No abstract

Background: Intellectual disability and impaired adaptive functioning are common in children with cerebral palsy, but there is a lack of studies assessing these issues in teenagers with cerebral palsy. Therefore, the aim of this study was to develop and test a predictive machine learning model to identify factors associated with intellectual disability in teenagers with cerebral palsy. Methods: This was a multicenter controlled cohort study of 91 teenagers with cerebral palsy (53 males, 38 females; mean age ± SD = 17 ± 1 y; range: 12-18 y). Data on etiology, diagnosis, spasticity, epilepsy, clinical history, communication abilities, behaviors, motor skills, eating, and drinking abilities were collected between 2005 and 2015. Intellectual disability was classified as “mild,” “moderate,” “severe,” or “profound” based on adaptive functioning, and according to the DSM-5 after 2013 and DSM-IV before 2013, the Wechsler Intelligence Scale for Children for patients up to ages 16 years, 11 months, and the Wechsler Adult Intelligence Scale for patients ages 17-18. Statistical analysis included Fisher’s exact test and multiple logistic regressions to identify factors associated with intellectual disability. A predictive machine learning model was developed to identify factors associated with having profound intellectual disability. The guidelines of the “Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis Statement” were followed. Results: Poor manual abilities (P ≤ .001), gross motor function (P ≤ .001), and type of epilepsy (intractable: P = .04; well controlled: P = .01) were significantly associated with profound intellectual disability. The average model accuracy, specificity, and sensitivity was 78%. Conclusion: Poor motor skills and epilepsy were associated with profound intellectual disability. The machine learning prediction model was able to adequately identify high likelihood of severe intellectual disability in teenagers with cerebral palsy.

Logistic regression–based predictive models are widely used in the healthcare field but just recently are used to predict comorbidities in children with cerebral palsy. This article presents a logistic regression approach to predict health conditions in children with cerebral palsy and a few examples from recent research. The model named PredictMed was trained, tested, and validated for predicting the development of scoliosis, intellectual disabilities, autistic features, and in the present study, feeding disorders needing gastrostomy. This was a multinational, cross-sectional descriptive study. Data of 130 children (aged 12–18 years) with cerebral palsy were collected between June 2005 and June 2015. The logistic regression–based model uses an algorithm implemented in R programming language. After splitting the patients in training and testing sets, logistic regressions are performed on every possible subset (tuple) of independent variables. The tuple that shows the best predictive performance in terms of accuracy, sensitivity, and specificity is chosen as a set of independent variables in another logistic regression to calculate the probability to develop the specific health condition (e.g. the need for gastrostomy). The average of accuracy, sensitivity, and specificity score was 90%. Our model represents a novelty in the field of some cerebral palsy–related health outcomes treatment, and it should significantly help doctors’ decision-making process regarding patient prognosis.

Autism spectrum disorder (ASD) is common in adolescents with cerebral palsy (CP) and there is a lack of studies applying artificial intelligence to investigate this field and this population in particular. The aim of this study is to develop and test a predictive learning model to identify factors associated with ASD in adolescents with CP. This was a multicenter controlled cohort study of 102 adolescents with CP (61 males, 41 females; mean age ± SD [standard deviation] = 16.6 ± 1.2 years; range: 12–18 years). Data on etiology, diagnosis, spasticity, epilepsy, clinical history, communication abilities, behaviors, intellectual disability, motor skills, and eating and drinking abilities were collected between 2005 and 2015. Statistical analysis included Fisher's exact test and multiple logistic regressions to identify factors associated with ASD. A predictive learning model was implemented to identify factors associated with ASD. The guidelines of the “transparent reporting of a multivariable prediction model for individual prognosis or diagnosis” (TRIPOD) statement were followed. Type of spasticity (hemiplegia > diplegia > tri/quadriplegia; OR [odds ratio] = 1.76, SE [standard error] = 0.2785, p = 0.04), communication disorders (OR = 7.442, SE = 0.59, p < 0.001), intellectual disability (OR = 2.27, SE = 0.43, p = 0.05), feeding abilities (OR = 0.35, SE = 0.35, p = 0.002), and motor function (OR = 0.59, SE = 0.22, p = 0.01) were significantly associated with ASD. The best average prediction model score for accuracy, specificity, and sensitivity was 75%. Motor skills, feeding abilities, type of spasticity, intellectual disability, and communication disorders were associated with ASD. The prediction model was able to adequately identify adolescents at risk of ASD.

Background Factors associated with gastrostomy placement in adolescents with developmental disabilities (DDs) and cerebral palsy (CP) are poorly investigated. We aimed to develop and validate a machine learning (ML) model for gastrostomy placement in adolescents with DDs and CP. Methods We performed a multinational, double‐blinded, case‐control study including 130 adolescents with severe DD and CP (72 males, 58 females; mean age 16 ± 2 years). Data on etiology, diagnosis, spasticity, epilepsy, clinical history, and functional assessments such as the Eating and Drinking Ability Classification System, Manual Ability Classification System, and Gross Motor Function Classification System were collected between 2005 and 2015. Analysis included Fisher exact test, multiple logistic regressions, and a supervised ML model, named PredictMed, to identify factors associated with gastrostomy placement. “Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis” guidelines were followed. Results Poor motor function (P < 0.001), trunk muscle tone disorder (P < 0.001), male gender (P < 0.01), epilepsy (P = 0.01), and severe neuromuscular scoliosis (P = 0.04) were factors linked with gastrostomy placement in univariate analysis. Epilepsy (P = 0.03), poor motor function (P = 0.04), and male gender (P = 0.04) were associated with gastrostomy placement in multivariate analysis with 95% accuracy. Conclusion Epilepsy, poor motor function, trunk muscles tone disorder, and male gender were accurate, sensitive, and specific factors associated with gastrostomy need.