Investigating Resuscitation Code Assignment in the Intensive Care Unit using Structured and Unstructured Data

This study investigates the feasibility of using structured data (age, gender, and medical condition), and unstructured medical notes on classification accuracy for resuscitation code status. Data was extracted from the MIMICII database. Natural language processing (NLP) was used to evaluate the social section of the nurses' progress notes. BoosTexter was used to predict the code-status using notes, age, gender, and Simplified Acute Physiology Score (SAPS). The relative impact of features was analyzed by feature ablation. Unstructured notes were the greatest single indicator of code status. The addition of text to medical condition features increased classification accuracy significantly (p<0.001.) N-gram frequency was analyzed. Gender differences were noted across all code-statuses, with women always more frequent (e.g. wife>husband.) Logistic regression on structured features was used determine gender bias or ageism. Evidence of bias was found; both females (OR=1.45) and patients over age 70 (OR=3.72) were more likely to be Do-Not-Resuscitate (DNR).