Miriam W. Van Ittersum

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.

Introduction The Work Well Functional Capacity Evaluation (WW FCE) is a two-day performance based test consisting of several work-related activities. Three lifting and carrying test items may be performed on both days. The objective of this study was to assess the need for repeated testing of these items in subjects with early osteoarthritis of the hip and/or the knee and to analyze sources of variation between the 2 days of measurement. Methods A standardized WW FCE protocol was applied, including repeated testing of lifting low, lifting overhead and carrying. Differences and associations between the 2 days were calculated using paired samples t-tests, intraclass correlation coefficients (ICC) and limits of agreement (LoA). Possible sources of individual variation between the 2 days were identified by Wilcoxon signed ranks tests. Pearson correlation coefficients were calculated for differences in performances between days and differences in possible sources of variation between days. Results Seventy-nine subjects participated in this study, their mean (SD) age was 56.6 (4.8) years, median (min–max) WOMAC (Western Ontario and McMaster Universities) index scores for pain, stiffness and physical function were 5 (0–17), 3 (0–7) and 14 (0–49), respectively. Median (min–max) SF36 physical function was 75 (5–95), and SF36 pain score was 67 (12–76). Mean performance differences ranged from −0.2 to −0.8 kg (P > 0.05). ICC’s ranged from 0.75 (lifting overhead) to 0.88 (lifting low). LoA were: lifting low 8.0 kg; lifting overhead 6.5 kg; carrying 9.0 kg. Pearson’s correlations were low and non-significant. Conclusions All three tests show acceptable two-day consistency. WW FCE testing on two consecutive days is not necessary for groups of subjects with early osteoarthritis. Individual sources of variation could not be identified.