Semester of Graduation

Spring 2019

Degree

Master of Science in Computer Science (MSCS)

Department

Computer Science

Document Type

Thesis

Abstract

The primary focus of this paper is the creation of a Machine Learning based algorithm for the analysis of large health based data sets. Our input was extracted from MIMIC-III, a large Health Record database of more than 40,000 patients. The main question was to predict if a patient will have complications during certain specified procedures performed in the hospital. These events are denoted by the icd9 code 996 in the individuals' health record. The output of our predictive model is a binary variable which outputs the value 1 if the patient is diagnosed with the specific complication or 0 if the patient is not. Our prediction algorithm is based on a Neural Network architecture, with a 90%-10% training-testing ratio. Our preliminary analysis yielded a prediction accuracy above 80%, outperforming various multi-linear models. A comparative analysis of various optimizers as well as time based performance measures is also included.

Date

12-25-2018

Committee Chair

Busch, Konstantin

Share

COinS