Diagnosis of Brain’s Health Condition through Smart ML Algorithm through Brain Waves

Mental health problems, when diagnosed early on, help professionals to provide better care to patients in the starting phase itself and improve the quality of life for the patients. Mental health issues, if not treated at an early age, lead to degradation in the conditions of patients. Machine learning techniques in recent years have given promising results in predicting patients' conditions. This study assessed the efficacy of five machine learning algorithms in detecting common mental health issues using various accuracy metrics, ROC, and classification reports. More than 1200 examples comprise the data collection gathered for approach testing and training. Fourteen – five crucial characteristics have been determined for the machine learning algorithms. The accuracy of the machine learning algorithms was compared. The decision tree classifier gave more accurate results, and the gap between their performances over the complete attribute set and the selected attribute set is insignificant and can be overcome by hyperparameter tunning. This research will be useful in developing a future health case system.