Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Ayis Pyrros; Stephen M Borstelmann; Ramana Mantravadi; Zachary Zaiman; Kaesha Thomas; Brandon Price; Eugene Greenstein; Nasir Siddiqui; Melinda Willis; Ihar Shulhan; John Hines-Shah; Jeanne M Horowitz; Paul Nikolaidis; Matthew P Lungren; Jorge Mario Rodríguez-Fernández; Judy Wawira Gichoya; Sanmi Koyejo; Adam E Flanders; Nishith Khandwala; Amit Gupta; John W Garrett; Joseph Paul Cohen; Brian T Layden; Perry J Pickhardt; William Galanter

doi:10.1038/s41467-023-39631-x

Opportunistic detection of type 2 diabetes using deep learning from frontal chest radiographs

Nat Commun. 2023 Jul 7;14(1):4039. doi: 10.1038/s41467-023-39631-x.

Authors

Ayis Pyrros^#^{1

2}, Stephen M Borstelmann^#³, Ramana Mantravadi⁴, Zachary Zaiman⁵, Kaesha Thomas⁵, Brandon Price⁶, Eugene Greenstein⁷, Nasir Siddiqui⁸, Melinda Willis⁸, Ihar Shulhan⁹, John Hines-Shah⁸, Jeanne M Horowitz¹⁰, Paul Nikolaidis¹⁰, Matthew P Lungren^{11

12

13}, Jorge Mario Rodríguez-Fernández¹⁴, Judy Wawira Gichoya⁵, Sanmi Koyejo¹⁵, Adam E Flanders¹⁶, Nishith Khandwala¹⁷, Amit Gupta¹⁸, John W Garrett¹⁹, Joseph Paul Cohen¹², Brian T Layden²⁰, Perry J Pickhardt¹⁹, William Galanter²⁰

Affiliations

¹ Duly Health and Care, Department of Radiology, Downers Grove, IL, USA. ayis@uic.edu.
² Department of Biomedical and Health Information Sciences, University of Illinois Chicago, Chicago, IL, USA. ayis@uic.edu.
³ Department of Radiology, University of Central Florida, Orlando, FL, USA.
⁴ Brainnet, Inc., West Harrison, NY, USA.
⁵ Department of Radiology, Emory University, Atlanta, GA, USA.
⁶ Department of Radiology, Florida State University, Tallahassee, FL, USA.
⁷ Department of Cardiology, Duly Health and Care, Downers Grove, IL, USA.
⁸ Duly Health and Care, Department of Radiology, Downers Grove, IL, USA.
⁹ EPAM, Inc, Newtown, PA, USA.
¹⁰ Department of Radiology, Northwestern University, Chicago, IL, USA.
¹¹ Department of Biomedical and Health Information Sciences, UCSF, San Francisco, CA, USA.
¹² Center for Artificial Intelligence in Medicine, Stanford University, Stanford, CA, USA.
¹³ Microsoft, Microsoft Corporation, Redmond, USA.
¹⁴ Department of Neurology, The University of Texas Medical Branch, Galveston, TX, USA.
¹⁵ Department of Computer Science, Stanford University, Stanford, CA, USA.
¹⁶ Department of Radiology, Thomas Jefferson University, Philadelphia, PA, USA.
¹⁷ Bunkerhill, Palo Alto, CA, USA.
¹⁸ Department of Radiology, University Hospitals Cleveland Medical Center, Cleveland, OH, USA.
¹⁹ Department of Radiology, University of Wisconsin, Madison, WI, USA.
²⁰ Department of Medicine, University of Illinois Chicago, Chicago, IL, USA.

^# Contributed equally.

Abstract

Deep learning (DL) models can harness electronic health records (EHRs) to predict diseases and extract radiologic findings for diagnosis. With ambulatory chest radiographs (CXRs) frequently ordered, we investigated detecting type 2 diabetes (T2D) by combining radiographic and EHR data using a DL model. Our model, developed from 271,065 CXRs and 160,244 patients, was tested on a prospective dataset of 9,943 CXRs. Here we show the model effectively detected T2D with a ROC AUC of 0.84 and a 16% prevalence. The algorithm flagged 1,381 cases (14%) as suspicious for T2D. External validation at a distinct institution yielded a ROC AUC of 0.77, with 5% of patients subsequently diagnosed with T2D. Explainable AI techniques revealed correlations between specific adiposity measures and high predictivity, suggesting CXRs' potential for enhanced T2D screening.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Deep Learning*
Diabetes Mellitus, Type 2* / diagnostic imaging
Humans
Prospective Studies
Radiography
Radiography, Thoracic / methods

Abstract

Publication types

MeSH terms

Grants and funding