Diagnosing Health Condition for Autism Spectrum Disorder based on Data Mining Techniques

What is ASD Diagnosis?

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that impairs an individual's social, communication and learning abilities. Every year, the World Health Organization diagnoses autism globally in one out of every 160 children.

The diagnosis of ASD is very important in the early stages of life, which prompted researchers to intensify efforts to reach the best solutions.

Significance of Research

The developed framework would be beneficial in advancing, accelerating, and selecting diagnosis tools in therapy with ASD. The selected model can identify severity as light, medium, or severe based on medical tests and Sociodemographic weighted features.

Research Contribution

1. Develop 72 hybrid classification models based on the intersection of eight feature selection techniques and nine ML algorithms to diagnose ASD patients using weighted medical tests and Sociodemographic Characteristics features. The weighting process has been constructed based on the FWIZC method for each set of feature selection techniques.
2. Advance a new dynamic Decision Matrix (DM) for evaluating and benchmarking the 72 developed hybrid diagnosis models based on eight performance evaluation metrics.
3. Develop a multi-criteria decision-making (MCDM) framework to evaluate and benchmark the 72 hybrid diagnosis models using the FDOSM method.
4. Construct the diverse weights of medical tests and Sociodemographic features based on four psychiatrists' experts using the FWZIC method.