Scalable and accurate deep learning with electronic health records
Масштабируемое и точное глубокое обучение с использованием электронных медицинских карт
2018-05-04
SCID: 54.1/sj5xnsw5
Discuss with AI
FHIR formatclinical event predictiondeep learningelectronic health recordspersonalized medicine
Figures from the paper
Abstract (AI)
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.
Key Findings
1
A FHIR-based sequential representation preserves patients’ entire raw EHRs, including clinical notes, avoiding labor-intensive predictor curation and information loss.
2
A case study showed that neural networks can identify clinically relevant information within patients’ raw charts, supporting scalable prediction across diverse clinical scenarios.
3
Deep learning models using raw EHR representations accurately predicted multiple medical outcomes across two centers without site-specific data harmonization.
4
The models predicted all final discharge diagnoses with a frequency-weighted AUROC of 0.90 and outperformed traditional clinically used predictive models across every evaluated task.
5
Using data from 216,221 hospitalized adults and 46,864,534,945 sequential data points, models achieved AUROCs of 0.93–0.94 for in-hospital mortality, 0.75–0.76 for 30-day unplanned readmission, and 0.85–0.86 for prolonged length of stay.
Research Object
Entire raw electronic health record (EHR) data of hospitalized adult patients represented in FHIR sequential format
Research Subject
Accurate, scalable, and cross-center prediction of multiple medical events from sequential EHR data, including mortality, readmission, prolonged length of stay, and discharge diagnoses
Publication Details
Publication Date
2018-05-04
Journal
Publisher
ISSN
Cited by
3209
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Scikit-learn: Machine Learning in Python2012
Representation Learning: A Review and New Perspectives2013
Infectious Diseases Society of America/American Thoracic Society Consensus Guidelines on the Management of Community-Acquired Pneumonia in Adults2007
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation2016
Cited by12
The potential for artificial intelligence in healthcare2019
Key challenges for delivering clinical impact with artificial intelligence2019
An overview of deep learning in medical imaging focusing on MRI2018
Precision Medicine, AI, and the Future of Personalized Health Care2020
Artificial Intelligence and Deep Learning in Ophthalmology2018
Redefining Radiology: A Review of Artificial Intelligence Integration in Medical Imaging2023
Automated machine learning: Review of the state-of-the-art and opportunities for healthcare2020
Introducing Artificial Intelligence Training in Medical Education2019
Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness2020
The Application of Deep Learning in Cancer Prognosis Prediction2020
Finding missed cases of familial hypercholesterolemia in health systems using machine learning2019
Explainable AI: A review of applications to neuroimaging data2022