Tyrak Katarzyna Ewa, Pajdzik Kinga, Konduracka Ewa, Ćmiel Adam, Jakieła Bogdan, Celejewska-Wójcik Natalia, Trąd Gabriela, Kot Adrianna, Urbańska Anna, Zabiegło Ewa, Kacorzyk Radosław, Kupryś-Lipińska Izabela, Oleś Krzysztof, Kuna Piotr, Sanak Marek, Mastalerz Lucyna
2nd Department of Internal Medicine, Jagiellonian University Medical College, Cracow, Poland.
Coronary and Heart Failure Department, Jagiellonian University School of Medicine, John Paul II Hospital, Cracow, Poland.
Allergy. 2020 Jul;75(7):1649-1658. doi: 10.1111/all.14214. Epub 2020 Mar 3.
To date, there has been no reliable in vitro test to either diagnose or differentiate nonsteroidal anti-inflammatory drug (NSAID)-exacerbated respiratory disease (N-ERD). The aim of the present study was to develop and validate an artificial neural network (ANN) for the prediction of N-ERD in patients with asthma.
This study used a prospective database of patients with N-ERD (n = 121) and aspirin-tolerant (n = 82) who underwent aspirin challenge from May 2014 to May 2018. Eighteen parameters, including clinical characteristics, inflammatory phenotypes based on sputum cells, as well as eicosanoid levels in induced sputum supernatant (ISS) and urine were extracted for the ANN.
The validation sensitivity of ANN was 94.12% (80.32%-99.28%), specificity was 73.08% (52.21%-88.43%), and accuracy was 85.00% (77.43%-92.90%) for the prediction of N-ERD. The area under the receiver operating curve was 0.83 (0.71-0.90).
The designed ANN model seems to have powerful prediction capabilities to provide diagnosis of N-ERD. Although it cannot replace the gold-standard aspirin challenge test, the implementation of the ANN might provide an added value for identification of patients with N-ERD. External validation in a large cohort is needed to confirm our results.
迄今为止，尚无可靠的体外试验来诊断或鉴别非甾体抗炎药（NSAID）加重的呼吸系统疾病（N-ERD）。本研究的目的是开发并验证一种人工神经网络（ANN），用于预测哮喘患者的N-ERD。
本研究使用了一个前瞻性数据库，该数据库包含2014年5月至2018年5月期间接受阿司匹林激发试验的N-ERD患者（n = 121）和阿司匹林耐受患者（n = 82）。提取了18个参数用于人工神经网络，包括临床特征、基于痰液细胞的炎症表型，以及诱导痰液上清液（ISS）和尿液中的类花生酸水平。
人工神经网络预测N-ERD的验证敏感性为94.12%（80.32%-99.28%），特异性为73.08%（52.21%-88.43%），准确性为85.00%（77.43%-92.90%）。受试者工作特征曲线下面积为0.83（0.71-0.90）。
所设计的人工神经网络模型似乎具有强大的预测能力，可用于N-ERD的诊断。虽然它不能替代金标准的阿司匹林激发试验，但人工神经网络的应用可能为识别N-ERD患者提供附加价值。需要在大型队列中进行外部验证以证实我们的结果。
