Hospitalizations account for almost one-third of the total health care spending in the United States. A substantial portion of those hospitalizations are readmissions, which is why the Hospital Readmissions Reduction Program (HRRP) was created by CMS with the goal of improving the quality of care for patients and reducing healthcare spending.
The Centers for Medicare and Medicaid Services (CMS) now penalizes hospitals for excess readmissions rates for certain conditions, with up to a three percent payment reduction. For many health systems, this can translate into millions of dollars. In fact, just one or two excess readmissions in populations such as diabeties, Heart Failure and Knee Replacements can tip a hospital over its allowable readmission rate.
Diabetes is the condition with the 3rd most all-cause, 30-day readmissions for Medicaid patients, and in 2011, American hospitals spent over $41 billion caring for diabetic patients who were readmitted within 30 days of discharge. Readmission of diabetes patients can usually be avoided if additional attention is paid to these patients with high readmission risk and appropriate actions are taken. This makes early prediction of the hospital readmission risk an important problem. Being able to predict which patients will be readmitted, could help save hospitals billions of dollars while also improving quality of care.
The goal of this project is to see how well we can predict 30 day hospital readmission of diabetes patients, i.e. classify and identify patients that are at risk of being readmitted after being discharge. We should be able to predict whether the patient will be readmitted to the hospital or not. For predicting it most accurately we will be using various prediction models for this purpose.
Because this is a classification problem, to predict whether a patient will be readmitted or not, we will be using six different classifiers, namely, Support Vector Machines, Generalized logistic regression, Artificial Neural Networks, Random Forest Classifier, Naïve Bayes Classifier and Decision Trees. The models will also be used to help determine what factors are the most important in predicting hospital readmission for diabetic patients.
After building, training, and testing the model, our models should be able to classify patients(yes/no) being readmitted within 30 days.
The dataset represents 10 years (1999-2008) of clinical care at 130 US hospitals and integrated delivery networks. It consists of 10,000 records and 52 features representing patient and hospital outcomes. This dataset is made publicly avaliable by the UCI Machine Learning Repository.
The data contains such attributes as patient number, race, gender, age, admission type, time in hospital, medical specialty of admitting physician, number of lab test performed, HbA1c test result, diagnosis, number of medication, diabetic medications, number of outpatient, inpatient, and emergency visits in the year before the hospitalization, etc.
This dataset will undergo intense cleaning procedures to be ready for modeling.
Feature selection for these models will be done by conducting Correlation Analysis, and eliminating features with class imbalance. Data will be converted and pre-processed by removing null values and changing categorical variables.
Strack B, DeShazo JP, Gennings C, Olmo JL, Ventura S, Cios KJ, Clore JN: Impact of HbA1c measurement on hospital readmission rates: analysis of 70,000 clinical database patient records. Biomed Res Int 2014, 2014:781670
Centers for Disease Control and Prevention: National Diabetes Statistics Report, 2017. In. Edited by Centers for Disease Control and Prevention US Department of Health and Human Services. Atlanta, GA; 2017
OLeppin AL, Gionfriddo MR, Kessler M, Brito JP, Mair FS, Gallacher K, Wang Z, Erwin PJ, Sylvester T, Boehmer K et al: Preventing 30-day hospital readmissions: a systematic review and meta-analysis of randomized trials. JAMA Intern Med 2014, 174(7):1095-1107
Rubin DJ, Handorf EA, Golden SH, Nelson DB, McDonnell ME, Zhao H: Development and Validation of a Novel Tool to Predict Hospital Readmission Risk among Patients with Diabetes. Endocr Pract 2016, 22(10):1204-1215