TY - JOUR T1 -深度学习算法有助于标准化ATS/ERS呼吸测量可接受性和可用性标准JF -欧洲呼吸杂志JO - Eur Respir J DO - 10.1183/13993003.00603-2020 VL - 56 IS - 6 SP - 2000603 AU - Das, Nilakash AU - Verstraete, Kenneth AU - Stanojevic, Sanja AU - Topalovic, Marko AU - Aerts, Jean-Marie AU - Janssens,Wim Y1 - 20/12/01 UR - //www.qdcxjkg.com/content/56/6/2000603.abstract N2 -基本原理虽然美国胸科学会(ATS)/欧洲呼吸学会(ERS)肺功能测定的质量控制标准包括几个定量限制,但188bet官网地址它也需要人工目视检查。目前的方法是耗时的,导致高技术人员之间的差异。我们提出了一种称为卷积神经网络(CNN)的深度学习方法,以标准化呼吸测量机动的可接受性和可用性。方法和方法在2011-2012年美国国家健康和营养检查调查的36873条曲线中,技术人员标记54%的曲线符合ATS/ERS 2005的可接受标准,测试的开始和结束都令人满意,但在1秒内确定了93%的曲线具有可用的用力呼气量。我们将原始数据处理成最大呼气流量-体积曲线(MEFVC)的图像,计算ATS/ERS可量化标准,并开发了cnn,以确定90%曲线的机动可接受性和可用性。在剩余10%的曲线上对模型进行测试。我们计算Shapley值来解释模型。结果在测试集(n=3738)中,CNN的可接受性准确率为87%,可用性准确率为92%,后者表现出较高的敏感性(92%)和特异性(96%)。它们明显优于ATS/ERS基于规则的可量化模型(p<0.0001)。 Shapley interpretation revealed MEFVC<1 s (MEFVC pattern within first second of exhalation) and plateau in volume–time were most important in determining acceptability, while MEFVC<1 s entirely determined usability.Conclusion The CNNs identified relevant attributes in spirometric curves to standardise ATS/ERS manoeuvre acceptability and usability recommendations, and further provides individual manoeuvre feedback. Our algorithm combines the visual experience of skilled technicians and ATS/ERS quantitative rules in automating the critical phase of spirometry quality control.Deep-learning models were developed to standardise ATS/ERS spirometric acceptability and usability criteria. This approach reduces the intertechnician variability and provides instant feedback to the user https://bit.ly/3dNFe1i ER -