Data-Driven Early Prediction of Cerebral Palsy Using AutoML and interpretable kinematic features
Abstract: Early identi!cation of cerebral palsy (CP) remains a major challenge
due to the reliance on expert assessments that are time-intensive
and not scalable. Consequently, a range of studies have aimed at us-
ing machine learning to predict CP scores based on motion tracking,
e.g. from video data. These studies generally predict clinical scores
which are a proxy for CP risk. However, clinicians do not REALLY
want to estimate scores, they want to estimate the patients’ risk
of developing clinical symptoms. Here we present a data-driven
machine-learning (ML) pipeline that extracts movement features
from infant video based motion tracking and estimates CP risk us-
ing AutoML. Using AutoSklearn, our framework minimizes risk of
over!tting by abstracting away researcher-driver hyperparameter
optimization. Trained on movement data from 3- to 4-month-old
infants, our classi!er predicts a highly indicative clinical score (Gen-
eral Movements Assessment [GMA]) with an ROC-AUC of 0.78 on
a held-out test set, indicating that kinematic movement features
capture clinically relevant variability. Without retraining, the same
model predicts the risk of cerebral palsy outcomes at later clinical
follow-ups with an ROC-AUC of 0.74, demonstrating that early
motor representations generalize to long-term neurodevelopmental
risk. We employ pre-registered lock-box validation to ensure rig-
orous performance evaluation. This study highlights the potential
of AutoML-powered movement analytics for neurodevelopmental
screening, demonstrating that data-driven feature extraction from
movement trajectories can provide an interpretable and scalable
approach to early risk assessment. By integrating pre-trained vi-
sion transformers, AutoML-driven model selection, and rigorous
validation protocols, this work advances the use of video-derived
movement features for scalable, data-driven clinical assessment,
demonstrating how computational methods based on readily avail-
able data like infant videos can enhance early risk detection in
neurodevelopmental disorders.
Loading