Document Type

Article

Publication Date

7-7-2023

Comments

This article is the author's final published version in Nature Communications, Volume 14, 2023, Article number 4039.

The published version is available at https://doi.org/10.1038/s41467-023-39631-x. Copyright © The Author(s) 2023.

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.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.

Additional Files
41467_2023_39631_MOESM1_ESM.docx (25 kB)
Supplementary Information
Peer Review.pdf (3542 kB)
Peer Review File
41467_2023_39631_MOESM3_ESM.docx (14 kB)
Description of Additional Supplementary Information File
41467_2023_39631_MOESM4_ESM.mp4 (32666 kB)
Supplementary Movie 1
Reporting Summary.pdf (1013 kB)
Reporting Summary

PubMed ID

37419921

Language

English

Download

Share

COinS