A Clinical Decision Support System for Identification of Factors Causing Stroke in Adults
Nonita Sharma1, Ravi Sharma2, Govind Singhal3, Punit Sharma4, Shouvik Banik5
1Nonita Sharma, Department of Computer Science and Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, India.
2Ravi Sharma, Department of Computer Science and Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, India.
3Govind Singhal, Department of Computer Science and Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, India.
4Punit Sharma, Department of Computer Science and Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, India.
5Shouvik Banik, Department of Computer Science and Engineering, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 1193-1197 | Volume-8 Issue-5, January 2020. | Retrieval Number: E5747018520/2020©BEIESP | DOI: 10.35940/ijrte.E5747.018520
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Among neurological patients, stroke is a significant concern that can lead to permanent disability or may cause death. Determining the contributing factors to stroke would better enable proactive forms of healthcare measures to be taken for reducing mortality and other effects of this disease. Numerous works have been carried out for determining the various factors which contribute to stroke. The goal of this work is to identify the factors which may cause stroke by proposing a Decision Support System. In this research work, various medical and psychological parameters are analyzed with the aim of determining association between these parameters and stroke. The methodology includes appropriate feature selection, attribute type conversion, univariate and multivariate analysis. Data mining techniques such as Chi square test and Frequency Distribution analysis are used for hypothesis testing and drawing inferences. The analysis shows that psychological factors such as Marital Status, Employment Status, and Age Group are the major contributors, which may lead to stroke in comparison to Medical factors. The findings can be used as a proactive measure for individuals who have high possibility of developing stroke. This work can also be used as a foundation to build a recommendation system for prevention of stroke.
Keywords: Correlation, Data mining, Decision Support Systems, Frequency Distribution, Healthcare, Stroke.
Scope of the Article: Data Mining.