TY - JOUR
T1 - Early Prediction of Autistic Spectrum Disorder Using Developmental Surveillance Data
AU - Amit, Guy
AU - Bilu, Yonatan
AU - Sudry, Tamar
AU - Avgil Tsadok, Meytal
AU - Zimmerman, Deena R.
AU - Baruch, Ravit
AU - Kasir, Nitsa
AU - Akiva, Pinchas
AU - Sadaka, Yair
N1 - Publisher Copyright:
© 2024 American Medical Association. All rights reserved.
PY - 2024/1/10
Y1 - 2024/1/10
N2 - Importance: With the continuous increase in the prevalence of autistic spectrum disorder (ASD), effective early screening is crucial for initiating timely interventions and improving outcomes. Objective: To develop predictive models for ASD using routinely collected developmental surveillance data and to assess their performance in predicting ASD at different ages and in different clinical scenarios. Design, Setting, and Participants: This retrospective cohort study used nationwide data of developmental assessments conducted between January 1, 2014, and January 17, 2023, with minimal follow-up of 4 years and outcome collection in March 2023. Data were from a national program of approximately 1000 maternal child health clinics that perform routine developmental surveillance of children from birth to 6 years of age, serving 70% of children in Israel. The study included all children who were assessed at the maternal child health clinics (N = 1187397). Children were excluded if they were born at a gestational age of 33 weeks or earlier, had no record of gestational age, or were followed up for less than 4 years without an ASD outcome. The data set was partitioned at random into a development set (80% of the children) and a holdout evaluation set (20% of the children), both with the same prevalence of ASD outcome. Exposures: For each child, demographic and birth-related covariates were extracted, as were per-visit growth measurements, quantified developmental milestone assessments, and referral summary covariates. Only information that was available before the prediction age was used for training and evaluating the models. Main Outcome and Measure: The main outcome was eligibility for a governmental disabled child allowance due to ASD, according to administrative data of the National Insurance Institute of Israel. The performance of the models that predict the outcome was evaluated and compared with previous work on the Modified Checklist for Autism in Toddlers (M-CHAT). Results: The study included 1187397 children (610588 [51.4%] male). The performance of the ASD prediction models improved with prediction age, with fair accuracy already at 12 months of age. A model that combined longitudinal measures of developmental milestone assessments with a minimal set of demographic variables, which was applied at 18 to 24 months of age, achieved an area under the receiver operating characteristic curve of 0.83, with a sensitivity of 45.1% at a specificity of 95.0%. A model using single-visit assessments achieved an area under the receiver operating characteristic curve of 0.81 and a sensitivity of 41.2% at a specificity of 95.0%. The best performing prediction models surpassed the pooled performance of M-CHAT (sensitivity, 40%; specificity, 95%) reported in studies with a similar design. Conclusions and Relevance: This cohort study found that ASD can be predicted from routine developmental surveillance data at an accuracy surpassing M-CHAT screening. This tool may be seamlessly integrated in the clinical workflow to improve early identification of children who may benefit from timely interventions..
AB - Importance: With the continuous increase in the prevalence of autistic spectrum disorder (ASD), effective early screening is crucial for initiating timely interventions and improving outcomes. Objective: To develop predictive models for ASD using routinely collected developmental surveillance data and to assess their performance in predicting ASD at different ages and in different clinical scenarios. Design, Setting, and Participants: This retrospective cohort study used nationwide data of developmental assessments conducted between January 1, 2014, and January 17, 2023, with minimal follow-up of 4 years and outcome collection in March 2023. Data were from a national program of approximately 1000 maternal child health clinics that perform routine developmental surveillance of children from birth to 6 years of age, serving 70% of children in Israel. The study included all children who were assessed at the maternal child health clinics (N = 1187397). Children were excluded if they were born at a gestational age of 33 weeks or earlier, had no record of gestational age, or were followed up for less than 4 years without an ASD outcome. The data set was partitioned at random into a development set (80% of the children) and a holdout evaluation set (20% of the children), both with the same prevalence of ASD outcome. Exposures: For each child, demographic and birth-related covariates were extracted, as were per-visit growth measurements, quantified developmental milestone assessments, and referral summary covariates. Only information that was available before the prediction age was used for training and evaluating the models. Main Outcome and Measure: The main outcome was eligibility for a governmental disabled child allowance due to ASD, according to administrative data of the National Insurance Institute of Israel. The performance of the models that predict the outcome was evaluated and compared with previous work on the Modified Checklist for Autism in Toddlers (M-CHAT). Results: The study included 1187397 children (610588 [51.4%] male). The performance of the ASD prediction models improved with prediction age, with fair accuracy already at 12 months of age. A model that combined longitudinal measures of developmental milestone assessments with a minimal set of demographic variables, which was applied at 18 to 24 months of age, achieved an area under the receiver operating characteristic curve of 0.83, with a sensitivity of 45.1% at a specificity of 95.0%. A model using single-visit assessments achieved an area under the receiver operating characteristic curve of 0.81 and a sensitivity of 41.2% at a specificity of 95.0%. The best performing prediction models surpassed the pooled performance of M-CHAT (sensitivity, 40%; specificity, 95%) reported in studies with a similar design. Conclusions and Relevance: This cohort study found that ASD can be predicted from routine developmental surveillance data at an accuracy surpassing M-CHAT screening. This tool may be seamlessly integrated in the clinical workflow to improve early identification of children who may benefit from timely interventions..
UR - http://www.scopus.com/inward/record.url?scp=85182088350&partnerID=8YFLogxK
U2 - 10.1001/jamanetworkopen.2023.51052
DO - 10.1001/jamanetworkopen.2023.51052
M3 - Article
C2 - 38198135
AN - SCOPUS:85182088350
SN - 2574-3805
VL - 7
SP - E2351052
JO - JAMA network open
JF - JAMA network open
IS - 1
ER -