Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence
Top Cited Papers
- 11 February 2019
- journal article
- research article
- Published by Springer Science and Business Media LLC in Nature Medicine
- Vol. 25 (3), 433-438
- https://doi.org/10.1038/s41591-018-0335-9
Abstract
Artificial intelligence (AI)-based methods have emerged as powerful tools to transform medical care. Although machine learning classifiers (MLCs) have already demonstrated strong performance in image-based diagnoses, analysis of diverse and massive electronic health record (EHR) data remains challenging. Here, we show that MLCs can query EHRs in a manner similar to the hypothetico-deductive reasoning used by physicians and unearth associations that previous statistical methods have not found. Our model applies an automated natural language processing system using deep learning techniques to extract clinically relevant information from EHRs. In total, 101.6 million data points from 1,362,559 pediatric patient visits presenting to a major referral center were analyzed to train and validate the framework. Our model demonstrates high diagnostic accuracy across multiple organ systems and is comparable to experienced pediatricians in diagnosing common childhood diseases. Our study provides a proof of concept for implementing an AI-based system as a means to aid physicians in tackling large amounts of data, augmenting diagnostic evaluations, and to provide clinical decision support in cases of diagnostic uncertainty or complexity. Although this impact may be most evident in areas where healthcare providers are in relative shortage, the benefits of such an AI system are likely to be universal.Keywords
This publication has 19 references indexed in Scilit:
- Scalable and accurate deep learning with electronic health recordsnpj Digital Medicine, 2018
- Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep LearningCell, 2018
- Machine Learning for Medical ImagingRadioGraphics, 2017
- Dermatologist-level classification of skin cancer with deep neural networksNature, 2017
- Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus PhotographsJAMA, 2016
- Clinical risk prediction with multilinear sparse logistic regressionPublished by Association for Computing Machinery (ACM) ,2014
- The Unreasonable Effectiveness of DataIEEE Intelligent Systems, 2009
- Electronic Health Records: A Guide for Clinicians and AdministratorsPublished by American Medical Association (AMA) ,2009
- Using Regular Expressions to Abstract Blood Pressure and Treatment Intensification Information from the Text of Physician NotesJournal of the American Medical Informatics Association, 2006
- Scaling to very very large corpora for natural language disambiguationPublished by Association for Computational Linguistics (ACL) ,2001