Scholarlink

<p>The use of Artificial Intelligence (AI) in healthcare monitoring is growing. Through the use of IoT sensors, which track the physiological state through a variety of health data, machine learning algorithms are used to monitor patient health. Thus, early diagnosis of any illness or mental disorder might help doctors save their patients’ lives. However, there are significant difficulties with utilizing the usual algorithms to forecast health statuses, such as time requirements, inaccuracies, and incorrect classification. The primary objective of this paper is to develop and evaluate an Artificial Ant Lion based Random Forest (AALRF) framework which leverages IoT sensors to collect and analyze patient data. First, a variety of patient records were gathered and used to train the system utilizing IoT sensors. Pre-processing also cleans up noises from the dataset, and feature extraction selects the important data. Then, the classification layer modified the ant lion’s fitness function to categorize the patient’s state of health and to produce a prescription. The proposed AALRF model demonstrated significant improvements over previous methods. It achieved an impressive accuracy of 99.52% in classifying health statuses and reduced the execution time to just 6&#xa0;s. These results underscore the model's potential in providing rapid and reliable health state categorization, ultimately aiding doctors in clinical judgment and prescription.</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

Design an Artificial Intelligence Based Machine Learning Framework for Improving Health Care Management

  • 期刊论文

  • 发表日期：

    2025年2月15日

查看全文
  • Vidhu Kiran Sharma,
  • Susheela Hooda

摘要

The use of Artificial Intelligence (AI) in healthcare monitoring is growing. Through the use of IoT sensors, which track the physiological state through a variety of health data, machine learning algorithms are used to monitor patient health. Thus, early diagnosis of any illness or mental disorder might help doctors save their patients’ lives. However, there are significant difficulties with utilizing the usual algorithms to forecast health statuses, such as time requirements, inaccuracies, and incorrect classification. The primary objective of this paper is to develop and evaluate an Artificial Ant Lion based Random Forest (AALRF) framework which leverages IoT sensors to collect and analyze patient data. First, a variety of patient records were gathered and used to train the system utilizing IoT sensors. Pre-processing also cleans up noises from the dataset, and feature extraction selects the important data. Then, the classification layer modified the ant lion’s fitness function to categorize the patient’s state of health and to produce a prescription. The proposed AALRF model demonstrated significant improvements over previous methods. It achieved an impressive accuracy of 99.52% in classifying health statuses and reduced the execution time to just 6 s. These results underscore the model's potential in providing rapid and reliable health state categorization, ultimately aiding doctors in clinical judgment and prescription.