Mental Health Mapper: AI Strategies for Understanding Disorders

This work studies the efficacy of classifiers using machine learning in detecting mental health disorders based on a variety of variables. Four classifiers, the Emotion Spectrum Classification algorithm, Psychology Profile Predictor, Mood Disorders Identifier, and Cognitive Functioning Classifier, are assessed utilising recall, precision, F1-score, support, supporting ratio, and accuracy metrics. The Emotion Spectrum Classifier has precision, recall, and F1-scores of 92.59%, 98.59%, and 98.42%, respectively, and an accuracy of 0.99 based on 1420 examples. The Psychological Profiles Predictor has a precision, recall, or F1-score score 91.23%, 92.86%, or 92.04%, respectively, and an accuracy of 0.96, calculated from 2800 cases. In a similar vein the Mood Disorder Identifier has precision, recall, and F1-scores of 93.55%, 92.06%, and 92.80%, respectively. With a precision of 0.96 and an availability of 3150 instances. Furthermore, the Cognitive Activity Classifier achieves precision, recall, and F1-scores of 92.31%, 93.75%, and 93.02%, respectively, with a precision of 0.96, based on 3200 instances. The macro, weighted, or micro average statistics provide comprehensive information about overall classifier performance. Overall, this study emphasises the efficacy of artificial intelligence classifiers in properly identifying mental health disorders, providing useful insights for health professionals as well as researchers in the field.