Scholarlink

In the recent few years many people started to realize the importance of mental health. In addition to taking care of our bodies we must also take care of our brains and emotions. The Neuro disorders: Depressive Bipolar Disorder, Mania Bipolar Disorder, and Major Depressive Disorder also present diagnostic and therapeutic complexity. The current paper utilises machine learning algorithms to forecast the neuro disorders based on a new dataset comprising of 120 patients with different mental illnesses. This dataset includes 17 core symptoms which have been primarily employed by psychiatrists for defining these disorders. Five supervised machine learning models, Random Forest, SVM, Decision Tree, KNN, and Naive Bayes, are applied for classifying individuals into four categories i.e., three disorders and a normal category. In this study, the SVM model had the optimal accuracy of 86% and such a model can help the mental health practitioners in diagnosis. The dataset was cleaned and tested using several libraries such as Scikit Learn, NumPy, and Pandas. This work shows that utilization of ML models may be effective in increasing diagnostic precision for mental health ailments.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Enhanced and Optimised Neuro Disorder Prediction Using Random Forest Classifier

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Kavya Sunki,
  • M. Sahiti,
  • B. V. Ramana Murthy,
  • Venkata Krithik Bhamidipati

摘要

In the recent few years many people started to realize the importance of mental health. In addition to taking care of our bodies we must also take care of our brains and emotions. The Neuro disorders: Depressive Bipolar Disorder, Mania Bipolar Disorder, and Major Depressive Disorder also present diagnostic and therapeutic complexity. The current paper utilises machine learning algorithms to forecast the neuro disorders based on a new dataset comprising of 120 patients with different mental illnesses. This dataset includes 17 core symptoms which have been primarily employed by psychiatrists for defining these disorders. Five supervised machine learning models, Random Forest, SVM, Decision Tree, KNN, and Naive Bayes, are applied for classifying individuals into four categories i.e., three disorders and a normal category. In this study, the SVM model had the optimal accuracy of 86% and such a model can help the mental health practitioners in diagnosis. The dataset was cleaned and tested using several libraries such as Scikit Learn, NumPy, and Pandas. This work shows that utilization of ML models may be effective in increasing diagnostic precision for mental health ailments.