Scalable and accurate deep learning with electronic health records

Alvin Rajkomar,Michael Pearson,Nissan Hajaj,Katherine Chou,Jake Marcus,Alexander Mossin,Peter J Liu,De Wang,Kun Zhang,Atul J Butte,Xiaobing Liu,Kai Chen,Eyal Oren,Gerardo Flores,Michael D Howell,Patrik Sundberg,Hector Yee,Srinivasan Madabushi,Gavin E Duggan,Yi Zhang,Nigam H Shah,Claire Cui,Justin Tansuwan,Kurt Litsch,Michaela Hardt,Greg S Corrado,Quoc V Le ,Samuel L Volchenboum,Jamie Irvine,Mimi Sun,Dana Ludwig,Jimbo Wilson,James Wexler,Andrew M Dai,J Michael Dean

doi:10.1038/s41746-018-0029-1

Abstract

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient’s record. We propose a representation of patients’ entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93–0.94), 30-day unplanned readmission (AUROC 0.75–0.76), prolonged length of stay (AUROC 0.85–0.86), and all of a patient’s final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient’s chart.

Highlights

The promise of digital medicine stems in part from the hope that, by digitizing health data, we might more leverage computer information systems to understand and improve care
For predictions made at discharge, the information considered across both datasets included 46,864,534,945 tokens of electronic health record (EHR) data
The area under the receiver operating characteristic curve (AUROC) at 24 h after admission was 0.95 for Hospital A and 0.93 for Hospital B

Summary

Introduction

The promise of digital medicine stems in part from the hope that, by digitizing health data, we might more leverage computer information systems to understand and improve care. In spite of the richness and potential of available data, scaling the development of predictive models is difficult because, for traditional predictive modeling techniques, each outcome to be predicted requires the creation of a custom dataset with specific variables.[7] It is widely held that 80% of the effort in an analytic model is preprocessing, merging, customizing, and cleaning datasets,[8,9] not analyzing them for insights. This profoundly limits the scalability of predictive models

Methods

Results

Conclusion