Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding

• Published in: PloS one Vol. 15; no. 4; p. e0221606
• Main Authors: Liu, Wenshuo, Stansbury, Cooper, Singh, Karandeep, Ryan, Andrew M, Sukul, Devraj, Mahmoudi, Elham, Waljee, Akbar, Zhu, Ji, Nallamothu, Brahmajee K
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 15.04.2020; Public Library of Science (PLoS)
• Subjects: Aged; Aged, 80 and over; Algorithms; Artificial neural networks; Biology and Life Sciences; Cardiology; Codes; Computer and Information Sciences; Embedding; Female; Health care policy; Heart attacks; Heart failure; Hospitalization; Hospitals; Humans; Internal medicine; Logistic Models; Male; Medical schools; Medicine; Medicine and Health Sciences; Middle Aged; Model accuracy; Models, Biological; Myocardial infarction; Myocardial Infarction - diagnosis; Natural language processing; Neural networks; Neural Networks, Computer; Patient Readmission; Patients; Physical Sciences; Prediction models; Prognosis; Reclassification; Regression; Regression analysis; Representations; Research and Analysis Methods; Risk Assessment; Standardization; Ann Arbor Michigan; United States > US; Michigan
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0221606

Reducing unplanned readmissions is a major focus of current hospital quality efforts. In order to avoid unfair penalization, administrators and policymakers use prediction models to adjust for the performance of hospitals from healthcare claims data. Regression-based models are a commonly utilized method for such risk-standardization across hospitals; however, these models often suffer in accuracy. In this study we, compare four prediction models for unplanned patient readmission for patients hospitalized with acute myocardial infarction (AMI), congestive health failure (HF), and pneumonia (PNA) within the Nationwide Readmissions Database in 2014. We evaluated hierarchical logistic regression and compared its performance with gradient boosting and two models that utilize artificial neural networks. We show that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models improves prediction of 30-day readmission. Our best models increased the AUC for prediction of 30-day readmissions from 0.68 to 0.72 for AMI, 0.60 to 0.64 for HF, and 0.63 to 0.68 for PNA compared to hierarchical logistic regression. Furthermore, risk-standardized hospital readmission rates calculated from our artificial neural network model that employed embeddings led to reclassification of approximately 10% of hospitals across categories of hospital performance. This finding suggests that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.