IoT in Healthcare: Transforming Patient Care with Engineering, Computer Science, and Medicine

Abstract

Internet of Things (IoT) integration into healthcare has taken patient care to a whole new level by means of real time monitoring, predicting results and decision making. In this research, engineering, computer science, and medicine unite to create a smart healthcare framework that uses four machine learning algorithms namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Random Forest (RF), and Artificial Neural Networks (ANN). The synthetic IoT based patient data used in the study simulated heart rate, temperature, oxygen level and blood pressure parameters. To determine the efficiency in which each algorithms diagnosed patients conditions, we evaluated each algorithm in terms on accuracy, precision, recall, and F1 score. Experimental results showed that ANN had the highest accuracy of 94.6%, RF 91.8%, SVM 89.5%, and KNN 86.3%. Likewise, ANN also produced better recall and precision, and hence, it became the more reliable model in this healthcare setting. The research shows how the diagnostic speed and accuracy can be improved by integrating high IoT devices along with intelligent algorithms, and by minimizing costs of healthcare and maximizing the patient outcomes. The study concludes with the significance of ethical data practice and the need of future integration of secure frameworks like blockchain to create highly scalable, trustworthy healthcare systems.