基于术前胸部X线片的深度学习预测心胸外科手术后死亡率
研究开发并验证了深度学习模型CXR-CTSurgery,基于术前胸部X线片预测心脏手术后死亡率。在麻省总医院9283例训练、3615例内部测试及布莱根妇女医院2840例外部测试中,该模型对STS指数手术的区分度与STS-PROM相似,校准度更优,且可用于非STS指数手术。
要点
- CXR-CTSurgery对STS指数手术的区分度与STS-PROM相似(MGH 0.83 vs 0.88,P=.20;BWH 0.74 vs 0.80,P=.14)。
- CXR-CTSurgery在校准度上优于STS-PROM(MGH O/E 0.74 vs 0.52;BWH O/E 0.91 vs 0.73)。
- 对非STS指数手术,CXR-CTSurgery区分度与STS指数手术相似(MGH 0.87 vs 0.83;BWH 0.73 vs 0.74)。
核心结论
- CXR-CTSurgery基于术前胸部X线片预测术后死亡率,区分度与STS-PROM相似且校准度更优,可能在STS-PROM无法计算或非STS指数手术时有用。
研究设计与样本
- 研究开发深度学习模型CXR-CTSurgery,基于术前胸部X线片预测心脏手术后死亡率,训练集为2014年4月8日前在麻省总医院(MGH)接受心脏手术的9283例患者。
- 模型在3615例不同的MGH患者中进行测试,并在布莱根妇女医院(BWH)2014年4月8日后接受手术的2840例患者中进行外部测试。
- 采用C统计量比较死亡率区分度,采用观察与预期比值(O/E比值)评估校准度。
主要发现
- 对于STS指数手术,CXR-CTSurgery的C统计量与STS-PROM在MGH测试队列相似(0.83 vs 0.88;P=.20),在BWH测试队列亦相似(0.74 vs 0.80;P=.14)。
- CXR-CTSurgery对非STS指数手术的C统计量与STS指数手术相似,MGH测试队列为0.87 vs 0.83,BWH测试队列为0.73 vs 0.74。
- 对于STS指数手术,CXR-CTSurgery的校准度优于STS-PROM,MGH测试队列O/E比值为0.74 vs 0.52,BWH测试队列O/E比值为0.91 vs 0.73。
临床怎么用
- 作者认为,当STS-PROM无法计算或针对非STS指数手术时,CXR-CTSurgery可能有用。
局限性
- 原文未报告局限性
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)。
原文
BACKGROUND: The Society of Thoracic Surgeons Predicted Risk of Mortality (STS-PROM) estimates mortality risk only for certain common procedures (eg, coronary artery bypass or valve surgery) and is cumbersome, requiring greater than 60 inputs. We hypothesized that deep learning can estimate postoperative mortality risk based on a preoperative chest radiograph for cardiac surgeries in which STS-PROM scores were available (STS index procedures) or unavailable (non-STS index procedures). METHODS: We developed a deep learning model (CXR-CTSurgery) to predict postoperative mortality based on preoperative chest radiographs in 9283 patients at Massachusetts General Hospital (MGH) having cardiac surgery before April 8, 2014. CXR-CTSurgery was tested on 3615 different MGH patients and externally tested on 2840 patients from Brigham and Women's Hospital (BWH) having surgery after April 8, 2014. Discrimination for mortality was compared with the STS-PROM using the C-statistic. Calibration was assessed using the observed-to-expected ratio (O/E ratio). RESULTS: For STS index procedures, CXR-CTSurgery had a C-statistic similar to STS-PROM at MGH (CXR-CTSurgery: 0.83 vs STS-PROM: 0.88; P = .20) and BWH (0.74 vs 0.80; P = .14) testing cohorts. The CXR-CTSurgery C-statistic for non-STS index procedures was similar to STS index procedures in the MGH (0.87 vs 0.83) and BWH (0.73 vs 0.74) testing cohorts. For STS index procedures, CXR-CTSurgery had better calibration than the STS-PROM in the MGH (O/E ratio: 0.74 vs 0.52) and BWH (O/E ratio: 0.91 vs 0.73) testing cohorts. CONCLUSIONS: CXR-CTSurgery predicts postoperative mortality based on a preoperative CXR with similar discrimination and better calibration than the STS-PROM. This may be useful when the STS-PROM cannot be calculated or for non-STS index procedures.
引用
- Raghu VK, Moonsamy P, Sundt TM, et al. Deep Learning to Predict Mortality After Cardiothoracic Surgery Using Preoperative Chest Radiographs. Ann Thorac Surg. 2022. PMID: 35609650. doi:10.1016/j.athoracsur.2022.04.056
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。