Scholarlink

<p>In today’s world, people experience a wide range of illnesses due to environmental changes, mainly pollution, heat waves and their lifestyle habits. Therefore, predicting diseases in their early stages is now a critical problem. Moreover, accurate symptom prediction becomes the most challenging task for a doctor. Therefore, machine learning plays a main role in disease prediction and solving this type of problem. Each year, a tonne of information is produced by the medical sciences in the form of datasets. Because of the increased amount of disease datasets in the healthcare and medical fields, an accurate picture of a specific disease prediction has benefited from early patient safety. Accordingly, machine learning is used to uncover hidden patterns present inside the disease datasets. To accurately identify disease, we intended to apply the machine learning classifiers Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Multi-Layer Perceptron (MLP), Stochastic Gradient Descent (SGD), Linear Discriminant Analysis (LD), Adaboost (AB), and Gradient Boosting (GB). The study identifies the best classifiers based on their accuracy, precision, recall, F1 and hamming loss. The outcomes of this experimental study show that the LR and MLP classifiers perform best in a disease prediction context and can properly deal with these disease datasets relatively well compared to all the other machine learning classifiers.</p>

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

The Experimental Study of Machine Learning Classifiers for Disease Prediction

  • 期刊论文

  • 发表日期：

    2025年9月25日

查看全文
  • Biswajit Senapati,
  • Ranjita Das

摘要

In today’s world, people experience a wide range of illnesses due to environmental changes, mainly pollution, heat waves and their lifestyle habits. Therefore, predicting diseases in their early stages is now a critical problem. Moreover, accurate symptom prediction becomes the most challenging task for a doctor. Therefore, machine learning plays a main role in disease prediction and solving this type of problem. Each year, a tonne of information is produced by the medical sciences in the form of datasets. Because of the increased amount of disease datasets in the healthcare and medical fields, an accurate picture of a specific disease prediction has benefited from early patient safety. Accordingly, machine learning is used to uncover hidden patterns present inside the disease datasets. To accurately identify disease, we intended to apply the machine learning classifiers Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Multi-Layer Perceptron (MLP), Stochastic Gradient Descent (SGD), Linear Discriminant Analysis (LD), Adaboost (AB), and Gradient Boosting (GB). The study identifies the best classifiers based on their accuracy, precision, recall, F1 and hamming loss. The outcomes of this experimental study show that the LR and MLP classifiers perform best in a disease prediction context and can properly deal with these disease datasets relatively well compared to all the other machine learning classifiers.