Development and evaluation of an expert system for the diagnosis of child autism

Area of Science:

• Pediatric Medicine
• Artificial Intelligence in Healthcare
• Developmental Psychology

Background:

• Early diagnosis of child autism is crucial for effective intervention.
• Existing diagnostic tools can be time-consuming and require specialized training.
• There is a need for efficient and accessible methods to identify potential autism cases in clinical settings.

Purpose of the Study:

• To develop and evaluate an expert system for the diagnosis of child autism.
• To assess the usefulness, usability, and diagnostic value of the expert system in a clinical environment.
• To explore the potential benefits of implementing such a system in pediatric healthcare.

Main Methods:

• Development of an expert system based on a diagnostic algorithm.
• Integration of the Parent's Evaluation of Developmental Status (PEDS) and Childhood Autism Rating Scale (CARS) into the system.
• Pilot testing with twelve pediatric nurses who used the system for 30 minutes.

Main Results:

• The majority of nurses found the expert system to be useful in clinical practice.
• Nurses perceived the system as a promising tool for identifying potential child autism cases.
• Positive feedback was received regarding the system's diagnostic value and potential for early identification.

Conclusions:

• The developed expert system shows significant promise as a diagnostic aid for child autism.
• Implementation in clinical settings could improve the efficiency of identifying children with autism.
• Further integration and validation of the system are recommended for widespread clinical adoption.