Smart Healthcare Analytics Solutions Using Deep Learning AI
Machine learning is widely used in various applications such as business organizations, e-commerce, and healthcare industry, scientific and engineering for predicting and discovering relationships among data. In the healthcare industry, the predictive ana
- PDF / 377,180 Bytes
- 8 Pages / 439.37 x 666.142 pts Page_size
- 9 Downloads / 208 Views
Abstract Machine learning is widely used in various applications such as business organizations, e-commerce, and healthcare industry, scientific and engineering for predicting and discovering relationships among data. In the healthcare industry, the predictive analytics in machine learning is mainly used for disease prediction. ML techniques help in predicting relationships in the electronic health record (EHR) data. The clinical process guidelines in the corpus may be considered as one of the inputs, and various healthcare parameters can be feature scaled, and the resultant architecture provides a positive impact in healthcare systems decision making. The objective of this work is to determine suitable features and optimal classifier design for a Deep Learning Healthcare Diagnosis system (DLHDS) to differentiate the endothelial dysfunction. It is used to predict under-perfused as wells as over-perfused tissues during dynamic contrast material–enhanced magnetic resonance (MR) imaging of the peripheral vascular and muscular system. Early detection of disease and by mapping the drug side effects with patient histories is the needed approach for future prescriptions. The real-time applications of knowledge acquisition of healthcare data research require deep learning healthcare diagnosis systems. This paper presents deep learning service share model architecture for the generalizations of knowledge processing which is available in form of cloud and by using various parameters which enhances the assistive intelligence. By using semi-supervised machine learning techniques, features are reduced based on their nature of correlation in EHR and analyzed by ML techniques classifier and achieved an accuracy of 97%, and it outperforms the other existing prediction models, and this improves the throughput in the prediction of diseases. Keywords Electronic health record · Predictive analytics · Semi-supervised approach · Machine learning techniques · Deep learning K. P. Subiksha (B) Olive Tree Consultives and Freelancing, Bengaluru, India e-mail: [email protected] M. Ramakrishnan School of Information Technology, Madurai Kamara University, Madurai, India © Springer Nature Singapore Pte Ltd. 2021 V. K. Gunjan and J. M. Zurada (eds.), Proceedings of International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, Advances in Intelligent Systems and Computing 1245, https://doi.org/10.1007/978-981-15-7234-0_67
707
708
K. P. Subiksha and M. Ramakrishnan
1 Introduction Third wave AI technologies and contextual adaptation and Natural communication, and breakthrough of algorithms, had begun to have explosive causal models development [1]. EHR data and clinical text written by healthcare professionals to communicate the status and history of a single patient to other healthcare professionals or themselves and its time and visibility are eased [2] via machine learning. The major components of a healthcare system are the health professionals such as physicians or nurses, health faci
Data Loading...
