Interstitial Lung Diseases Program, Division of Respirology and Sleep Medicine, Queen's University, 102 Stuart Street, Kingston, Ontario, K7L 2V7, Canada.
Division of Pulmonary, Critical Care and Sleep Medicine, University of Cincinnati, 231 Albert Sabin Way, ML 0564, Cincinnati, OH, 45267-0564, United States.
Respir Investig. 2024 Jul;62(4):670-676. doi: 10.1016/j.resinv.2024.05.010. Epub 2024 May 20.
A machine learning classifier system, Fibresolve, was designed and validated as an adjunct to non-invasive diagnosis in idiopathic pulmonary fibrosis (IPF). The system uses a deep learning algorithm to analyze chest computed tomography (CT) imaging. We hypothesized that Fibresolve is a useful predictor of mortality in interstitial lung diseases (ILD).
Fibresolve was previously validated in a multi-site >500-patient dataset. In this analysis, we assessed the usefulness of Fibresolve to predict mortality in a subset of 228 patients with IPF and other ILDs in whom follow up data was available. We applied Cox regression analysis adjusting for the Gender, Age, and Physiology (GAP) score and for other known predictors of mortality in IPF. We also analyzed the role of Fibresolve as tertiles adjusting for GAP stages.
During a median follow-up of 2.8 years (range 5 to 3434 days), 89 patients died. After adjusting for GAP score and other mortality risk factors, the Fibresolve score significantly predicted the risk of death (HR: 7.14; 95% CI: 1.31-38.85; p = 0.02) during the follow-up period, as did forced vital capacity and history of lung cancer. After adjusting for GAP stages and other variables, Fibresolve score split into tertiles significantly predicted the risk of death (p = 0.027 for the model; HR 1.37 for 2nd tertile; 95% CI: 0.77-2.42. HR 2.19 for 3rd tertile; 95% CI: 1.22-3.93).
The machine learning classifier Fibresolve demonstrated to be an independent predictor of mortality in ILDs, with prognostic performance equivalent to GAP based solely on CT images.
机器学习分类器系统 Fibresolve 被设计并验证为特发性肺纤维化 (IPF) 的无创诊断辅助工具。该系统使用深度学习算法分析胸部计算机断层扫描 (CT) 成像。我们假设 Fibresolve 是间质性肺疾病 (ILD) 死亡率的有用预测指标。
Fibresolve 先前在一个多站点>500 例患者的数据集得到了验证。在这项分析中，我们评估了 Fibresolve 在有随访数据的 228 例 IPF 和其他 ILD 患者亚组中预测死亡率的有用性。我们应用 Cox 回归分析，调整了性别、年龄和生理学 (GAP) 评分以及其他已知的 IPF 死亡率预测因素。我们还分析了 Fibresolve 作为 tertiles 调整 GAP 阶段的作用。
在中位数为 2.8 年（范围为 5 至 3434 天）的随访期间，有 89 例患者死亡。在调整 GAP 评分和其他死亡率风险因素后，Fibresolve 评分显著预测了死亡风险（HR：7.14；95%CI：1.31-38.85；p=0.02），用力肺活量和肺癌病史也是如此。在调整 GAP 阶段和其他变量后，Fibresolve 评分分为 tertiles 显著预测了死亡风险（模型 p=0.027；第 2 tertile 的 HR 为 1.37；95%CI：0.77-2.42；第 3 tertile 的 HR 为 2.19；95%CI：1.22-3.93）。
机器学习分类器 Fibresolve 证明是ILD 死亡率的独立预测指标，其预后性能与仅基于 CT 图像的 GAP 相当。
