Significant and Distinctive <i>n</i>-Grams in Oncology Notes: A Text-Mining Method to Analyze the Effect of OpenNotes on Clinical Documentation.

Abstract

OpenNotes is a national movement established in 2010 that gives patients access to their visit notes through online patient portals, and its goal is to improve transparency and communication. To determine whether granting patients access to their medical notes will have a measurable effect on provider behavior, we developed novel methods to quantify changes in the length and frequency of use of <i>n</i>-grams (sets of words used in exact sequence) in the notes. We analyzed 102,135 notes of 36 hematology/oncology clinicians before and after the OpenNotes debut at Beth Israel Deaconess Medical Center. We applied methods to quantify changes in the length and frequency of use of sequential co-occurrence of words (<i>n</i>-grams) in the unstructured content of the notes by unsupervised hierarchical clustering and proportional analysis of <i>n</i>-grams. The number of significant <i>n</i>-grams averaged over all providers did not change, but for individual providers, there were significant changes. That is, all significant observed changes were provider specific. We identified eight providers who were late note signers. This group significantly reduced its late signing behavior after OpenNotes implementation. Although the number of significant <i>n</i>-grams averaged over all providers did not change, our text-mining method detected major content changes in specific providers' documentation at the <i>n</i>-gram level. The method successfully identified a group of providers who decreased their late note signing behavior.