PROJECT TITLE :

A Natural Language Processing Framework for Assessing Hospital Readmissions for Patients with COPD - 2017

ABSTRACT:

With the passage of recent federal legislation several medical institutions are now accountable for reaching target hospital readmission rates. Chronic diseases account for many hospital readmissions and Chronic Obstructive Pulmonary Disease has been recently added to the list of diseases for which the United States government penalizes hospitals incurring excessive readmissions. Though there have been efforts to statistically predict those most at risk of readmission, few have focused primarily on unstructured clinical notes. We tend to have proposed a framework that uses Natural Language Processing to analyze clinical notes and predict readmission. Several algorithms at intervals the sector of knowledge mining and Machine Learning exist, therefore a framework for component choice is made to pick the best elements. Naïve Bayes using Chi-Squared Feature Selection offers an AUC of zero.690 while maintaining fast computational times.