Related Experiment Video
Updated: Jul 2, 2025
Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
Machine learning approaches to evaluate infants' general movements in the writhing stage-a pilot study
Lisa Letzkus1, J Vince Pulido2, Abiodun Adeyemo3
1Department of Pediatrics, University of Virginia Children's Hospital, PO Box 800828, Charlottesville, VA, 22908, USA. lmc8c@uvahealth.org.
Insights
Machine learning accurately assesses infant general movements (GMs) in the neonatal intensive care unit (NICU). This automated system distinguishes normal from abnormal GMs, aiding early cerebral palsy risk assessment.
Area of Science:
- Neonatal neurology
- Machine learning in healthcare
- Developmental pediatrics
Background:
- General movements (GMs) are crucial for assessing infant neurological development.
- Identifying abnormal GMs, like cramped-synchronized (CS) movements, can indicate neurological conditions.
- Objective assessment of GMs in the neonatal intensive care unit (NICU) is challenging.
Purpose of the Study:
- To describe machine learning techniques for automatic evaluation of infant general movements (GMs) during the writhing stage.
- To develop and validate a computer-vision based pose estimation model for NICU infants.
- To create a preliminary movement model distinguishing normal from cramped-synchronized (CS) GMs.
Main Methods:
- Retrospective analysis of 85 videos from 74 NICU infants.
- Utilized a NICU-trained pose estimation model for key point localization (accuracy measured by Object Key Point Similarity - OKS).
- Developed a movement model using cosine similarity and autocorrelation to differentiate normal and CS GMs.
Main Results:
- The NICU-trained pose estimation model achieved higher accuracy (0.91 OKS) compared to a generic model (0.83 OKS, p < 0.001).
- Significant differences in lower limb autocorrelation values were found between normal and CS GMs (p < 0.05).
- Automated pose estimation of key points in NICU patients was demonstrated as feasible.
Conclusions:
- Machine learning, particularly a NICU-trained pose estimation model, can accurately assess infant GMs.
- This automated approach shows promise for earlier detection of cerebral palsy (CP) risk.
- The findings support the potential of AI tools for neurodevelopmental assessment prior to hospital discharge.
Abstract:
The goals of this study are to describe machine learning techniques employing computer-vision movement algorithms to automatically evaluate infants' general movements (GMs) in the writhing stage. This is a retrospective study of infants admitted 07/2019 to 11/2021 to a level IV neonatal intensive care unit (NICU). Infant GMs, classified by certified expert, were analyzed in two-steps (1) determination of anatomic key point location using a NICU-trained pose estimation model [accuracy determined using object key point similarity (OKS)]; (2) development of a preliminary movement model to distinguish normal versus cramped-synchronized (CS) GMs using cosine similarity and autocorrelation of major joints. GMs were analyzed using 85 videos from 74 infants; gestational age at birth 28.9 ± 4.1 weeks and postmenstrual age (PMA) at time of video 35.9 ± 4.6 weeks The NICU-trained pose estimation model was more accurate (0.91 ± 0.008 OKS) than a generic model (0.83 ± 0.032 OKS, p < 0.001). Autocorrelation values in the lower limbs were significantly different between normal (5 videos) and CS GMs (5 videos, p < 0.05). These data indicate that automated pose estimation of anatomical key points is feasible in NICU patients and that a NICU-trained model can distinguish between normal and CS GMs. These preliminary data indicate that machine learning techniques may represent a promising tool for earlier CP risk assessment in the writhing stage and prior to hospital discharge.
