Scholarlink

A few of the ongoing diseases that are becoming more prevalent every year is diseases mellitus (i.e., diabetes). Diabetes that is not under control may increase the chance of additional ailments like tumors, kidney failure, and eyesight. This paper conducts a comparative analysis to address the aforementioned problems, relying on classification and prediction techniques. In this research, classification techniques are used and data is sourced from the Pima Indian Diabetic Database at the UCI Machine Learning Laboratory. The dataset contains the female patient data. With the quick growth of machine learning, several facets of medical health have benefited. In this study, a comparative analysis has been conducted to predict the diabetes in females using machine learning classification on a dataset that includes Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). After analyzing the statistical results, it has been observed that the RF outperforms with a maximum accuracy of 76%.

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

Diabetes Prediction in Females Using Machine Learning Algorithms

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nitin Kumar,
  • Tarun Kumar Sharma,
  • Sumika Jain

摘要

A few of the ongoing diseases that are becoming more prevalent every year is diseases mellitus (i.e., diabetes). Diabetes that is not under control may increase the chance of additional ailments like tumors, kidney failure, and eyesight. This paper conducts a comparative analysis to address the aforementioned problems, relying on classification and prediction techniques. In this research, classification techniques are used and data is sourced from the Pima Indian Diabetic Database at the UCI Machine Learning Laboratory. The dataset contains the female patient data. With the quick growth of machine learning, several facets of medical health have benefited. In this study, a comparative analysis has been conducted to predict the diabetes in females using machine learning classification on a dataset that includes Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT). After analyzing the statistical results, it has been observed that the RF outperforms with a maximum accuracy of 76%.