Data science methodologies in smart healthcare: a review

• Published in: Health and technology Vol. 12; no. 2; pp. 329 - 344
• Main Authors: Parida, Prasanta Kumar, Dora, Lingraj, Swain, Monorama, Agrawal, Sanjay, Panda, Rutuparna
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2022; Springer Nature B.V
• Subjects: Algorithms; Artificial intelligence; Big Data; Biological and Medical Physics; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Blood pressure; Classification; Cloud computing; Clustering; Computational Biology/Bioinformatics; Data mining; Data science; Decision making; Deep learning; Engineering; Health care; Health services; Interdisciplinary subjects; Internet of Things; Machine learning; Medical equipment; Medical imaging; Medical technology; Medicine/Public Health; Methods; Neural networks; Physicians; R & D/Technology Policy; Review Paper; Support vector machines; Deep learning; Smart healthcare; Data science technique; Machine learning
• ISSN: 2190-7188; 2190-7196
• DOI: 10.1007/s12553-022-00648-9

Data Science methodologies empower the representation and quantitative investigation in the field of smart healthcare. It is of extraordinary noteworthiness for early detection/classification of diseases for treatment planning. Nonetheless, there is a strong need to provide an in-depth survey of the existing methodologies highlighting their pros and cons to make them attractive for the researchers. The present study is an effort in this direction. The contribution made in this paper provides a new research path to the data science methodologies in smart healthcare, as opposed to the existing review articles. Recently, medical imaging investigation used deep learning (DL), as it defeats the limitations of the visual evaluation and the conventional machine learning methods for smart healthcare services. Research and methodologies are yet to be explored for the development of e-health. In this review paper, the uses of data science techniques in the clinical practice are highlighted. Also, it focuses on the state-of-the-art methods in the DL-based detection/classification of diseases. We emphasize the trends and challenges in smart healthcare as well as compare some baseline methods. This paper may be beneficial for the researchers to explore many more ideas covering all aspects of data science methodologies and applications for smart healthcare.