A Machine Learning Technique for Reducing Hospital Readmissions for Diabetic Diseases
Mohammad Ismail1, D.Praveen Kumar Reddy2, K. Sai Srikanth3
1Dr. Mohammed Ismail , Professor CSE in KLEF Deemed to be University, Bachelor of Engineering Degree from Visvesvaraya Technological University, Belgaum India.
2D.Praveen, student of the Computer Science and Engineering Department at the Koneru Lakshmaiah Educational Foundation situated at Vaddeswaram, Guntur District.
3K.Sai Srikanth, student of the Computer Science and Engineering Department at the Koneru Lakshmaiah Educational Foundation situated at Vaddeswaram, Guntur District.
Manuscript received on November 14, 2019. | Revised Manuscript received on 23 November, 2019. | Manuscript published on December 10, 2019. | PP: 4878-4884 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6475129219/2019©BEIESP | DOI: 10.35940/ijitee.B6475.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: The number of readmissions in diabetic diseases keeps increasing from time to time in patients from various hospitals. This brings a dreadful name to the hospital and is also considered as an act of irresponsibility of the doctors. So in order to reduce the readmissions of diabetic patients, we propose an approach which uses a machine learning technique to compare the hospital records of various patients. We have used various diabetic dataset features for our technique to predict the readmission probability rates of patients. We compared our proposed technique with existing Machine Learning algorithms like Random Forest, K-means clustering, Support Vector Machine(SVM) and found the best possible prediction with proposed approach using receiver operating characteristic( ROC) curve.
Keywords: Natural language Handling, Medical data Frameworks, Decision Emotionally Supportive Networks, Data Mining, Feature Extraction
Scope of the Article: Machine Learning