Search results

Gymmermansoog

Assessing Children's Fine Motor Skills With Sensor-Augmented Toys: Machine Learning Approach

BACKGROUND: Approximately 5%-10% of elementary school children show delayed development of fine motor skills. To address these problems, detection is required. Current assessment tools are time-consuming, require a trained supervisor, and are not motivating for children. Sensor-augmented toys and machine learning have been presented as possible solutions to address this problem.OBJECTIVE: This study examines whether sensor-augmented toys can be used to assess children's fine motor skills. The objectives were to (1) predict the outcome of the fine motor skill part of the Movement Assessment Battery for Children Second Edition (fine MABC-2) and (2) study the influence of the classification model, game, type of data, and level of difficulty of the game on the prediction.METHODS: Children in elementary school (n=95, age 7.8 [SD 0.7] years) performed the fine MABC-2 and played 2 games with a sensor-augmented toy called "Futuro Cube." The game "roadrunner" focused on speed while the game "maze" focused on precision. Each game had several levels of difficulty. While playing, both sensor and game data were collected. Four supervised machine learning classifiers were trained with these data to predict the fine MABC-2 outcome: k-nearest neighbor (KNN), logistic regression (LR), decision tree (DT), and support vector machine (SVM). First, we compared the performances of the games and classifiers. Subsequently, we compared the levels of difficulty and types of data for the classifier and game that performed best on accuracy and F1 score. For all statistical tests, we used α=.05.RESULTS: The highest achieved mean accuracy (0.76) was achieved with the DT classifier that was trained on both sensor and game data obtained from playing the easiest and the hardest level of the roadrunner game. Significant differences in performance were found in the accuracy scores between data obtained from the roadrunner and maze games (DT, P=.03; KNN, P=.01; LR, P=.02; SVM, P=.04). No significant differences in performance were found in the accuracy scores between the best performing classifier and the other 3 classifiers for both the roadrunner game (DT vs KNN, P=.42; DT vs LR, P=.35; DT vs SVM, P=.08) and the maze game (DT vs KNN, P=.15; DT vs LR, P=.62; DT vs SVM, P=.26). The accuracy of only the best performing level of difficulty (combination of the easiest and hardest level) achieved with the DT classifier trained with sensor and game data obtained from the roadrunner game was significantly better than the combination of the easiest and middle level (P=.046).CONCLUSIONS: The results of our study show that sensor-augmented toys can efficiently predict the fine MABC-2 scores for children in elementary school. Selecting the game type (focusing on speed or precision) and data type (sensor or game data) is more important for determining the performance than selecting the machine learning classifier or level of difficulty.

Step by Step

This thesis focuses on topics such as preterm birth, variation in gross motor development, factors that influence (premature) infant gross motor development, and parental beliefs and practices. By gaining insight into these topics, this thesis aims to contribute to clinical decision-making of paediatric physiotherapists together with parents, and with that shape early intervention.

Motor milestones, physical activity, overweight and cardiometabolic risk

Later achievement of infant motor milestones is related to lower levels of physical activity during childhood:

Background: The aim of this study is to investigate whether age of infant motor milestone achievement is related to levels of physical activity (PA), weight status and blood pressure at age 4–7years of age. Methods: In the Dutch GECKO (Groningen Expert Center of Kids with Obesity) Drenthe cohort, the age of achieving the motor milestone ‘walking without support’ was reported by parents. Weight status and blood pressure were assessed by trained health nurses and PA was measured using the Actigraph GT3X between age 4 and 7years. Results: Adjusted for children’s age, sex and the mother’s education level, infants who achieved walking without support at a later age, spent more time in sedentary behaviour during childhood and less time in moderate-tovigorous PA. Later motor milestones achievement was not related to higher BMI Z-score, waist circumference Zscore, diastolic or systolic blood pressure. Conclusion: The results of this study indicate that a later age of achieving motor milestone within the normal range have a weak relation to lower PA levels at later age. It is not likely that this will have consequences for weight status or blood pressure at 4–7years of age.

Infant Motor Milestones and Childhood Overweight:

Background: Poor motor skill competence may influence energy balance with childhood overweight as a result. Our aim was to investigate whether the age of motor milestone achievement has changed over the past decades and whether this change may contribute to the increasing trend observed in childhood overweight. Methods: Motor skill competence was assessed in children from the Young Netherlands Twin Register born between 1987 and 2007. Follow-up ranged from 4 up to 10 years. Weight and height were assessed at birth, 6 months, 14 months, and 2, 4, 7, and 10 years. Results: Babies born in later cohorts achieved their motor milestones ‘crawling’, ‘standing’, and ‘walkingunassisted’ later compared to babies born in earlier cohorts (N = 18,514, p <0.001). The prevalence of overweight at age 10 was higher in later cohorts (p = 0.033). The increase in overweight at age 10 was not explained by achieving motor milestones at a later age and this persisted after adjusting for gestational age, sex, and socioeconomic status. Conclusion: Comparing children born in 1987 to those born in 2007, we conclude that children nowadays achieve their motor milestones at a later age. This does not however, explain the increasing trend in childhood overweight.