Predictive Value of Early Autism Detection Models Based on Electronic Health Record Data Collected Before Age 1 Year

Engelhard, Matthew M.; Henao, Ricardo; Berchuck, Samuel I.; Chen, Junya; Eichner, Brian; Herkert, Darby; Kollins, Scott H.; Olson, Andrew; Perrin, Eliana M.; Rogers, Ursula; Sullivan, Connor; Zhu, YiQin; Sapiro, Guillermo; Dawson, Geraldine

doi:10.1001/jamanetworkopen.2022.54303

Cited by 13 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial cohort included all patients with an autism‐related ICD‐10‐CM diagnosis (F84.0, F84.5, F84.8, or F84.9) associated with encounters before 1st June 2021. Following a computable phenotype previously investigated at DUHS (Engelhard et al, 2023), our inclusion criteria were (a) diagnosis codes related to autism associated with ≥2 encounters; (b) ≥1 documented encounter of any type at least 2 years prior to the first autism code; and (c) an observed autism diagnosis code before age 18. Criterion (a) was designed to ensure patients received routine care within DUHS for a substantial period of time prior to autism diagnosis.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Sex differences in the age of childhood autism diagnosis and the impact of co‐occurring conditions

Gu,

Dawson,

Engelhard

2023

Autism Research

Self Cite

View full text Add to dashboard Cite

Sex differences in the age of autism diagnosis during childhood have been documented consistently but remain poorly understood. In this study, we used electronic health records data from a diverse, academic medical center to quantify differences in the age of autism diagnosis between boys and girls and identify associations between the age of diagnosis and co‐occurring neurodevelopmental, psychiatric, and medical conditions. An established computable phenotype was used to identify all autism diagnoses within the Duke University Health System between 2014 and 2021. Co‐occurring neurodevelopmental and psychiatric diagnoses as well as visits to specific medical and supportive services were identified in the 2 years prior to the autism diagnosis. Cox proportional hazards models were fitted to quantify associations between diagnosis age and sex with and without controlling for the presence of each co‐occurring diagnosis and visit type. Records from 1438 individuals (1142 boys and 296 girls) were included. Girls were more likely to be diagnosed either before age 3 ( = 497.720, p < 0.001) or after age 11 ( = 4.014, p = 0.047), whereas boys were more likely to be diagnosed between ages 3 and 11 ( = 5.532, p = 0.019). Visits for anxiety ( = 4.200, p = 0.040) and mood disorders ( = 7.033, p = 0.008) were more common in girls and associated with later autism diagnosis (HR = 0.615, p < 0.001; and HR = 0.493, p < 0.001). Visits for otolaryngology were more common in boys and associated with an earlier autism diagnosis (HR = 1.691, p < 0.001). After controlling for these conditions, associations between sex and diagnosis age were reduced and not statistically significant. These results show that the age of autism diagnosis differs in girls compared to boys, but these differences were neutralized when controlling for co‐occurring neurodevelopmental and psychiatric conditions prior to autism diagnosis. Understanding sex differences and the possible mediating role of other diagnoses may suggest targets for intervention to promote earlier and more equitable diagnosis.

show abstract

Section: Methodsmentioning

confidence: 99%

“…How to cite this article: Gu, Z., Dawson, G., & Engelhard, M. (2023). Sex differences in the age of childhood autism diagnosis and the impact of co-occurring conditions.…”

Section: Funding Informationmentioning

confidence: 99%

Sex differences in the age of childhood autism diagnosis and the impact of co‐occurring conditions

Gu,

Dawson,

Engelhard

2023

Autism Research

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast to traditional screening tools that require expensive, time-consuming procedures, AI models can learn subtle patterns and precursors of disease, and then automatically identify at-risk patients using longitudinal information stored in EHRs [12,13]. For instance, models trained on routine EHR data have detected autism spectrum disorder in infants as early as 30 days after birth (nearly one year earlier than standard autism screening tools) [14], and they have detected latent diseases in adults such as peripheral artery disease [15]. They have also identified individuals at high risk of falling [16], and predicted the development of pressure ulcers within the first 24 hours of admission to an intensive care unit [17].…”

Section: Electronic Health Recordsmentioning

confidence: 99%

AI in Rehabilitation Medicine: Opportunities and Challenges

Lanotte,

O’Brien,

Jayaraman

2023

Ann Rehabil Med

View full text Add to dashboard Cite

Artificial intelligence (AI) tools are increasingly able to learn from larger and more complex data, thus allowing clinicians and scientists to gain new insights from the information they collect about their patients every day. In rehabilitation medicine, AI can be used to find patterns in huge amounts of healthcare data. These patterns can then be leveraged at the individual level, to design personalized care strategies and interventions to optimize each patient’s outcomes. However, building effective AI tools requires many careful considerations about how we collect and handle data, how we train the models, and how we interpret results. In this perspective, we discuss some of the current opportunities and challenges for AI in rehabilitation. We first review recent trends in AI for the screening, diagnosis, treatment, and continuous monitoring of disease or injury, with a special focus on the different types of healthcare data used for these applications. We then examine potential barriers to designing and integrating AI into the clinical workflow, and we propose an end-to-end framework to address these barriers and guide the development of effective AI for rehabilitation. Finally, we present ideas for future work to pave the way for AI implementation in real-world rehabilitation practices.

show abstract

“…Previous work on autism prediction using electronic health records (EHRs) identified covariates that are associated with autism, such as low birth weight, small for gestational age, low Apgar scores, and other perinatal complications . More recently, Engelhard et al reported high predictive value of their EHR-based autism prediction model, applied before 1 year of age. Similarly, Onishchenko et al used medical claims data to estimate an autism comorbid risk score that aimed to improve the accuracy of M-CHAT.…”

Section: Introductionmentioning

confidence: 99%

Early Prediction of Autistic Spectrum Disorder Using Developmental Surveillance Data

Amit,

Bilu,

Sudry

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceWith the continuous increase in the prevalence of autistic spectrum disorder (ASD), effective early screening is crucial for initiating timely interventions and improving outcomes.ObjectiveTo 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 ParticipantsThis 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 = 1 187 397). 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.ExposuresFor 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 MeasureThe 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).ResultsThe study included 1 187 397 children (610 588 [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 RelevanceThis 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.

show abstract

Predictive Value of Early Autism Detection Models Based on Electronic Health Record Data Collected Before Age 1 Year

Cited by 13 publications

References 34 publications

Sex differences in the age of childhood autism diagnosis and the impact of co‐occurring conditions

Sex differences in the age of childhood autism diagnosis and the impact of co‐occurring conditions

AI in Rehabilitation Medicine: Opportunities and Challenges

Early Prediction of Autistic Spectrum Disorder Using Developmental Surveillance Data

Contact Info

Product

Resources

About