Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis
Genauigkeit von Deep Learning bei der Diagnose der chronisch obstruktiven Lungenerkrankung: systematische Übersicht und Metaanalyse
Journal of Medical Internet Research · 2026-01-14 · 28 · e83459-e83459
DOI: 10.2196/83459 ↗Auf einen Blick
56 Studien mit 886.753 Teilnehmenden untersuchten die Genauigkeit von DL zur COPD-Diagnose und zum GOLD-Staging. Für die binäre Diagnose zeigten CT- und Atemschall-Modelle eine hohe Genauigkeit.
Fragestellung
Wie genau sind Deep-Learning-Modelle für die Diagnose von COPD und für die Stadieneinteilung nach GOLD?
Methode
Systematische Übersicht und Metaanalyse; Suche in Cochrane Library, Embase, Web of Science und PubMed bis 1. November 2025; Bewertung mit QUADAS-2; Metaanalysen der Validierungssätze.
Ergebnisse
Binäre COPD-Diagnose: Sensitivität 0,87 (95 %-KI 0,85–0,90), Spezifität 0,88 (95 %-KI 0,84–0,92), DOR 52 (95 %-KI 30–88), AUC 0,93. CT: AUC 0,92. Atemschall: AUC 0,98.
Einschränkungen
Substanzielle Heterogenität und begrenzte externe Validierung; multiclass GOLD-Grading mit eingeschränkter Genauigkeit.
Schlussfolgerung der Autor:innen
Die Autor:innen schließen, dass CT- und Atemschall-Modelle für die binäre COPD-Erkennung eine hohe Genauigkeit zeigen, das multiclass GOLD-Grading jedoch weiterhin problematisch ist.
Kernaussagen
- 56 Studien mit 886.753 Teilnehmenden
- Binäre COPD-Diagnose mit hoher Treffgenauigkeit
- GOLD-Staging nur eingeschränkt genau
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Systematische Übersicht in Journal of Medical Internet Research, published online on 2026-01-14. Written by Hui Yang and 5 co-authors. Institution: School of Management, Guizhou University, Huaxi District, Guiyang, Guizhou, 550025, China, 86 18286022086. Major MEDLINE topics: Pulmonary Disease, Chronic Obstructive, Deep Learning. Cited 1 times so far (Crossref); 75 references. The full text is freely available in PubMed Central.
Topics: COPD
Abstract (original language)
Background
Chronic obstructive pulmonary disease (COPD) is a common chronic lung disease. Deep learning (DL), a data-driven machine learning approach, has gained attention in clinical practice, particularly for diagnosing COPD and grading its severity. However, systematic evidence of its diagnostic and grading accuracy remains limited, posing challenges for developing intelligent diagnostic tools.
Objective
This study aimed to systematically estimate the accuracy of DL models for diagnosing and grading COPD, providing up-to-date evidence for the design and clinical implementation of intelligent detection tools.
Methods
The Cochrane Library, Embase, Web of Science, and PubMed were systematically searched for studies on DL for diagnosing COPD and grading its severity published up to November 1, 2025. Risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. Subgroup analyses by the validation set generation method and imaging data source were conducted, and meta-analyses were performed on the validation sets. For binary outcomes, diagnostic 2×2 tables were synthesized using a bivariate mixed effects model; for multiclass outcomes, accuracy estimates were pooled using random-effects models.
Results
In total, 56 studies comprising 886,753 participants were included. Inputs were computed tomography (CT) imaging (n=30), breath sounds or audio (n=12), conventional chest X-ray (n=2), X-ray film (n=2), and other modalities (n=10), including pulmonary function indices or curves or physiological waveforms, electrocardiograms, volumetric capnography maps, radiogenetic data, and clinical scores. For binary classification of COPD, DL models yielded a pooled sensitivity of 0.87 (95% CI 0.85‐0.90), specificity of 0.88 (95% CI 0.84‐0.92), diagnostic odds ratio (DOR) of 52 (95% CI 30‐88), and the area under the summary receiver operating characteristic curve (AUC) of 0.93. For CT-based DL models, pooled sensitivity was 0.86 (95% CI 0.84‐0.89), specificity was 0.87 (95% CI 0.82‐0.90), DOR was 42 (95% CI 26‐68), and AUC was 0.92. For respiratory sound–based models, sensitivity was 0.91 (95% CI 0.84‐0.95), specificity was 0.96 (95% CI 0.91‐0.98), DOR was 237 (95% CI 78‐723), and AUC was 0.98. In multiclass classification, the DL models showed limited accuracy in discriminating Global Initiative for Chronic Obstructive Lung Disease (GOLD) stages: GOLD stage 0 (84.2%, 95% CI 60.5%‐98.2%), stage 1 (61.7%, 95% CI 40.7%‐80.8%), stage 2 (67.9%, 95% CI 37.6%‐91.7%), stage 3 (70.8%, 95% CI 16.3%‐100%), and stage 4 (70.8%, 95% CI 16.3%‐100%).
Conclusions
This study is the first systematic synthesis of DL applications for COPD detection and GOLD staging. DL models based on CT images and breath sounds show high accuracy for binary COPD detection, whereas multiclass GOLD grading remains concerning. These findings support the development and updating of artificial intelligence−assisted COPD screening tools; however, substantial heterogeneity and limited external validation warrant cautious interpretation. Future reproducible multicenter studies with standardized reporting are needed.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- School of Management, Guizhou University, Huaxi District, Guiyang, Guizhou, 550025, China, 86 18286022086.
- School of Forensic Medicine, Guizhou Medical University, Guiyang, Guizhou, China.
- School of Anesthesiology, Guizhou Medical University, Guiyang, Guizhou, China.
Cite
APA
Yang, H., Wu, Y., Wu, T., Ji, J., Lei, S., & Xu, W. (2026). Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e83459-e83459. https://doi.org/10.2196/83459
Vancouver
Yang H, Wu Y, Wu T, Ji J, Lei S, Xu W. Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e83459-e83459. doi:10.2196/83459
BibTeX
@article{Yang2026,
author = {Yang, Hui and Wu, Yijiu and Wu, Tong and Ji, Jingyan and Lei, Sitao and Xu, Weibin},
title = {Accuracy of Deep Learning in Diagnosing Chronic Obstructive Pulmonary Disease: Systematic Review and Meta-Analysis},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e83459--e83459},
doi = {10.2196/83459}
}
EUVIMED