Feature Signature Discovery for Autism Detection: An Automated Machine Learning Based Feature Ranking Framework.

Researchers created a computer program that can help identify early signs of autism using questionnaire responses from people of all ages. The system automatically finds the most important warning signs and achieved very high accuracy (around 90-95%) in distinguishing between people with and without autism. The researchers say this approach is easier to use than previous methods and could potentially help with earlier autism detection.

This 2023 study developed an automated machine learning (AutoML) framework to identify early markers for autism detection across age groups (toddlers to adults) using Q-chat screening data. The researchers applied feature ranking techniques to identify the most significant non-clinical markers that could distinguish between autistic and non-autistic individuals. Their AutoML approach achieved approximately 90% Matthews Correlation Coefficient and 95% balanced accuracy across all four age groups tested. The study claims this framework outperformed previous deep learning approaches while being more flexible and easier to implement, requiring minimal user intervention for automated optimization.

The AutoML framework shows promise for developing automated autism screening tools using questionnaire data. However, clinical validation, regulatory approval, and integration into existing screening protocols would be necessary before implementation. The approach may support earlier detection efforts but requires further research to establish clinical utility.

Sample sizes not reported. Study methodology and validation procedures unclear from abstract. No details on specific feature signatures identified. Comparison with deep learning approaches lacks methodological detail. Clinical validation and real-world applicability not established.

Autism spectrum disorder is the most used umbrella term for a myriad of neuro-degenerative/developmental conditions typified by inappropriate social behavior, lack of communication/comprehension skills, and restricted mental and emotional maturity. The intriguing factor of this disorder is attributed to the fact that it can be detected only by close monitoring of developmental milestones after childbirth. Moreover, the exact causes for the occurrence of this neurodevelopmental condition are still unknown. Besides, autism is prevalent across individuals irrespective of ethnicity, genetic/familial history, and economic/educational background.

Although research suggests that autism is genetic in nature and early detection of this disorder can greatly enhance the independent lifestyle and societal adaptability of affected individuals, there is still a great dearth of information to support the statement of proven facts and figures. This research work places emphasis on the application of automated machine learning incorporated with feature ranking techniques to generate significant feature signatures for the early detection of autism. Publicly available datasets based on the Q-chat scores of individuals across diverse age groups-toddlers, children, adolescents, and adults have been employed in this study. A machine learning framework based on automated hyperparameter optimization is proposed in this work to rank the potential nonclinical markers for autism.

Moreover, this study aimed at ranking the AutoML models based on Mathew's correlation coefficient and balanced accuracy via which nonclinical markers were identified from these datasets. Besides, the feature signatures and their significance in distinguishing between classes are being reported for the first time in autism detection. The proposed framework yielded ∼90% MCC and ∼95% balanced accuracy across all four age groups of autism datasets. Deep learning approaches have yielded a maximum of 92.7% accuracy on the same datasets but are limited in their ability to extract significant markers, have not reported on MCC for unbalanced data, and cannot adapt automatically to new data entries.

However, AutoML approaches are more flexible, easier to implement, and provide automated optimization, thereby yielding the highest accuracy with minimal user intervention.