Cargando…
Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis
In this study, we developed a model to predict culture test results for pulmonary tuberculosis (PTB) with a customized multimodal approach and evaluated its performance in different clinical settings. Moreover, we investigated potential performance improvements by combining this approach with deep l...
Autores principales: | , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10643438/ https://www.ncbi.nlm.nih.gov/pubmed/37957334 http://dx.doi.org/10.1038/s41598-023-47146-0 |
_version_ | 1785147115588026368 |
---|---|
author | Choi, So Yeon Choi, Arom Baek, Song-Ee Ahn, Jin Young Roh, Yun Ho Kim, Ji Hoon |
author_facet | Choi, So Yeon Choi, Arom Baek, Song-Ee Ahn, Jin Young Roh, Yun Ho Kim, Ji Hoon |
author_sort | Choi, So Yeon |
collection | PubMed |
description | In this study, we developed a model to predict culture test results for pulmonary tuberculosis (PTB) with a customized multimodal approach and evaluated its performance in different clinical settings. Moreover, we investigated potential performance improvements by combining this approach with deep learning-based automated detection algorithms (DLADs). This retrospective observational study enrolled patients over 18 years of age who consecutively visited the level 1 emergency department and underwent chest radiograph and sputum testing. The primary endpoint was positive sputum culture for PTB. We compared the performance of the diagnostic models by replacing radiologists’ interpretations of chest radiographs with screening scores calculated through DLAD. The optimal diagnostic model had an area under the receiver operating characteristic curve of 0.924 (95% CI 0.871–0.976) and an area under precision recall curve of 0.403 (95% CI 0.195–0.580) while maintaining a specificity of 81.4% when sensitivity was fixed at 90%. Multicomponent models showed improved performance for detecting PTB when chest radiography interpretation was replaced by DLAD. Multicomponent diagnostic models with DLAD customized for different clinical settings are more practical than traditional methods for detecting patients with PTB. This novel diagnostic approach may help prevent the spread of PTB and optimize healthcare resource utilization in resource-limited clinical settings. |
format | Online Article Text |
id | pubmed-10643438 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Nature Publishing Group UK |
record_format | MEDLINE/PubMed |
spelling | pubmed-106434382023-11-13 Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis Choi, So Yeon Choi, Arom Baek, Song-Ee Ahn, Jin Young Roh, Yun Ho Kim, Ji Hoon Sci Rep Article In this study, we developed a model to predict culture test results for pulmonary tuberculosis (PTB) with a customized multimodal approach and evaluated its performance in different clinical settings. Moreover, we investigated potential performance improvements by combining this approach with deep learning-based automated detection algorithms (DLADs). This retrospective observational study enrolled patients over 18 years of age who consecutively visited the level 1 emergency department and underwent chest radiograph and sputum testing. The primary endpoint was positive sputum culture for PTB. We compared the performance of the diagnostic models by replacing radiologists’ interpretations of chest radiographs with screening scores calculated through DLAD. The optimal diagnostic model had an area under the receiver operating characteristic curve of 0.924 (95% CI 0.871–0.976) and an area under precision recall curve of 0.403 (95% CI 0.195–0.580) while maintaining a specificity of 81.4% when sensitivity was fixed at 90%. Multicomponent models showed improved performance for detecting PTB when chest radiography interpretation was replaced by DLAD. Multicomponent diagnostic models with DLAD customized for different clinical settings are more practical than traditional methods for detecting patients with PTB. This novel diagnostic approach may help prevent the spread of PTB and optimize healthcare resource utilization in resource-limited clinical settings. Nature Publishing Group UK 2023-11-13 /pmc/articles/PMC10643438/ /pubmed/37957334 http://dx.doi.org/10.1038/s41598-023-47146-0 Text en © The Author(s) 2023 https://creativecommons.org/licenses/by/4.0/Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) . |
spellingShingle | Article Choi, So Yeon Choi, Arom Baek, Song-Ee Ahn, Jin Young Roh, Yun Ho Kim, Ji Hoon Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title | Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title_full | Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title_fullStr | Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title_full_unstemmed | Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title_short | Effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
title_sort | effect of multimodal diagnostic approach using deep learning-based automated detection algorithm for active pulmonary tuberculosis |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10643438/ https://www.ncbi.nlm.nih.gov/pubmed/37957334 http://dx.doi.org/10.1038/s41598-023-47146-0 |
work_keys_str_mv | AT choisoyeon effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis AT choiarom effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis AT baeksongee effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis AT ahnjinyoung effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis AT rohyunho effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis AT kimjihoon effectofmultimodaldiagnosticapproachusingdeeplearningbasedautomateddetectionalgorithmforactivepulmonarytuberculosis |