Hospital readmissions are expensive and it also reflect the inadequacies in healthcare system. Early identification of patients facing high risk of readmission can enable healthcare providers to conduct additional investigations and possible prevention of readmissions. This not only improves the quality of health care but also reduces the medical expense on readmission.
Motivation: Diabetes is a chronic condition affecting people of all ages which serves as a precursor for other medical conditions and could trigger other health concerns in future. Once a person is diagnosed to have diabetes he is sure to have it for whole of his life. There is no wonder drug yet that can cure diabetes, but well managed diabetes gives a good quality of life. To serve this purpose, as to manage and avoid admittance or readmittance condition our project would act as a protocol.
Objective: In our project we leverage Machine learning methods on public health data to build a system for identifying diabetic patients facing a high risk of future readmission. The sensitivity is more desirable for hospitals because it is more crucial to correctly identify “high risk” patients who are to be readmitted than identifying “low risk” patients.
Dataset: https://archive.ics.uci.edu/ml/datasets/diabetes+130-us+hospitals+for+years+1999-2008
Step 1: Follow Link https://conda.io/docs/installation.html
Step 2: Clone Repository: git clone git@github.com:niyatpatel23295/diabetes-readmission-prediction.git
Step 3: Change directory: cd diabetes-readmission-prediction
Step 4: Navigate to web_server: cd web_server
Step 5: Start the server: FLASK_APP=server.py flask run