Department of Respiratory and Critical Care Medicine, Changi General Hospital, Singapore
Department of Radiology, Changi General Hospital, Singapore.
BMJ Open Respir Res. 2021 Aug;8(1). doi: 10.1136/bmjresp-2021-001045.
Chest radiograph (CXR) is a basic diagnostic test in community-acquired pneumonia (CAP) with prognostic value. We developed a CXR-based artificial intelligence (AI) model (CAP AI predictive Engine: CAPE) and prospectively evaluated its discrimination for 30-day mortality.
Deep-learning model using convolutional neural network (CNN) was trained with a retrospective cohort of 2235 CXRs from 1966 unique adult patients admitted for CAP from 1 January 2019 to 31 December 2019. A single-centre prospective cohort between 11 May 2020 and 15 June 2020 was analysed for model performance. CAPE mortality risk score based on CNN analysis of the first CXR performed for CAP was used to determine the area under the receiver operating characteristic curve (AUC) for 30-day mortality.
315 inpatient episodes for CAP occurred, with 30-day mortality of 19.4% (n=61/315). Non-survivors were older than survivors (mean (SD)age, 80.4 (10.3) vs 69.2 (18.7)); more likely to have dementia (n=27/61 vs n=58/254) and malignancies (n=16/61 vs n=18/254); demonstrate higher serum C reactive protein (mean (SD), 109 mg/L (98.6) vs 59.3 mg/L (69.7)) and serum procalcitonin (mean (SD), 11.3 (27.8) μg/L vs 1.4 (5.9) μg/L). The AUC for CAPE mortality risk score for 30-day mortality was 0.79 (95% CI 0.73 to 0.85, p<0.001); Pneumonia Severity Index (PSI) 0.80 (95% CI 0.74 to 0.86, p<0.001); Confusion of new onset, blood Urea nitrogen, Respiratory rate, Blood pressure, 65 (CURB-65) score 0.76 (95% CI 0.70 to 0.81, p<0.001), respectively. CAPE combined with CURB-65 model has an AUC of 0.83 (95% CI 0.77 to 0.88, p<0.001). The best performing model was CAPE incorporated with PSI, with an AUC of 0.84 (95% CI 0.79 to 0.89, p<0.001).
CXR-based CAPE mortality risk score was comparable to traditional pneumonia severity scores and improved its discrimination when combined.
胸部 X 线摄影（CXR）是社区获得性肺炎（CAP）的基本诊断测试，具有预后价值。我们开发了一种基于 CXR 的人工智能（AI）模型（CAP AI 预测引擎：CAPE），并前瞻性评估了其对 30 天死亡率的区分能力。
使用卷积神经网络（CNN）的深度学习模型对 2019 年 1 月 1 日至 2019 年 12 月 31 日期间因 CAP 入院的 1966 名成年患者的 2235 张 CXR 进行了回顾性队列研究。对 2020 年 5 月 11 日至 2020 年 6 月 15 日期间的单中心前瞻性队列进行了模型性能分析。基于对 CAP 进行的首次 CXR 的 CNN 分析，使用 CAPE 死亡率风险评分来确定 30 天死亡率的受试者工作特征曲线下面积（AUC）。
共发生 315 例 CAP 住院病例，30 天死亡率为 19.4%（n=61/315）。非幸存者比幸存者年龄更大（平均（SD）年龄，80.4（10.3）vs 69.2（18.7））；更有可能患有痴呆症（n=27/61 vs n=58/254）和恶性肿瘤（n=16/61 vs n=18/254）；表现出更高的血清 C 反应蛋白（平均（SD），109 mg/L（98.6）vs 59.3 mg/L（69.7））和血清降钙素原（平均（SD），11.3（27.8）μg/L vs 1.4（5.9）μg/L）。CAPE 死亡率风险评分对 30 天死亡率的 AUC 为 0.79（95%CI 0.73 至 0.85，p<0.001）；肺炎严重指数（PSI）为 0.80（95%CI 0.74 至 0.86，p<0.001）；新出现的混乱、血尿素氮、呼吸频率、血压、65 岁（CURB-65）评分分别为 0.76（95%CI 0.70 至 0.81，p<0.001）。CAPE 联合 CURB-65 模型的 AUC 为 0.83（95%CI 0.77 至 0.88，p<0.001）。表现最佳的模型是 CAPE 与 PSI 结合，AUC 为 0.84（95%CI 0.79 至 0.89，p<0.001）。
基于 CXR 的 CAPE 死亡率风险评分与传统肺炎严重程度评分相当，并在结合使用时提高了其区分能力。
