from suburban areas provided valid data. This study showed that greenspaces and smaller distances from the children's home to school were associated with afterschool leisure time PA and walking. Greater distances between home and school, as well as pedestrian infrastructure were associated with increased cycling. Conclusion: We demonstrated associations between environments and afterschool PA within several behavioral contexts. Future studies are encouraged to target specific behavioral domains and to develop natural experiments based on interactions between several types of the environment, child characteristics and potential socio-cognitive processes. LinkedIn: https://www.linkedin.com/in/sanned/
MULTIFILE
To compare comfort‐related outcomes when wearing rigid gas permeable (RGP) contact lenses made of two different materials and using two cleaning regimes. In a double‐masked lens material cross‐over study, subjects (n = 28 who completed the study) were refitted with new lenses made from (A) Boston XO material in one eye and made from (B) ONSI‐56 material in the other eye. The lenses made from materials A and B were worn on the right eye and the left eye following the pattern AB–BA–AB (or vice versa) during the first, second, and third 5 week trial periods respectively. Miraflow cleaner (1st and 2nd period) was replaced by Boston Advance cleaner in the 3rd period. Comfort‐related outcomes were assessed by a numerical rating scale (NRS) after each period. Subjects rated six comfort‐related factors: satisfaction, sharpness of vision, end of day comfort, maximum comfortable wearing time, maximum wearing time and foreign body feeling. Additionally we obtained subjects’ preferences for type of lens and lens cleaner during an exit interview. The sessile drop method was used to measure static contact angles.
LINK
