Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants
Daniel Groos1, Lars Adde2,3, Sindre Aubert4
1Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway.
Insights
A new deep learning method accurately predicts cerebral palsy (CP) in infants using videos of their movements. This AI tool shows promise for early detection and intervention, improving outcomes for high-risk newborns.
Area of Science:
- Neurology
- Artificial Intelligence in Medicine
- Developmental Pediatrics
Background:
- Early identification of cerebral palsy (CP) is crucial for timely intervention, but current expert-based assessments are not widely accessible.
- Conventional machine learning methods for CP prediction have shown limitations in validity.
- There is a need for objective, scalable tools for early CP detection in high-risk infants.
Purpose of the Study:
- To develop and externally validate a novel deep learning (DL) model for predicting CP.
- To assess the DL model's performance using videos of infant spontaneous movements at 9 to 18 weeks' corrected age.
- To compare the DL model's accuracy against the General Movement Assessment (GMA) tool and conventional machine learning.
Main Methods:
- A prognostic study involving 557 high-risk infants from multiple international sites.
- Infants underwent video recording of spontaneous movements at 9-18 weeks' corrected age.
- A deep learning model was trained and validated using video data to predict CP status at older ages.
Main Results:
- The DL-based CP prediction method demonstrated strong external validation performance with 71.4% sensitivity and 94.1% specificity.
- The DL method achieved higher accuracy (90.6%) compared to conventional machine learning (72.7%) but similar accuracy to the GMA tool (85.9%).
- The DL model showed higher sensitivity for predicting nonambulatory and spastic bilateral CP subtypes.
Conclusions:
- A deep learning-based method shows significant predictive accuracy for CP in infants based on early movement videos.
- This AI-driven approach offers a potential pathway for objective, early detection of CP in clinical practice.
- Further integration of such tools could enhance early intervention strategies and improve long-term outcomes for affected children.
Importance:
Early identification of cerebral palsy (CP) is important for early intervention, yet expert-based assessments do not permit widespread use, and conventional machine learning alternatives lack validity.
Objective:
To develop and assess the external validity of a novel deep learning-based method to predict CP based on videos of infants' spontaneous movements at 9 to 18 weeks' corrected age.
Design, Setting, And Participants:
This prognostic study of a deep learning-based method to predict CP at a corrected age of 12 to 89 months involved 557 infants with a high risk of perinatal brain injury who were enrolled in previous studies conducted at 13 hospitals in Belgium, India, Norway, and the US between September 10, 2001, and October 25, 2018. Analysis was performed between February 11, 2020, and September 23, 2021. Included infants had available video recorded during the fidgety movement period from 9 to 18 weeks' corrected age, available classifications of fidgety movements ascertained by the general movement assessment (GMA) tool, and available data on CP status at 12 months' corrected age or older. A total of 418 infants (75.0%) were randomly assigned to the model development (training and internal validation) sample, and 139 (25.0%) were randomly assigned to the external validation sample (1 test set).
Exposure:
Video recording of spontaneous movements.
Main Outcomes And Measures:
The primary outcome was prediction of CP. Deep learning-based prediction of CP was performed automatically from a single video. Secondary outcomes included prediction of associated functional level and CP subtype. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed.
Results:
Among 557 infants (310 [55.7%] male), the median (IQR) corrected age was 12 (11-13) weeks at assessment, and 84 infants (15.1%) were diagnosed with CP at a mean (SD) age of 3.4 (1.7) years. Data on race and ethnicity were not reported because previous studies (from which the infant samples were derived) used different study protocols with inconsistent collection of these data. On external validation, the deep learning-based CP prediction method had sensitivity of 71.4% (95% CI, 47.8%-88.7%), specificity of 94.1% (95% CI, 88.2%-97.6%), positive predictive value of 68.2% (95% CI, 45.1%-86.1%), and negative predictive value of 94.9% (95% CI, 89.2%-98.1%). In comparison, the GMA tool had sensitivity of 70.0% (95% CI, 45.7%-88.1%), specificity of 88.7% (95% CI, 81.5%-93.8%), positive predictive value of 51.9% (95% CI, 32.0%-71.3%), and negative predictive value of 94.4% (95% CI, 88.3%-97.9%). The deep learning method achieved higher accuracy than the conventional machine learning method (90.6% [95% CI, 84.5%-94.9%] vs 72.7% [95% CI, 64.5%-79.9%]; P < .001), but no significant improvement in accuracy was observed compared with the GMA tool (85.9%; 95% CI, 78.9%-91.3%; P = .11). The deep learning prediction model had higher sensitivity among infants with nonambulatory CP (100%; 95% CI, 63.1%-100%) vs ambulatory CP (58.3%; 95% CI, 27.7%-84.8%; P = .02) and spastic bilateral CP (92.3%; 95% CI, 64.0%-99.8%) vs spastic unilateral CP (42.9%; 95% CI, 9.9%-81.6%; P < .001).
Conclusions And Relevance:
In this prognostic study, a deep learning-based method for predicting CP at 9 to 18 weeks' corrected age had predictive accuracy on external validation, which suggests possible avenues for using deep learning-based software to provide objective early detection of CP in clinical settings.
More Related Videos
09:24Quantified Assessment of Infant's Gross Motor Abilities Using a Multisensor Wearable
Published on: May 17, 2024
08:26Event-related Potentials During Target-response Tasks to Study Cognitive Processes of Upper Limb Use in Children with Unilateral Cerebral Palsy
Published on: January 11, 2016