Readmission Prediction of Diabetic based on Convolutional Neural Networks

Unplanned readmission expenses have always accounted for a large part of the expenditure of the health care system, and reducing hospital readmission rate is important for the government to reduce the financial burden and improving hospital efficiency. First of all, we preprocess the readmission records of patients, including feature creation, feature selection, imbalanced data processing, and data reduction. Then we compare the traditional machine learning algorithms and propose a convolution neural networks model combined with PCA. The experimental results show that the accuracy of the readmission prediction is effectively guaranteed, and the AUC reaches 0.97.

[1]  Malladihalli S. Bhuvan,et al.  Identifying Diabetic Patients with High Risk of Readmission , 2016, ArXiv.

[2]  Xing Yifan Jai Sharma.  Diabetes patient Readmission Prediction using Big Data Analytic tools , 2015 .

[3]  Yue Zhao,et al.  A review of Convolutional Neural Networks in Remote Sensing Image , 2019, ICSCA.

[4]  Z. Kong,et al.  A Metaheuristic LASSO Model for Diabetic Readmission Prediction , 2016 .

[5]  Ahmad Hammoudeh,et al.  Predicting Hospital Readmission among Diabetics using Deep Learning , 2018, EUSPN/ICTH.

[6]  Grant S. Fletcher,et al.  International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions. , 2016, JAMA internal medicine.

[7]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[8]  Damian R Mingle,et al.  Predicting Diabetic Readmission Rates: Moving Beyond Hba1c , 2017 .

[9]  Yaochu Jin,et al.  An improved support vector machine-based diabetic readmission prediction , 2018, Comput. Methods Programs Biomed..

[10]  Beata Strack,et al.  Impact of HbA1c Measurement on Hospital Readmission Rates: Analysis of 70,000 Clinical Database Patient Records , 2014, BioMed research international.

[11]  V. K. Bhalla,et al.  Predicting readmissions: poor performance of the LACE index in an older UK population. , 2012, Age and ageing.

[12]  Francisco Herrera,et al.  SMOTE-IPF: Addressing the noisy and borderline examples problem in imbalanced classification by a re-sampling method with filtering , 2015, Inf. Sci..