Automated Movement Analysis to Predict Cerebral Palsy in Very Preterm Infants: An Ambispective Cohort Study

Abstract

The General Movements Assessment requires extensive training. As an alternative, a novel automated movement analysis was developed and validated in preterm infants. Infants < 31 weeks’ gestational age or birthweight ≤ 1500 g evaluated at 3–5 months using the general movements assessment were included in this ambispective cohort study. The C-statistic, sensitivity, specificity, positive predictive value, and negative predictive value were calculated for a predictive model. A total of 252 participants were included. The median gestational age and birthweight were 274/7 weeks (range 256/7–292/7 weeks) and 960 g (range 769–1215 g), respectively. There were 29 cases of cerebral palsy (11.5%) at 18–24 months, the majority of which (n = 22) were from the retrospective cohort. Mean velocity in the vertical direction, median, standard deviation, and minimum quantity of motion constituted the multivariable model used to predict cerebral palsy. Sensitivity, specificity, positive, and negative predictive values were 55%, 80%, 26%, and 93%, respectively. C-statistic indicated good fit (C = 0.74). A cluster of four variables describing quantity of motion and variability of motion was able to predict cerebral palsy with high specificity and negative predictive value. This technology may be useful for screening purposes in very preterm infants; although, the technology likely requires further validation in preterm and high-risk term populations.

Spontaneous movements as prognostic tool of neurodevelopmental outcomes in preterm infants: a narrative review

“…According to the guidelines, GMA is among the recommended evaluation tools for the early detection and intervention of preterm infants [ 5 ]. However, it is not universally utilized worldwide because of limited access to clinical expertise in GMA [ 50 ]. GMA is either a qualitative or semiquantitative evaluation method that is highly dependent on the skills and experience of the assessor.…”

Fusão de Dados de Vídeos RGB e Pontos-Chaves para Classificação de Movimentos Gerais de Bebês

“…Uma tentativa de automatizar a análise de GMs foi realizada em [Raghuram et al 2022] com o objetivo de detectar precocemente paralisia cerebral. O estudo consistiu no desenvolvimento de um modelo estatístico baseado em vídeos 2D.…”

“…Nesse sentido, a atipicidade na execuc ¸ão dos GMs pode indicar distúrbios do neurodesenvolvimento, envolvendo a predic ¸ão de risco de paralisia cerebral ou até mesmo a presenc ¸a de deficiências cognitivas [Aizawa et al 2021]. Por essa razão, a GMA é considerada uma ferramenta de avaliac ¸ão recomendada para acompanhamento de bebês, especialmente prematuros ou com fatores de riscos atrelados, como: baixo peso, exposic ¸ão à infecc ¸ões intrautero, associac ¸ão com idade materna avanc ¸ada, pré-eclampsia, oligodrâmnia, entre outros [Raghuram et al 2022].…”

“…No entanto, a maioria dos trabalhos que se concentram na avaliac ¸ão de GMs a partir de vídeos utiliza modelos de aprendizado de máquina (AM) que tratam os dados em 2D, limitando o uso das informac ¸ões espac ¸o-temporais [Raghuram et al 2022, Tsuji et al 2020]. Os modelos de AM profundo, que são atualmente o estado na arte em reconhecimento de gestos e ac ¸ões a partir de vídeo, são ferramentas que permitem tratar informac ¸ões espac ¸o-temporais.…”