Machine Learning of Infant Spontaneous Movements for the Early Prediction of Cerebral Palsy: A Multi-Site Cohort Study

Abstract

Background: Early identification of cerebral palsy (CP) during infancy will provide opportunities for early therapies and treatments. The aim of the present study was to present a novel machine-learning model, the Computer-based Infant Movement Assessment (CIMA) model, for clinically feasible early CP prediction based on infant video recordings. Methods: The CIMA model was designed to assess the proportion (%) of CP risk-related movements using a time-frequency decomposition of the movement trajectories of the infant's body parts. The CIMA model was developed and tested on video recordings from a cohort of 377 high-risk infants at 9-15 weeks corrected age to predict CP status and motor function (ambulatory vs. non-ambulatory) at mean 3.7 years age. The performance of the model was compared with results of the general movement 2 of 17 assessment (GMA) and neonatal imaging. Results: The CIMA model had sensitivity (92.7%) and specificity (81.6%), which was comparable to observational GMA or neonatal cerebral imaging for the prediction of CP. Infants later found to have non-ambulatory CP had significantly more CP risk-related movements (median: 92.8%, p = 0.02) compared with those with ambulatory CP (median: 72.7%). Conclusion: The CIMA model may be a clinically feasible alternative to observational GMA.

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

“…In the cases considered so far, the prevalence of fidgety movements in newborns from the age of two months has been considered more frequently, especially in the context of early detection of the risk of cerebral palsy [ 35 ]. An approach similar to that presented in this study was used by Ihnen et al [ 27 ], who analyzed cerebral palsy prediction in a large group of recordings of children over nine weeks of age. Their training set was built based on the classification of the entire recordings, and then each 5 s of the recording were classified.…”

“…In individual studies, authors have attempted to identify irregularities, mostly by reducing the problem to the classification of the recording into the normal and abnormal groups. The proposed solutions can be divided according to the method of the extraction of features describing the child’s movement into those based on features extracted directly from the recording (optical flow, background subtraction) [ 25 , 26 ] and pose-based features, in which the extraction of features is preceded by the process of locating individual body segments [ 27 , 28 ]. Currently, the extraction capabilities of pose-based features have improved due to the availability of ready-made human pose estimation libraries such as OpenPose [ 29 ], whose accuracy in the case of infant movement analysis has been confirmed in various studies [ 28 , 30 ].…”

AI Approaches towards Prechtl’s Assessment of General Movements: A Systematic Literature Review

“…Moreover, Random Forest and AdaBoost seem to be a good choice of classifier, but the method lacks kinematic features that could be introduced by using depth cameras. A new model called Computer-based Infant Movement Assessment (CIMA) was introduced and evaluated on even more infants (377 high-risk infants) by Ihlen et al [ 18 ]. The 1–5 min video recording of 9–15 weeks corrected age infants were used to predict CP.…”

“…As a result of the nominal use of GMA in neonatal follow-up programs, several studies have tried to automate this method. These studies are based on either indirect sensing using visual sensors (2D or 3D video) [ 7 , 13 , 14 , 15 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 24 ], direct sensing using motion sensors [ 25 , 26 , 27 , 28 , 29 , 30 , 31 ], or both [ 32 , 33 , 34 ]. They have shown excellent results, however, they lack full automation and also have several fundamental limitations.…”

“…They have shown excellent results, however, they lack full automation and also have several fundamental limitations. First, all the studies are either based on a small number of subjects or a fewer number of data samples with respect to CP [ 7 , 18 , 19 , 20 , 25 , 26 , 27 , 32 , 34 ]. It is also not clear if the prediction model in these studies has external validity for high-risk infants.…”