Abilities and Disabilities-Applying Machine Learning to Disentangle the Role of Intelligence in Diagnosing Autism Spectrum Disorders

Females evaluated for autism: characteristics and co-occurring and differential DSM-5 diagnoses

Objective: While sex differences in autism spectrum disorder (ASD) have been identified in areas such as neurocognitive functioning, behavior patterns, and diagnostic criteria, less work has focused on differences within females referred for ASD evaluation, including those who did not go on to receive a diagnosis. This study examined psychological and behavioral characteristics and co-occurring and differential DSM-5 diagnoses between pediatric female participants who received an ASD diagnosis (ASD+) and those who did not (ASD-). Method: Data on cognitive functioning, adaptive functioning, internalizing symptoms, externalizing symptoms, and ADOS-2 scores were analyzed among 137 3- to 20-year-old patients. The sample was divided into two age groups (ages 3-8 and ages 9-20) for analyses of between-group differences (ASD+ vs. ASD-) and predictors of group membership. Results: Females in the ASD+ group were significantly younger, had lower cognitive scores, lower internalizing and externalizing symptoms, and had higher Autism Diagnostic Observation Schedule-2 (ADOS-2) scores than those in the ASD- group. ADOS-2 scores were also the only significant predictor of ASD group membership across age groups. The ASD+ group had a higher percentage of intellectual disability while the ASD- group had higher percentages of anxiety disorder, attention-deficit/hyperactivity disorder, and disruptive behavior disorders. Conclusions: Psychological and behavioral presentations among females referred for ASD evaluation varied with age and ASD diagnostic groups. These results highlight potential female differences in ASD referrals and identification of ASD and the need to improve care for females in consideration of demographic factors.

A Machine Learning Approach to the Diagnosis of Autism Spectrum Disorder and Multi-Systemic Developmental Disorder Based on Retrospective Data and ADOS-2 Score

Early and accurate diagnosis of autism spectrum disorders (ASD) and tailored therapeutic interventions can improve prognosis. ADOS-2 is a standardized test for ASD diagnosis. However, owing to ASD heterogeneity, the presence of false positives remains a challenge for clinicians. In this study, retrospective data from patients with ASD and multi-systemic developmental disorder (MSDD), a term used to describe children under the age of 3 with impaired communication but with strong emotional attachments, were tested by machine learning (ML) models to assess the best predictors of disease development as well as the items that best describe these two autism spectrum disorder presentations. Maternal and infant data as well as ADOS-2 score were included in different ML testing models. Depending on the outcome to be estimated, a best-performing model was selected. RIDGE regression model showed that the best predictors for ADOS social affect score were gut disturbances, EEG retrievals, and sleep problems. Linear Regression Model showed that term pregnancy, psychomotor development status, and gut disturbances were predicting at best for the ADOS Repetitive and Restricted Behavior score. The LASSO regression model showed that EEG retrievals, sleep disturbances, age at diagnosis, term pregnancy, weight at birth, gut disturbances, and neurological findings were the best predictors for the overall ADOS score. The CART classification and regression model showed that age at diagnosis and weight at birth best discriminate between ASD and MSDD.

A machine learning-based diagnostic model for children with autism spectrum disorders complicated with intellectual disability

Background

Early detection of children with autism spectrum disorder (ASD) and comorbid intellectual disability (ID) can help in individualized intervention. Appropriate assessment and diagnostic tools are lacking in primary care. This study aims to explore the applicability of machine learning (ML) methods in diagnosing ASD comorbid ID compared with traditional regression models.

Method

From January 2017 to December 2021, 241 children with ASD, with an average age of 6.41 ± 1.96, diagnosed in the Developmental Behavior Department of the Children's Hospital Affiliated with the Medical College of Zhejiang University were included in the analysis. This study trained the traditional diagnostic models of Logistic regression (LR), Support Vector Machine (SVM), and two ensemble learning algorithms [Random Forest (RF) and XGBoost]. Socio-demographic and behavioral observation data were used to distinguish whether autistic children had combined ID. The hyperparameters adjustment uses grid search and 10-fold validation. The Boruta method is used to select variables. The model's performance was evaluated using discrimination, calibration, and decision curve analysis (DCA).

Result

Among 241 autistic children, 98 (40.66%) were ASD comorbid ID. The four diagnostic models can better distinguish whether autistic children are complicated with ID, and the accuracy of SVM is the highest (0.836); SVM and XGBoost have better accuracy (0.800, 0.838); LR has the best sensitivity (0.939), followed by SVM (0.952). Regarding specificity, SVM, RF, and XGBoost performed significantly higher than LR (0.355). The AUC of ML (SVM, 0.835 [95% CI: 0.747-0.944]; RF, 0.829 [95% CI: 0.738-0.920]; XGBoost, 0.845 [95% CI: 0.734-0.937]) is not different from traditional LR (0.858 [95% CI: 0.770-0.944]). Only SVM observed a good calibration degree. Regarding DCA, LR, and SVM have higher benefits in a wider threshold range.

Conclusion

Compared to the traditional regression model, ML model based on socio-demographic and behavioral observation data, especially SVM, has a better ability to distinguish whether autistic children are combined with ID.

Autism Spectrum Disorder and IQ - A Complex Interplay

Autism spectrum disorder (ASD) is characterized as a very heterogeneous child-onset disorder, whose heterogeneity is partly determined by differences in intelligence quotient (IQ). Older epidemiological studies suggested that the IQ-related spectrum tends to be skewed to the left, i.e., a larger proportion of individuals with ASD have below average intelligence, while only few individuals with ASD may have an IQ above average. This picture changed over time with broadening the spectrum view. Within the present perspective article, we discuss discrepancies in IQ profiles between epidemiological and clinical studies and identify potential underlying aspects, for example, the influence of external factors such as sample biases or differences in availability of autism health services. Additionally, we discuss the validity and reciprocal influences of ASD diagnostics and IQ measurement. We put the impact of these factors for diagnostic as well as care and support situations of patients into perspective and want to encourage further research to contribute to the conceptualization of "autism" more comprehensively including the IQ as well as to examine broader (life) circumstances, interacting factors and diagnostic requirements of given diagnoses in childhood as compared to adulthood.