Writhing Movement Detection in Newborns on the Second and Third Day of Life Using Pose-Based Feature Machine Learning Classification

Abstract

Observation of neuromotor development at an early stage of an infant’s life allows for early diagnosis of deficits and the beginning of the therapeutic process. General movement assessment is a method of spontaneous movement observation, which is the foundation for contemporary attempts at objectification and computer-aided diagnosis based on video recordings’ analysis. The present study attempts to automatically detect writhing movements, one of the normal general movement categories presented by newborns in the first weeks of life. A set of 31 recordings of newborns on the second and third day of life was divided by five experts into videos containing writhing movements (with occurrence time) and poor repertoire, characterized by a lower quality of movement in relation to the norm. Novel, objective pose-based features describing the scope, nature, and location of each limb’s movement are proposed. Three machine learning algorithms are evaluated in writhing movements’ detection in leave-one-out cross-validation for different feature extraction time windows and overlapping time. The experimental results make it possible to indicate the optimal parameters for which 80% accuracy was achieved. Based on automatically detected writhing movement percent in the video, infant movements are classified as writhing movements or poor repertoire with an area under the ROC (receiver operating characteristics) curve of 0.83.

The future of General Movement Assessment: The role of computer vision and machine learning – A scoping review

“…Armed with the rapid advancing computer science, a surging interest in developing automated GMA prevails in the field. Among the identified studies directly devoted to automated vision-based GMA, the majority were published within the past five years, and more are coming day after day (e.g., Doroniewicz et al, 2020 ; Groos, Adde, Støen, Ramampiaro, & Ihlen, 2020 ). As a limitation, we targeted only the publications in English during the past decade.…”

Novel AI driven approach to classify infant motor functions

“…Two studies used full pose recovery based on passive measurements 64 , 67 . McCay et al 64 used artificial data made up from “normal” and “abnormal” participants; As feature vector binned joint movements are used.…”

“…McCay et al 64 used artificial data made up from “normal” and “abnormal” participants; As feature vector binned joint movements are used. Doroniewicz et al 67 analyzed 31 participants to distinguish normal and abnormal (i.e., poor repertoire) writhing movements. The feature vector holds information about the movement’s area, movement’s shape, and the center of the movement’s area.…”

An Automated Approach for General Movement Assessment: A Pilot Study

“…Most of the previous studies considered accelerometer data for automating GMA are based on genetic algorithms or machine learning approaches (17,31,(34)(35)(36)(37). These are also almost the exclusive methods applied to 2D RGB camera data mimicking the clinical evaluation (38)(39)(40)(41)(42). Machine learning methods have great potentialities for classifying data.…”