超越气泡征:人工智能分析「气泡床」微环境提升感染性腹腔积液诊断效能
多中心回顾性研究纳入797例经培养证实的感染性腹腔积液患者,基于非增强CT开发全自动人工智能模型BUBBLE-AI,分析气泡周围炎症微环境,外部测试AUC为0.82(95%CI 0.72-0.93),显著优于传统气泡征与仅临床模型,总误诊率24.1%。
要点
- BUBBLE-AI基于非增强CT全自动分割气泡周围「气泡床」微环境,外部测试AUC 0.82(95%CI 0.72-0.93)。
- 模型总误诊率24.1%,低于气泡征的38.5%和仅临床模型的34.3%。
- 特征分析显示「气泡床」微环境为最主要预测信息来源,占特征35.8%。
核心结论
- BUBBLE-AI为基于非增强CT全自动准确诊断感染性腹腔积液的工具,可更可靠识别感染状态,有助抗菌药物管理和减少诊断错误。
研究设计与样本
- 多中心回顾性研究,2011年7月至2024年7月,797例经培养证实的感染性腹腔积液患者,分为训练集637例、验证集80例和外部测试集80例。
诊断标准与关键数值
- BUBBLE-AI验证集AUC 0.92,外部测试集AUC 0.82(95%CI 0.72-0.93),显著优于传统方法(P < 0.001);总误诊率24.1%,气泡征38.5%,仅临床模型34.3%。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: Accurate diagnosis of infected intra-abdominal fluid collections (IAFCs) is challenging, as the conventional "gas bubble sign" on computed tomography (CT) has poor sensitivity. This study aimed to develop and validate a fully automated artificial intelligence (AI) model using non-contrast CT to improve diagnostic accuracy.
METHODS: In this multicenter retrospective study (July 2011-July 2024), 797 patients with IAFCs confirmed by culture were divided into training (n = 637), validation (n = 80), and external test (n = 80) sets. We developed an AI model, Bubble Bed Based Learning Engine for Abdominal Infection (BUBBLE-AI), based on the novel "bubble bed" concept, which analyzes the inflammatory microenvironment around gas bubbles. The model integrates deep learning and radiomic features, extracted from automated segmentations, with clinical data.
RESULTS: The BUBBLE-AI model demonstrated robust and generalizable performance, achieving an area under the curve (AUC) of 0.92 in validation and 0.82 (95% CI: 0.72-0.93) in external testing, significantly outperforming traditional methods (P < 0.001). The model achieved a total misdiagnosis rate of 24.1%, a substantial improvement over the bubble sign (38.5%) and a clinical-only model (34.3%). Feature analysis confirmed the "bubble bed" microenvironment was the most dominant source of predictive information (35.8% of features), validating our core hypothesis.
CONCLUSION: The BUBBLE-AI provides a fully automated and accurate tool for diagnosing IAFC infections from non-contrast CT. By identifying infection status more reliably, it can guide antimicrobial stewardship, reduce diagnostic errors, and optimize clinical decision-making.
引用
- Guo Y, Chen C, Wang T, et al. Beyond gas bubbles: AI analysis of the "bubble bed" microenvironment improves diagnosis of infected abdominal collections. Abdom Radiol (NY). 2025. PMID: 41452460. doi:10.1007/s00261-025-05260-9
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。