Scholarlink

The disease prediction system utilizes Multinomial Naive Bayes, Random Forest, K-Nearest Neighbor, Logistic Regression, Support Vector Machine, Decision Tree, Multilayer Perceptron, Voting Classifier, and Deep Learning Sequential models to accurately predict diseases based on observed symptoms. The system incorporates data preprocessing techniques, model training using multiple algorithms, evaluation, and disease prediction. The effectiveness of the system is evaluated using various evaluation metrics, providing insights into the accuracy and reliability of the predictions. The results demonstrate the potential of the system in assisting medical professionals in diagnosing diseases and making informed decisions. The highest accuracy is given by K-nearest neighbor (91.74%) and deep learning (91.68%).

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

Predictive Symptom Analysis of Machine Learning Techniques and Deep Learning for Disease Diagnosis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Pushkal Garg,
  • Deevesh Chaudhary,
  • Vivek Kumar,
  • Lala Arnav Vatsal

摘要

The disease prediction system utilizes Multinomial Naive Bayes, Random Forest, K-Nearest Neighbor, Logistic Regression, Support Vector Machine, Decision Tree, Multilayer Perceptron, Voting Classifier, and Deep Learning Sequential models to accurately predict diseases based on observed symptoms. The system incorporates data preprocessing techniques, model training using multiple algorithms, evaluation, and disease prediction. The effectiveness of the system is evaluated using various evaluation metrics, providing insights into the accuracy and reliability of the predictions. The results demonstrate the potential of the system in assisting medical professionals in diagnosing diseases and making informed decisions. The highest accuracy is given by K-nearest neighbor (91.74%) and deep learning (91.68%).