Sasaki Koji, Garcia-Manero Guillermo, Nigo Masayuki, Jabbour Elias, Ravandi Farhad, Wierda William G, Jain Nitin, Takahashi Koichi, Montalban-Bravo Guillermo, Daver Naval G, Thompson Philip A, Pemmaraju Naveen, Kontoyiannis Dimitrios P, Sato Junya, Karimaghaei Sam, Soltysiak Kelly A, Raad Issam I, Kantarjian Hagop M, Carter Brett W
Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX; Department of Hematology, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan.
Department of Leukemia, The University of Texas MD Anderson Cancer Center, Houston, TX.
Clin Lymphoma Myeloma Leuk. 2025 May;25(5):319-327. doi: 10.1016/j.clml.2024.11.013. Epub 2024 Nov 29.
The sensitivity of reverse-transcription polymerase chain reaction (RT-PCR) is limited for diagnosis of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Chest computed tomography (CT) is reported to have high sensitivity; however, given the limited availability of chest CT during a pandemic, the assessment of more readily available imaging, such as chest radiographs, augmented by artificial intelligence may substitute for the detection of the features of coronavirus disease 2019 (COVID-19) pneumonia.
We trained a deep convolutional neural network to detect SARS-CoV-2 pneumonia using publicly available chest radiography imaging data including 8,851 normal, 6,045 pneumonia, and 200 COVID-19 pneumonia radiographs. The entire cohort was divided into training (n = 13,586) and test groups (n = 1510). We assessed the accuracy of prediction with independent external data.
The sensitivity and positive predictive values of the assessment by artificial intelligence were 96.8% and 90.9%, respectively. In the first external validation of 204 chest radiographs among 107 patients with confirmed COVID-19, the artificial intelligence algorithm correctly identified 174 (85%) chest radiographs as COVID-19 pneumonia among 97 (91%) patients. In the second external validation with 50 immunocompromised patients with leukemia, the higher probability of the artificial intelligence assessment for COVID-19 was correlated with suggestive features of COVID-19, while the normal chest radiographs were closely correlated with the likelihood of normal chest radiographs by the artificial intelligence prediction.
The assessment method by artificial intelligence identified suspicious lung lesions on chest radiographs. This novel approach can identify patients for confirmatory chest CT before the progression of COVID-19 pneumonia.
逆转录聚合酶链反应（RT-PCR）在严重急性呼吸综合征冠状病毒2（SARS-CoV-2）诊断中的敏感性有限。据报道，胸部计算机断层扫描（CT）具有较高的敏感性；然而，考虑到在大流行期间胸部CT的可用性有限，利用人工智能增强的更容易获得的影像学检查，如胸部X线片，可能替代对2019冠状病毒病（COVID-19）肺炎特征的检测。
我们使用公开可用的胸部X线影像数据训练了一个深度卷积神经网络，以检测SARS-CoV-2肺炎，这些数据包括8851张正常、6045张肺炎和200张COVID-19肺炎的X线片。整个队列被分为训练组（n = 13586）和测试组（n = 1510）。我们使用独立的外部数据评估预测的准确性。
人工智能评估的敏感性和阳性预测值分别为96.8%和90.9%。在对107例确诊COVID-19患者的204张胸部X线片进行的首次外部验证中，人工智能算法在97例（91%）患者中正确识别出174张（85%）胸部X线片为COVID-19肺炎。在对50例白血病免疫功能低下患者进行的第二次外部验证中，人工智能评估为COVID-19的较高概率与COVID-19的提示性特征相关，而正常胸部X线片与人工智能预测的正常胸部X线片可能性密切相关。
人工智能评估方法可识别胸部X线片上可疑的肺部病变。这种新方法可以在COVID-19肺炎进展之前识别出需要进行胸部CT确诊的患者。
