Intelligent Decision Support System for Healthcare

Abstract

The advanced technologies of the Internet of Things (IoT) provide modern environments support for medical applications and produce a vast amount of various types of health care data, such as sensors data, clinical data, omic data, and later transfer these data to Machine learning (ML) component for data extraction, its classification, and mining, and use the filtered data for prediction of the diseases. Further, Machine learning algorithms are facilitating mathematical comparison of collected datasets for decision making systems which can identify the current trend and forecasts future issues through learning. ML-based approaches can evaluate the conditions according to the data collection. Learning datasets play an important role in predicting accurately the existing and new problems future trends. Performance of learning models depends on the quality of data collection, therefore any distorted data of type grimy data, noisy data, messy data, and incomplete information leads to erroneous detection, estimation, and prediction. Further, the experimental results display the effectiveness of the proposed approach as an efficient adoption of machine learning algorithms into IoT applications in contrary to other models.