Dal Ismail, Kaya Hasan Burak
Department of Thoracic Surgery, Kastamonu University, Kastamonu, Turkey.
Department of Emergency Medicine, Kastamonu University, Kastamonu, Turkey.
J Multidiscip Healthc. 2025 Jul 17;18:4099-4111. doi: 10.2147/JMDH.S535405. eCollection 2025.
Accurate and timely detection of pneumothorax on chest radiographs is critical in emergency and critical care settings. While subtle cases remain challenging for clinicians, artificial intelligence (AI) offers promise as a diagnostic aid. This retrospective diagnostic accuracy study evaluates a deep learning model developed using Google Cloud Vertex AI for pneumothorax detection on chest X-rays.
A total of 152 anonymized frontal chest radiographs (76 pneumothorax, 76 normal), confirmed by computed tomography (CT), were collected from a single center between 2023 and 2024. The median patient age was 50 years (range: 18-95), with 67.1% male. The AI model was trained using AutoML Vision and evaluated in both cloud and edge deployment environments. Diagnostic accuracy metrics-including sensitivity, specificity, and F1 score-were compared with those of 15 physicians from four specialties (general practice, emergency medicine, thoracic surgery, radiology), stratified by experience level. Subgroup analysis focused on minimal pneumothorax cases. Confidence intervals were calculated using the Wilson method.
In cloud deployment, the AI model achieved an overall diagnostic accuracy of 0.95 (95% CI: 0.83, 0.99), sensitivity of 1.00 (95% CI: 0.83, 1.00), specificity of 0.89 (95% CI: 0.69, 0.97), and F1 score of 0.95 (95% CI: 0.86, 1.00). Comparable performance was observed in edge mode. The model outperformed junior clinicians and matched or exceeded senior physicians, particularly in detecting minimal pneumothoraces, where AI sensitivity reached 0.93 (95% CI: 0.79, 0.97) compared to 0.55 (95% CI: 0.38, 0.69) - 0.84 (95% CI: 0.69, 0.92) among human readers.
The Google Cloud Vertex AI model demonstrates high diagnostic performance for pneumothorax detection, including subtle cases. Its consistent accuracy across edge and cloud settings supports its integration as a second reader or triage tool in diverse clinical workflows, especially in acute care or resource-limited environments.
在急诊和重症监护环境中，准确及时地在胸部X光片上检测气胸至关重要。虽然细微的病例对临床医生来说仍然具有挑战性，但人工智能（AI）有望成为一种诊断辅助工具。这项回顾性诊断准确性研究评估了使用谷歌云Vertex AI开发的用于胸部X光片气胸检测的深度学习模型。
2023年至2024年期间，从一个单一中心收集了总共152张经计算机断层扫描（CT）确认的匿名胸部正位X光片（76张气胸，76张正常）。患者的中位年龄为50岁（范围：18 - 95岁），男性占67.1%。AI模型使用AutoML Vision进行训练，并在云端和边缘部署环境中进行评估。将诊断准确性指标，包括敏感性、特异性和F1分数，与来自四个专业（全科、急诊医学、胸外科、放射科）的15名医生的指标进行比较，并按经验水平分层。亚组分析聚焦于微小气胸病例。使用威尔逊方法计算置信区间。
在云端部署中，AI模型的总体诊断准确性为0.95（95%置信区间：0.83，0.99），敏感性为1.00（95%置信区间：0.83，1.00），特异性为0.89（95%置信区间：0.69，0.97），F1分数为0.95（95%置信区间：0.86，1.00）。在边缘模式下观察到了类似的性能。该模型优于初级临床医生，与高级医生相当或超过高级医生，特别是在检测微小气胸方面，AI的敏感性达到0.93（95%置信区间：0.79，0.97），而人类读者的敏感性为0.55（95%置信区间：0.38，0.69） - 0.84（95%置信区间：0.69，0.92）。
谷歌云Vertex AI模型在气胸检测方面表现出很高的诊断性能，包括细微病例。其在边缘和云端设置中一致的准确性支持将其作为第二阅片者或分诊工具整合到各种临床工作流程中，特别是在急性护理或资源有限的环境中。
