Utilizing uncoded consultation notes from electronic medical records for predictive modeling of colorectal cancer

• The paper studies several natural language processing (NLP) techniques to extract predictors from uncoded data in electronic medical records (EMRs).
• Some techniques are well-known while other have been developed specifically for this research.
• The approaches have been applied to a large dataset we have access to, covering 90,000 patients in general practices.
• We focus on predictive modelling of colorectal cancer, which is a challenging disease to study as it is a common type of cancer, while the symptoms are very a-specific for the disease.
• The results show that some of the NLP techniques studied can complement the coded EMR data, and hence, result in improved predictive models.

ObjectiveMachine learning techniques can be used to extract predictive models for diseases from electronic medical records (EMRs). However, the nature of EMRs makes it difficult to apply off-the-shelf machine learning techniques while still exploiting the rich content of the EMRs. In this paper, we explore the usage of a range of natural language processing (NLP) techniques to extract valuable predictors from uncoded consultation notes and study whether they can help to improve predictive performance.MethodsWe study a number of existing techniques for the extraction of predictors from the consultation notes, namely a bag of words based approach and topic modeling. In addition, we develop a dedicated technique to match the uncoded consultation notes with a medical ontology. We apply these techniques as an extension to an existing pipeline to extract predictors from EMRs. We evaluate them in the context of predictive modeling for colorectal cancer (CRC), a disease known to be difficult to diagnose before performing an endoscopy.ResultsOur results show that we are able to extract useful information from the consultation notes. The predictive performance of the ontology-based extraction method moves significantly beyond the benchmark of age and gender alone (area under the receiver operating characteristic curve (AUC) of 0.870 versus 0.831). We also observe more accurate predictive models by adding features derived from processing the consultation notes compared to solely using coded data (AUC of 0.896 versus 0.882) although the difference is not significant. The extracted features from the notes are shown be equally predictive (i.e. there is no significant difference in performance) compared to the coded data of the consultations.ConclusionIt is possible to extract useful predictors from uncoded consultation notes that improve predictive performance. Techniques linking text to concepts in medical ontologies to derive these predictors are shown to perform best for predicting CRC in our EMR dataset.