Healthcare Monitoring System Driven by Machine Learning and Internet of Medical Things (MLIoMT)
Kutubuddin Sayyad Liyakat Kazi
Abstract
The primary objective of the project is to develop an ML-based healthcare system that can quickly and accurately diagnose a variety of diseases. Seven machine learning classification algorithms were used in this work to forecast nine deadly diseases, such as kidney disorders, hepatitis, diabetes, and blood pressure: adaptive boosting, Random Forest,DT, Support Vector Machines, Naïve Bayes, Artificial Neural Networks, and K-Nearest Neighbour. Performance metrics including Precision, Accuracy, and Recall are used to assess the suggested model's effectiveness. The performance of the classifiers is evaluated using four metrics: accuracy, precision, recall, and precision. For every ailment, the current healthcare model achieves a minimum accuracy of 82.3% and a maximum accuracy of 95.7%. There are minimal and maximum precision and recall values for each disease: 81.4% and 95.7%, respectively, and 64.3% and 90.3%, respectively. This ML driven IoMT approach we call as DL approach.