Related Experiment Video
Updated: Aug 12, 2025
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Predictive Value of Early Autism Detection Models Based on Electronic Health Record Data Collected Before Age 1 Year
Matthew M Engelhard1, Ricardo Henao1,2,3, Samuel I Berchuck4
1Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, North Carolina.
Insights
Early autism detection using electronic health records (EHRs) shows promising accuracy by 30 days of age. This predictive model, based on routine care data, can improve early identification of autism spectrum disorder (ASD).
Area of Science:
- Pediatric Health
- Developmental Neuroscience
- Medical Informatics
Background:
- Early detection of autism spectrum disorder (ASD) is crucial for timely intervention and support.
- Electronic health records (EHRs) contain valuable data that can be leveraged for passive monitoring and early ASD detection.
- Identifying early correlates of ASD in routine clinical data can enhance diagnostic accuracy.
Purpose of the Study:
- To evaluate the predictive capability of models for early autism detection using EHR data collected before one year of age.
- To quantify the performance of predictive models in identifying children with autism spectrum disorder (ASD) based on early health records.
Main Methods:
- Retrospective diagnostic study utilizing EHR data from children under 30 days old.
- Development and validation of L2-regularized Cox proportional hazards models to predict later ASD diagnosis.
- Analysis of data collected from birth up to 360 days of age, with statistical analysis conducted between August 2020 and April 2022.
Main Results:
- The study included 45,080 children, with 1.5% diagnosed with ASD.
- Autism detection models at 30 days achieved 45.5% sensitivity and 23.0% positive predictive value (PPV) at 90.0% specificity.
- By 360 days of age, detection improved, reaching 59.8% sensitivity and 17.6% PPV at 81.5% specificity, or 38.8% sensitivity and 31.0% PPV at 94.3% specificity.
Conclusions:
- EHR-based autism detection demonstrates clinically meaningful accuracy as early as 30 days of life.
- The predictive accuracy of these models improves by the child's first year.
- Automated EHR-based screening, potentially combined with caregiver surveys, can enhance early autism detection efforts.
Importance:
Autism detection early in childhood is critical to ensure that autistic children and their families have access to early behavioral support. Early correlates of autism documented in electronic health records (EHRs) during routine care could allow passive, predictive model-based monitoring to improve the accuracy of early detection.
Objective:
To quantify the predictive value of early autism detection models based on EHR data collected before age 1 year.
Design, Setting, And Participants:
This retrospective diagnostic study used EHR data from children seen within the Duke University Health System before age 30 days between January 2006 and December 2020. These data were used to train and evaluate L2-regularized Cox proportional hazards models predicting later autism diagnosis based on data collected from birth up to the time of prediction (ages 30-360 days). Statistical analyses were performed between August 1, 2020, and April 1, 2022.
Main Outcomes And Measures:
Prediction performance was quantified in terms of sensitivity, specificity, and positive predictive value (PPV) at clinically relevant model operating thresholds.
Results:
Data from 45 080 children, including 924 (1.5%) meeting autism criteria, were included in this study. Model-based autism detection at age 30 days achieved 45.5% sensitivity and 23.0% PPV at 90.0% specificity. Detection by age 360 days achieved 59.8% sensitivity and 17.6% PPV at 81.5% specificity and 38.8% sensitivity and 31.0% PPV at 94.3% specificity.
Conclusions And Relevance:
In this diagnostic study of an autism screening test, EHR-based autism detection achieved clinically meaningful accuracy by age 30 days, improving by age 1 year. This automated approach could be integrated with caregiver surveys to improve the accuracy of early autism screening.
