Scholarlink

Mental health issues is a serious ailment that affects a vast number of people. Improving the health quality of patients is an utmost issue that no nation can afford to ignore. Deterioration of mental health can be due to the factors like stress, depression, lack of activity, and many other reasons. Various machine learning algorithms will be used to forecast early prognosis in the human body for a higher degree of precision by building models from patient-generated information forecasting outcomes more accurately. The current paper will predict the stress using ensemble techniques and machine learning classification algorithms on the dataset, which includes a K-Nearest Neighbours Classifier (KNN), Logistic Regression (LR), Decision Trees (DT), Random Forest Classifier (RFC), AdaBoost and Hist Gradient Boosting. When compared to other models, each model’s precision varies. The research demonstrates that the model can accurately forecast with a 97.5% confidence level with Hist Gradient Boosting, 68% for the AdaBoost, 77.4% for gradient boosting, 68% for logistic regression and 57% for linear SVC. Ensemble machine learning is an active research field in prediction and working as an efficient detection system.

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

Early Diagnosis and Prediction of Mental Health Using Ensemble Learning Model

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Yashika,
  • Seema Rani,
  • Sanjeev Kumar

摘要

Mental health issues is a serious ailment that affects a vast number of people. Improving the health quality of patients is an utmost issue that no nation can afford to ignore. Deterioration of mental health can be due to the factors like stress, depression, lack of activity, and many other reasons. Various machine learning algorithms will be used to forecast early prognosis in the human body for a higher degree of precision by building models from patient-generated information forecasting outcomes more accurately. The current paper will predict the stress using ensemble techniques and machine learning classification algorithms on the dataset, which includes a K-Nearest Neighbours Classifier (KNN), Logistic Regression (LR), Decision Trees (DT), Random Forest Classifier (RFC), AdaBoost and Hist Gradient Boosting. When compared to other models, each model’s precision varies. The research demonstrates that the model can accurately forecast with a 97.5% confidence level with Hist Gradient Boosting, 68% for the AdaBoost, 77.4% for gradient boosting, 68% for logistic regression and 57% for linear SVC. Ensemble machine learning is an active research field in prediction and working as an efficient detection system.