Prognosis analysis of thick data: Clustering heart diseases risk groups case study. (June 2021)

• Record Type: Journal Article
• Authors: Fiaidhi, J.; Mohammed, S.
• Is Part Of: Computers & electrical engineering. Volume 92(2021)
• Publication Date: 2021-06
• Subjects: Thick Data -- Prognosis Analysis -- Fuzzy Clustering -- Small Datasets -- Healthcare Data -- Risk Analysis -- Machine Learning; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107187
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Analyzing clinical data differs from other machine learning data analysis as most of the clinical data are relatively small requiring more qualitative techniques to bring focus to the context and then to predict important indicators like the patient risk in developing heart disease. The strength of qualitative analytics lies in data thickness as they can work on small samples and corpuses ("small data"). However, working with thick data analytics requires involving patient characteristics (e.g. socioeconomic status, family background, working conditions, social support, psycho-social characteristics, lifestyle risk factors, age group, gender and social capital) and their weights in a particular clinical practice. Therefore, the role of patient characteristics is not only a dominant factor in thick data analytics but it is also linked to predicting the prognosis of patient cases. A Fuzzy C-Means algorithm is presented as technique for prognostic predictions to identify risk groups associated with Cardiovascular Disease (CVD) conditions.