The dataset includes 121 children aged 7-12, with 61 diagnosed with ADHD based on DSM-IV criteria and 60 healthy controls without psychiatric disorders, epilepsy, or high-risk behaviors.
Key machine learning concepts like data preprocessing, feature engineering, and classification algorithms are employed. Data preprocessing involves handling missing values, normalizing features, and encoding categorical variables. Feature engineering extracts relevant information from demographic details, clinical history, and medication usage.
Various algorithms such as logistic regression, naive bayes estimator,Artificial Neural Networks(ANN), KMeans Clustering, Decision Tree for Level CLassification are evaluated to identify the most effective model for ADHD prediction.
Model performance is evaluated using metrics like accuracy, precision, recall, and F1-score to measure the model's ability to differentiate between children with ADHD and healthy controls.