Prediction of Emergency Department Hospital Admission Based on Natural Language Processing and Neural Networks
- 1 January 2017
- journal article
- Published by Georg Thieme Verlag KG in Methods of Information in Medicine
- Vol. 56 (05), 377-389
- https://doi.org/10.3414/me17-01-0024
Abstract
Summary Objective: To describe and compare logistic regression and neural network modeling strategies to predict hospital admission or transfer following initial presentation to Emergency Department (ED) triage with and without the addition of natural language processing elements. Methods: Using data from the National Hospital Ambulatory Medical Care Survey (NHAMCS), a cross-sectional probability sample of United States EDs from 2012 and 2013 survey years, we developed several predictive models with the outcome being admission to the hospital or transfer vs. discharge home. We included patient characteristics immediately available after the patient has presented to the ED and undergone a triage process. We used this information to construct logistic regression (LR) and multilayer neural network models (MLNN) which included natural language processing (NLP) and principal component analysis from the patient’s reason for visit. Ten-fold cross validation was used to test the predictive capacity of each model and receiver operating curves (AUC) were then calculated for each model. Results: Of the 47,200 ED visits from 642 hospitals, 6,335 (13.42%) resulted in hospital admission (or transfer). A total of 48 principal components were extracted by NLP from the reason for visit fields, which explained 75% of the overall variance for hospitalization. In the model including only structured variables, the AUC was 0.824 (95% CI 0.818-0.830) for logistic regression and 0.823 (95% CI 0.817-0.829) for MLNN. Models including only free-text information generated AUC of 0.742 (95% CI 0.7310.753) for logistic regression and 0.753 (95% CI 0.742-0.764) for MLNN. When both structured variables and free text variables were included, the AUC reached 0.846 (95% CI 0.839-0.853) for logistic regression and 0.844 (95% CI 0.836-0.852) for MLNN. Conclusions: The predictive accuracy of hospital admission or transfer for patients who presented to ED triage overall was good, and was improved with the inclusion of free text data from a patient’s reason for visit regardless of modeling approach. Natural language processing and neural networks that incorporate patient-reported outcome free text may increase predictive accuracy for hospital admission.Keywords
This publication has 60 references indexed in Scilit:
- Automatic Prediction of Rheumatoid Arthritis Disease Activity from the Electronic Medical RecordsPLOS ONE, 2013
- Comparative Study of Four Time Series Methods in Forecasting Typhoid Fever Incidence in ChinaPLOS ONE, 2013
- Early Hospital Readmission is a Predictor of One-Year Mortality in Community-Dwelling Older Medicare BeneficiariesJournal of General Internal Medicine, 2012
- Natural language processing: an introductionJournal of the American Medical Informatics Association, 2011
- Text mining for the Vaccine Adverse Event Reporting System: medical text classification using informative feature selectionJournal of the American Medical Informatics Association, 2011
- Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosisComputers in Biology and Medicine, 2011
- Access block and emergency department overcrowdingCritical Care, 2011
- Application of support vector machine modeling for prediction of common diseases: the case of diabetes and pre-diabetesBMC Medical Informatics and Decision Making, 2010
- What can natural language processing do for clinical decision support?Journal of Biomedical Informatics, 2009
- A study to derive a clinical decision rule for triage of emergency department patients with chest pain: design and methodologyBMC Emergency Medicine, 2008