Artificial intelligence to improve efficiency of administration of gross motor function assessment in children with cerebral palsy.

AIM: To create a reduced version of the 66-item Gross Motor Function Measure (rGMFM-66) using innovative artificial intelligence methods to improve efficiency of administration of the GMFM-66. METHOD: This study was undertaken using information from an existing data set of children with cerebral palsy participating in a rehabilitation programme. Different self-learning approaches (random forest, support vector machine [SVM], and artificial neural network) were evaluated to estimate the GMFM-66 score with the fewest possible test items. Test agreements were evaluated (among other statistics) by intraclass correlation coefficients (ICCs). RESULTS: Overall, 1217 GMFM-66 assessments (509 females, mean age 8y 10mo [SD 3y 9mo]) at a single time and 187 GMFM-66 assessments and reassessments (80 females, mean age 8y 5mo [SD 3y 10mo]) after 1 year were evaluated. The model with SVM predicted the GMFM-66 scores most accurately. The ICCs of the rGMFM-66 and the full GMFM-66 were 0.997 (95% confidence interval [CI] 0.996-0.997) at a single time and 0.993 (95% CI 0.993-0.995) for the evaluation of the change over time. INTERPRETATION: The study shows that the efficiency of the full GMFM-66 assessment can be increased by using machine learning (self-learning algorithms). The presented rGMFM-66 score showed an excellent agreement with the full GMFM-66 score when applied to a single assessment and when evaluating the change over time.

Physical Activity for the Treatment of Adolescent Depression: A Systematic Review and Meta-Analysis.

Background: A noticeable proportion of adolescents with depression do not respond to guideline recommended treatment options. This systematic review and meta-analysis investigated the effectiveness of physical activity interventions as an alternative or complementary treatment for adolescents (12-18 years) with depression. The characteristics of the physical activity treatment that were most effective in reducing symptoms in adolescents with depression and the impact of methodological shortcomings in the existing research were also examined. Methods: Medline, PsycINFO, SPORTDiscus, ProQuest, and CENTRAL were searched for eligible records. Effect size estimates were pooled based on the application of a random-effects model. Potential moderation by physical activity characteristics (i.e., intensity, type, context, and time frame) and methodological features (i.e., type of control group and diagnostic tool to identify depression at baseline) was investigated by means of subgroup analyses and meta-regressions. The certainty of evidence was assessed by the Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) approach. The primary outcome was the antidepressant effect of physical activity at postintervention measurement time point. As secondary outcomes, the sustainability of effects after the end of physical activity treatment and the acceptability of physical activity treatments were assessed. Overall, 10 studies were included in the qualitative synthesis and 9 studies involving 431 patients were included in the quantitative synthesis. Results: A moderate, significant antidepressant effect of physical activity was found (Hedges' g = -0.47, 95% CI = -0.71 to -0.24). Heterogeneity was small (T2 = 0.0313, I 2 = 27%, p = 0.18). However, the certainty of evidence was downgraded to low because the included studies contained serious methodological limitations. Moderator analyses revealed that session intensity significantly moderated the antidepressant effect of physical activity. Moreover, noticeably smaller effect sizes were found in studies that used non-physical activity sham treatments as control treatments (e.g., playing board games), compared to studies that used no control group treatments. Only three studies assessed the sustainability of effects after the end of physical activity treatment. The results suggest that the antidepressant effects further increase after the end of physical activity interventions. There was no significant difference in dropout risk between the physical activity and control groups. Conclusions: This review suggests that physical activity is effective in treating depression in adolescents. Physical activity sessions should be at least moderately intense [rate of perceived exertion (RPE) between 11 and 13] to be effective. Furthermore, our results suggest that physical activity treatments are well accepted. However, the low methodological quality in included studies might have led to effect overestimation. Therefore, more studies with higher methodological quality are needed to confirm the recommendation for physical activity treatments in adolescents with depression.