Classification of the Disposition of Patients Hospitalized with COVID-19: Reading Discharge Summaries Using Natural Language Processing

Abstract

Background Medical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19. Objective Our study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes. Methods Text mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women’s Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set. Results The study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: “appointments specialty,” “home health,” and “home care” (home); “intubate” and “ARDS” (inpatient rehabilitation); “service” (SNIF); “brief assessment” and “covid” (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition. Conclusions A supervised learning–based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients’ discharge disposition that is possible with EHR data.

The Role of Natural Language Processing during the COVID-19 Pandemic: Health Applications, Opportunities, and Challenges

“…For instance, using a combination of NLP and ML methods enables the prediction of potential ICU admissions from the EHRs of patients with COVID-19 [ 37 ]. Another study used hospital discharge summary notes to develop an NLP pipeline to categorize the discharge dispositions of such patients [ 38 ]. Within the Department of Veterans Affairs (VA), a study developed an NLP system to extract possible positive COVID-19 cases from clinical text [ 39 ].…”

The Value of Extracting Clinician-Recorded Affect for Advancing Clinical Research on Depression: Proof-of-Concept Study Applying Natural Language Processing to Electronic Health Records

“…Using tools built around ontologies (controlled vocabularies), like SNOMED-CT (Systematized Nomenclature of Medicine-Clinical Terms) [11], NLP has enabled researchers to automate the capture of information in clinical narratives [10]. This data mining of EHRs can be useful for detecting patterns in patient care, such as choice of treatments, adherence, and changes in functioning and well-being over time [12], which can predict patient treatment habits and their symptom outcomes [13], as well as patient outcomes [14].…”

ARDSFlag: An NLP/Machine Learning Algorithm to Visualize and Detect High-Probability ARDS Admissions Independent of Provider Recognition and Billing Codes

“…ARDSFlag uses machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria. ML and NLP have been proven to offer strong potential for identifying and predicting complex medical conditions by incorporating EHR data [13][14][15][16] . We also develop a visualization that integrates all components of the Berlin criteria in one graph.…”