A Platform based on Multiple Regression to Estimate the Effect of
in-Hospital Events on Total Charges
The paper main focus is to develop interactive web platform which utilizes a multiple linear
regression model that can predict total charges. The findings indicate that integration of
predictive models into clinical decision support systems is feasible. Medical claims data can
provide a useful estimation of the in-hospital charges. Hospital acquired conditions have
significant impact on the in-hospital charges.
The paper is divided and organized into the following sections
– The data that is used for the development of the platform
– Detailed information on the training and the performance of the predictive model.
– Architecture and functionality of the web platform with a use-case scenario
The attributes of the dataset are classified into 6 categories
– Admission information and demographics
– Discharge information
– Clinical outcomes
– Hospital Procedures
– Diagnoses
– Cost of care and diagnosis related groups
The categories of non-ordinary nominal attributes were transformed to binary attributes. A
