Clinical Data Fusion and Machine Learning Techniques for Smart Healthcare
Shrida P. Kalamkar, Geetha Mary Amalanathan · 2020
Healthcare applications produce a large amount of data from multiple heterogeneous healthcare devices. These heterogeneous devices produce data in different formats. In clinical decisions, generally, one source of information may not be able to achieve an accurate decision. For accurate analysis, heterogeneous data can be fused, which in turn helps to develop a more understanding of a particular disease. Fusing data from diverse sources like clinical repositories, sensory devices, historical or textual data is vital for both patients and healthcare providers. However, with the increasing number of sensory devices, the complexity of data fusion is also increasing. Various issues like complex distributed processing, unreliable data communication, the uncertainty of data analysis, data transmission at different rates have identified. This paper aims to present different perspectives of data fusion to evaluate healthcare applications based on these issues.Further, these proposed different perceptual classifications are applied to assess applications in the healthcare domain. We highlight the challenges of data fusion in the healthcare domain and discuss future research opportunities for data fusion in healthcare. We also offer a brief introduction to data fusion and machine learning by discussing some of the applications and typical techniques.