Diagnostic and interventional radiology (Ankara, Turkey) · 2026
Large-scale evaluation of multimodal large language models for pneumothorax detection.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Güzel Hamza Eren, Özenbaş Cemre, Koç Ali Murat
Аннотация
PURPOSE: Pneumothorax requires rapid recognition and accurate interpretation of chest X-rays (CXRs), particularly in acute settings where delays can have serious consequences. With the emergence of advanced image interpretation models capable of visual analysis, their diagnostic reliability in radiology practice remains to be determined. This study aimed to assess the diagnostic performance of three state-of-the-art systems in detecting pneumothorax using a large, well-annotated dataset.
METHODS: A total of 10,675 CXRs from the publicly available SIIM-ACR Pneumothorax Segmentation dataset were analyzed. Three multimodal models (GPT-4o, Gemini 2 Pro, and Claude 4 Sonnet) were evaluated using a uniform, image-based approach. Each model's binary outputs (presence: 1, absence: 0) were compared with reference results to determine accuracy, sensitivity, specificity, precision, and F1 scores. Additional subgroup analyses were conducted across pneumothorax size categories: small, medium, and large. Pairwise statistical comparisons were performed using McNemar's test. Sensitivity, specificity, and overall accuracy are reported with corresponding 95% confidence intervals.
RESULTS: The prevalence of pneumothorax in the dataset was 22.3% (n = 2,379). All models demonstrated high specificity (above 0.90) but consistently low sensitivity (0.16-0.36). The best overall performance was observed with Gemini 2, which achieved an accuracy of 0.79 and specificity of 0.95, whereas Claude 4 showed greater sensitivity (0.20-0.34) across lesion-size categories. Diagnostic performance improved with increasing pneumothorax size, but smaller lesions remained difficult to identify. Pairwise comparisons confirmed statistically significant differences among all evaluated systems (P < 0.050).
CONCLUSION: In this large-scale evaluation, the tested models exhibited strong reliability in identifying normal examinations but limited ability to detect subtle or small pneumothoraxes. Despite high specificity, low sensitivity limits the use of current multimodal large language models as rule-out tools for pneumothorax. With continued refinement, these models may eventually support radiologists by improving workflow efficiency and diagnostic confidence.
CLINICAL SIGNIFICANCE: Automated systems capable of high specificity but low sensitivity should not be relied upon to exclude pneumothorax. However, they may serve as valuable assistants for confirming positive findings and prioritizing urgent cases in busy clinical workflows.
METHODS: A total of 10,675 CXRs from the publicly available SIIM-ACR Pneumothorax Segmentation dataset were analyzed. Three multimodal models (GPT-4o, Gemini 2 Pro, and Claude 4 Sonnet) were evaluated using a uniform, image-based approach. Each model's binary outputs (presence: 1, absence: 0) were compared with reference results to determine accuracy, sensitivity, specificity, precision, and F1 scores. Additional subgroup analyses were conducted across pneumothorax size categories: small, medium, and large. Pairwise statistical comparisons were performed using McNemar's test. Sensitivity, specificity, and overall accuracy are reported with corresponding 95% confidence intervals.
RESULTS: The prevalence of pneumothorax in the dataset was 22.3% (n = 2,379). All models demonstrated high specificity (above 0.90) but consistently low sensitivity (0.16-0.36). The best overall performance was observed with Gemini 2, which achieved an accuracy of 0.79 and specificity of 0.95, whereas Claude 4 showed greater sensitivity (0.20-0.34) across lesion-size categories. Diagnostic performance improved with increasing pneumothorax size, but smaller lesions remained difficult to identify. Pairwise comparisons confirmed statistically significant differences among all evaluated systems (P < 0.050).
CONCLUSION: In this large-scale evaluation, the tested models exhibited strong reliability in identifying normal examinations but limited ability to detect subtle or small pneumothoraxes. Despite high specificity, low sensitivity limits the use of current multimodal large language models as rule-out tools for pneumothorax. With continued refinement, these models may eventually support radiologists by improving workflow efficiency and diagnostic confidence.
CLINICAL SIGNIFICANCE: Automated systems capable of high specificity but low sensitivity should not be relied upon to exclude pneumothorax. However, they may serve as valuable assistants for confirming positive findings and prioritizing urgent cases in busy clinical workflows.