Intra-observer reliability of Prechtl's method for the qualitative assessment of general movements in Taiwanese infants

Deep-Learning Markerless Tracking of Infant General Movements using Standard Video Recordings

Monitoring spontaneous General Movements (GM) of infants 6-20 weeks post-term age is a reliable tool to assess the quality of neurodevelopment in early infancy. Abnormal or absent GMs are reliable prognostic indicators of whether an infant is at risk of developing neurological impairments and disorders such as cerebral palsy (CP). Therapeutic interventions are most effective at improving neuromuscular outcomes if administered in early infancy. Current clinical protocols require trained assessors to rate videos of infant movements, a time-intensive task. This work proposes a simple, inexpensive, and broadly applicable markerless pose-estimation approach for automatic infant movement tracking using conventional video recordings from handheld devices (e.g., tablets and mobile phones). We leverage the enhanced capabilities of deep-learning technology in image processing to identify 12 anatomical locations (3 per limb) in each video frame, tracking a baby's natural movement throughout the recordings. We validate the capability of resnet152 and a mobile-net-v2-1 to identify body-parts in unseen frames from a full-term male infant, using a novel automatic unsupervised approach that fuses likelihood outputs of a Kalman filter and the deep-nets. Both deep-net models were found to perform very well in the identification of anatomical locations in the unseen data with high average Percentage of Correct Keypoints (aPCK) performances of >99.65% across all locations.Clinical relevance-Results of this research confirm the feasibility of a low-cost and publicly accessible technology to automatically track infants' GMs and diagnose those at higher risk of developing neurological conditions early, when clinical interventions are most effective.

The General Movements Motor Optimality Score in High-Risk Infants: A Systematic Scoping Review

PURPOSE

The aim of this systematic scoping review was to explore the use of the motor optimality score in the fidgety movement period in clinical practice, and to investigate evidence for the motor optimality score in predicting neurodevelopmental outcomes.

SUMMARY OF KEY POINTS

Thirty-seven studies, with 3662 infants, were included. Studies were conceptualized and charted into 4 categories based on the motor optimality score: prediction, outcome measure, descriptive, or psychometric properties. The most represented populations were preterm or low-birth-weight infants (16 studies), infants with cerebral palsy or neurological concerns (5 studies), and healthy or term-born infants (4 studies).

CONCLUSION

The motor optimality score has the potential to add value to existing tools used to predict risk of adverse neurodevelopmental outcomes. Further research is needed regarding the reliability and validity of the motor optimality score to support increased use of this tool in clinical practice. What this adds to the evidence : The motor optimality score has potential to improve the prediction of adverse neurodevelopmental outcomes. Further research on validity and reliability of the motor optimality score is needed; however, a revised version, the motor optimality score-R (with accompanying manual) will likely contribute to more consistency in the reporting of the motor optimality score in future.

Validity of General Movement Assessment Based on Clinical and Home Videos

INTRODUCTION

The purposes of this study were to develop an instructional leaflet on home video recording for the General Movement Assessment (GMA) and to examine the concurrent and predictive validity of the GMA completed by physical therapists (PTs) and completed by parents.

METHODS

The GMA and the Alberta Infant Motor Scale (AIMS) were completed by PTs in the clinic. Parents completed the GMA following the instructional leaflet.

RESULTS

The content validity of the leaflet was 0.83. The consistency of the GMA results between sources was κ = 0.869. The concurrent validity of the GMA at a corrected age of 3 months was κ = 0.266 (PT) versus 0.525 (parent) using the 10th-percentile cutoffs of the AIMS. The positive likelihood ratio was 26 (PT) versus 25 (parents) at a corrected age of 12 months based on 5th-percentile cutoffs of the AIMS.

CONCLUSIONS

Home GMA videos are valid for clinical assessment following the instructional leaflet.