Enhanced Autism Prediction Using YOLO V11 And Random Forest on Clinical Data

diagnostic techniques can be laborious and rely significantly on subjective evaluations, but early discovery is essential for prompt management. To overcome these limitations, machine learning techniques particularly Convolutional Neural Networks (CNNs), have been explored for ASD detection. However, existing models often fall short terms of reliability and accuracy for real-world applications. Our proposed approach enhances ASD prediction by integrating the YOLO V11 algorithm with the Autism Clinical Dataset, leveraging its efficiency in object detection and classification to analyze behavioral patterns associated with ASD. Additionally, we incorporate the Random Forest algorithm for dataset training, which significantly improves classification performance. Experimental result demonstrate that our model achieve an impressive 98.5% accuracy with 97.8% precision, 98.2% recall and an F1-score of 98.0% ensuring a highly reliable prediction system. By combining these advanced techniques, our model offers faster and more precise ASD detection paving way for earlier diagnoses and better-informed treatment plans, ultimately improving the quality of life for individuals with ASD.