Related Experiment Video
Updated: Jun 13, 2025
Measuring the Functional Abilities of Children Aged 3-6 Years Old with Observational Methods and Computer Tools
Published on: June 20, 2020
Development and validation of a nomogram for predicting intellectual disability in children with cerebral palsy
Junying Yuan1,2, Gailing Wang2, Mengyue Li3
1Henan Pediatric Clinical Research Center and Henan Key Laboratory of Child Brain Injury, Institute of Neuroscience and Third Affiliated Hospital and of Zhengzhou University, Zhengzhou 450052, China.
Insights
This study developed a predictive model to identify children with cerebral palsy (CP) at high risk for intellectual disability (ID). Early identification enables timely interventions to improve outcomes for children with CP.
Area of Science:
- Pediatric Neurology
- Developmental Pediatrics
- Clinical Genetics
Background:
- Intellectual disability (ID) frequently co-occurs with cerebral palsy (CP), posing significant challenges.
- Early identification of ID in children with CP is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To develop and validate a predictive model for assessing the risk of intellectual disability (ID) in children diagnosed with cerebral palsy (CP).
Main Methods:
- Analysis of data from 885 children with CP, with 377 diagnosed with ID.
- Utilized least absolute shrinkage and selection operator (LASSO) regression, logistic regression, and decision curve analysis (DCA).
- Model performance assessed using receiver operating characteristic (ROC) curves and calibration plots with bootstrapping validation.
Main Results:
- A predictive nomogram identified key risk factors including preterm birth, CP subtypes, Gross Motor Function Classification System (GMFCS) level, MRI findings, epilepsy, and hearing loss.
- The model demonstrated strong predictive ability with an area under the ROC curve (AUC) of 0.781 (95% CI: 0.7504-0.8116).
- Good model fit and clinical utility were confirmed by calibration plots, Hosmer-Lemeshow test, and DCA.
Conclusions:
- The developed predictive model effectively identifies children with CP at high risk for ID, supporting early intervention.
- Stratified risk categories offer precise clinical management guidance to optimize outcomes for children with CP.
- Leveraging neuroplasticity during early childhood is key for improving developmental trajectories in children with CP.
Objective:
Intellectual disability (ID) is a prevalent comorbidity in children with cerebral palsy (CP), presenting significant challenges to individuals, families and society. This study aims to develop a predictive model to assess the risk of ID in children with CP.
Methods:
We analyzed data from 885 children diagnosed with CP, among whom 377 had ID. Using least absolute shrinkage and selection operator regression, along with univariate and multivariate logistic regression, we identified key predictors for ID. Model performance was evaluated through receiver operating characteristic curves, calibration plots, and decision curve analysis (DCA). Bootstrapping validation was also employed.
Results:
The predictive nomogram included variables such as preterm birth, CP subtypes, Gross Motor Function Classification System level, MRI classification category, epilepsy status and hearing loss. The model demonstrated strong discrimination with an area under the receiver operating characteristic curve (AUC) of 0.781 (95% CI: 0.7504-0.8116) and a bootstrapped AUC of 0.7624 (95% CI: 0.7216-0.8032). Calibration plots and the Hosmer-Lemeshow test indicated a good fit (χ2= 7.9061, p = 0.4427). DCA confirmed the model's clinical utility. The cases were randomly divided into test group and validation group at a 7:3 ratio, demonstrating strong discrimination, good fit and clinical utility; similar results were found when stratified by sex.
Conclusions:
This predictive model effectively identifies children with CP at a high risk for ID, facilitating early intervention strategies. Stratified risk categories provide precise guidance for clinical management, aiming to optimize outcomes for children with CP by leveraging neuroplasticity during early childhood.
