Diabetes_predictive_model
We designed, implemented and compared various regression and classification models on Diabetics patient data.
predictive models used: Multiple Linear Regression (MLR), Naive Bayes, Decision Tree, Logistic Regression, Artificial Neural Networks (ANN).
Target Variables: Time in Hospital (Regression), Change in medication (Binary Classification)
For more detailed information, review attached PDFs, and presentation files.
The Platform used: KNIME (https://www.knime.com/)
Dataset used: Diabetes 130-US hospitals for years 1999-2008 Data Set (http://archive.ics.uci.edu/ml/datasets/Diabetes+130-US+hospitals+for+years+1999-2008)
Base Paper on data: Impact of HbA1c Measurement on Hospital Readmission Rates: Analysis of 70,000 Clinical Database Patient Records (https://www.hindawi.com/journals/bmri/2014/781670/)
useful links:
https://en.wikipedia.org/wiki/List_of_ICD-9_codes
https://www.knime.com/learning/cheatsheets
https://docs.knime.com/2019-06/analytics_platform_quickstart_guide/index.html