What question did this study set out to answer?

Evaluate the diagnostic accuracy of AI models for classifying malignancy in lung nodules using chest CT images.

June 5, 2026

Externally Tested AI Models for Malignancy Classification of Lung Nodules at Chest CT: A Systematic Review and Meta-Analysis

Key Points

Evaluate the diagnostic accuracy of AI models for classifying malignancy in lung nodules using chest CT images.
Systematic search of major databases conducted in January 2025.
Twenty-one studies analyzed with a total of 7,454 lung nodules using pathology and/or follow-up as reference.
Risk of bias assessed with QUADAS-2 and pooled sensitivity and specificity estimated using bivariate random-effects models.
Pooled sensitivity of 88% and specificity of 75% for malignancy classification.
Area under the ROC curve was 0.89, with diagnostic odds ratio of 22.4.
Heterogeneity was high, with I2 > 90%, and model architecture impacted specificity.

Abstract

Purpose To evaluate the pooled diagnostic accuracy of externally tested AI models for malignancy classification of lung nodules on chest CT. Materials and Methods A systematic search of PubMed, Embase, Web of Science, CINAHL, and the Cochrane Library was performed in January 2025 to identify studies evaluating AI models for malignancy classification of lung nodules on chest CT using pathology and/or at least 2-year follow-up as reference standards. Risk of bias was assessed using QUADAS-2, and pooled sensitivity and specificity were estimated using bivariate random-effects models. Results Twenty-one studies including 7,454 nodules were analyzed, with lung cancer prevalence ranging from 5.7% (17/297) to 91.5% (214/234). All models were based on deep learning; 17 studies (81%) involved Asian populations, 15 (71%) used non-screening populations, 14 (67%) reported 2D or 3D CNN architectures, and eight (38%) specified predefined malignancy thresholds. High risk of bias was identified in five studies for patient selection and two for index testing. Pooled sensitivity was 88%, specificity 75%, positive likelihood ratio 3.55, negative likelihood ratio 0.16, area under the receiver operating characteristic curve 0.89, and diagnostic odds ratio 22.4. Heterogeneity was high (I 2 > 90%). Model architecture was associated with specificity, with higher values in studies reporting 2D or 3D CNNs compared with those without reported architecture (82–83% vs 58%, P = .03; meta-regression P = .02); other subgroup analyses showed no evidence of differences. Conclusion Externally tested AI models demonstrated high sensitivity but moderate specificity for malignancy classification of lung nodules on chest CT, supporting a potential role in rule-out strategies. However, substantial heterogeneity, inconsistent reporting, and risk of bias limit interpretation. ©RSNA, 2026

Perguntar à IA

Bookmark