Related Experiment Video
Updated: Aug 13, 2025
A Battery of Motor Tests in a Neonatal Mouse Model of Cerebral Palsy
Published on: November 3, 2016
Prediction Model for Identifying Computational Phenotypes of Children with Cerebral Palsy Needing Neurotoxin
Carlo M Bertoncelli1,2,3, Michal Latalski4, Domenico Bertoncelli1,3
1Department of Computer Science, Hal Marcus College of Science & Engineering, University of West Florida, Pensacola, FL 32514, USA.
Insights
Predicting neurotoxin treatments for children with cerebral palsy (CP) is crucial. A new machine-learning model accurately identifies children with CP likely to need neurotoxin injections based on clinical features.
Area of Science:
- Pediatric Neurology
- Rehabilitation Medicine
- Biostatistics
Background:
- Neurotoxin treatments are common for children with cerebral palsy (CP), but factors predicting their need are not well understood.
- Identifying children likely to benefit from neurotoxin injections can optimize treatment strategies and improve outcomes.
Purpose of the Study:
- To develop and validate a prediction model for identifying the prognostic phenotype of children with CP who require neurotoxin injections.
- To analyze clinical and functional factors associated with neurotoxin treatment in pediatric CP.
Main Methods:
- A longitudinal, international, multicenter, double-blind descriptive study involving 165 children with CP (aged 12-18 years).
- Data collected from 2005-2020 included functional and clinical information, analyzed using the BTX-PredictMed machine-learning model.
- External validation of the prediction model was performed following "Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis" guidelines.
Main Results:
- Univariate analysis linked neuromuscular scoliosis, equines foot, and etiological type to neurotoxin treatments.
- Multivariate analysis identified upper limb and trunk muscle tone disorders, spasticity, dystonia, and hip dysplasia as strongly associated with neurotoxin injections.
- The prediction model achieved an average accuracy, sensitivity, and specificity of 75%.
Conclusions:
- The developed BTX-PredictMed model accurately identifies clinical features associated with neurotoxin treatment needs in children with CP.
- This tool aids in identifying children with CP who are likely candidates for neurotoxin injections, improving prognostic assessments.
- Further research can refine this model for personalized treatment planning in pediatric cerebral palsy management.
Abstract:
Factors associated with neurotoxin treatments in children with cerebral palsy (CP) are poorly studied. We developed and externally validated a prediction model to identify the prognostic phenotype of children with CP who require neurotoxin injections. We conducted a longitudinal, international, multicenter, double-blind descriptive study of 165 children with CP (mean age 16.5 ± 1.2 years, range 12−18 years) with and without neurotoxin treatments. We collected functional and clinical data from 2005 to 2020, entered them into the BTX-PredictMed machine-learning model, and followed the guidelines, “Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis”. In the univariate analysis, neuromuscular scoliosis (p = 0.0014), equines foot (p < 0.001) and type of etiology (prenatal > peri/postnatal causes, p = 0.05) were linked with neurotoxin treatments. In the multivariate analysis, upper limbs (p < 0.001) and trunk muscle tone disorders (p = 0.02), the presence of spasticity (p = 0.01), dystonia (p = 0.004), and hip dysplasia (p = 0.005) were strongly associated with neurotoxin injections; and the average accuracy, sensitivity, and specificity was 75%. These results have helped us identify, with good accuracy, the clinical features of prognostic phenotypes of subjects likely to require neurotoxin injections.
