Publication Type : Conference Paper
Publisher : 2016 International Conference on Computing, Communication and Automation (ICCCA)
Source : 2016 International Conference on Computing, Communication and Automation (ICCCA) (2016)
Url : http://ieeexplore.ieee.org/abstract/document/7813730/
ISBN : 9781509016662
Accession Number : 16585527
Keywords : Adaboost, Arthritis, chronic diseases, claims data, clinical data, clinical relevance, CMS data, Data mining, diabetes, diagnostic codes, diagnostic tests, Diseases, drugs data, Health care, Healthcare, Heart, hospital data, ICD9 codes, InfoGain, kidney disease, learning (artificial intelligence), Machine learning, medical diagnostic computing, Medical diagnostic imaging, medical practitioner, osteoporosis, Predictive models
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science, Mathematics
Year : 2016
Abstract : Healthcare in simplest form is all about diagnosis and prevention of disease or treatment of any injury by a medical practitioner. It plays an important role in providing quality life for the society. The concern is how to provide better service with less expensive therapeutically equivalent alternatives. Machine Learning techniques (ML) help in achieving this goal. Healthcare has various categories of data like clinical data, claims data, drugs data and hospital data. This paper focuses on clinical and claims data for studying 11 chronic diseases such as kidney disease, osteoporosis, arthritis etc. using the claims data. The correlation between the chronic diseases and the corresponding diagnostic tests is analyzed, by using ML techniques. An effective conclusion on various diagnostics for each chronic disease is made, keeping in mind the clinical relevance.
Cite this Research Publication : Dr. Deepa Gupta, Khare, S., and Aggarwal, A., “A method to predict diagnostic codes for chronic diseases using machine learning techniques”, in 2016 International Conference on Computing, Communication and Automation (ICCCA), 2016.