BACKGROUND Interstitial lung disease (ILD) results in high morbidity and healthcare utilization. Diagnostic delays remain common and often occur in non-pulmonology settings. Screening for ILD in these settings has the potential to reduce diagnostic delays and improve patient outcomes. RESEARCH QUESTION Can a pulmonary function test (PFT)-derived diagnostic prediction tool (ILD-Screen) accurately identify incident ILD cases in patients undergoing PFT in non-pulmonology settings. STUDY DESIGN AND METHODS Clinical and physiologic PFT variables predictive of ILD were identified using iterative multivariable logistic regression models. ILD status was determined using a multi-reader approach. An ILD-Screen score was generated using final regression model coefficients, with a score ≥8 considered positive. ILD-Screen test performance was validated in an independent external cohort and applied prospectively to PFTs over one-year to identify incident ILD cases at our institution. RESULTS Variables comprising the ILD-Screen were age, height, total lung capacity, forced expiratory volume in one second, diffusion capacity and PFT indication. The ILD-Screen demonstrated consistent test performance across cohorts, with a sensitivity of 0.79 and specificity of 0.83 when applied prospectively. A positive ILD-Screen strongly predicted ILD (OR 18.6, 95% CI 9.4-36.9) and outperformed common ILD clinical features, including cough, dyspnea, lung crackles and restrictive lung physiology. Prospective ILD-Screen application resulted in a higher proportion of patients undergoing chest CT when compared to a historical control cohort (74% vs. 56%, respectively, p=0.003), with a significantly shorter median time to chest imaging (5.6 vs 21.1 months, respectively, p<0.001). INTERPRETATION The ILD-Screen demonstrated good test performance in predicting ILD across diverse geographic settings and when applied prospectively. Systematic ILD-Screen application has the potential to reduce diagnostic delays and facilitate earlier intervention in patients with ILD.

中文翻译：

---

间质性肺病诊断预测工具的推导和验证

背景间质性肺病（ILD）导致高发病率和医疗保健利用率。诊断延迟仍然很常见，并且经常发生在非肺病学环境中。在这些环境中筛查 ILD 有可能减少诊断延误并改善患者预后。研究问题 肺功能测试 (PFT) 衍生的诊断预测工具 (ILD-Screen) 能否准确识别在非肺病学环境中接受 PFT 的患者中发生的 ILD 病例。研究设计和方法 使用迭代多变量逻辑回归模型确定预测 ILD 的临床和生理 PFT 变量。ILD 状态是使用多阅读器方法确定的。使用最终回归模型系数生成 ILD-Screen 分数，分数 ≥ 8 被认为是阳性。ILD-Screen 测试性能在一个独立的外部队列中得到验证，并在一年内前瞻性地应用于 PFT，以识别我们机构中发生的 ILD 病例。结果 构成 ILD 筛查的变量包括年龄、身高、肺总量、一秒用力呼气量、扩散能力和 PFT 指征。ILD-Screen 展示了跨队列的一致测试性能，前瞻性应用时的灵敏度为 0.79，特异性为 0.83。阳性 ILD 筛查强烈预测 ILD（OR 18.6，95% CI 9.4-36.9），并且优于常见的 ILD 临床特征，包括咳嗽、呼吸困难、肺部湿啰音和限制性肺生理。与历史对照队列相比，前瞻性 ILD-Screen 应用导致接受胸部 CT 的患者比例更高（分别为 74% 和 56%，p=0。003），胸部成像的中位时间显着缩短（分别为 5.6 和 21.1 个月，p<0.001）。解释 ILD-Screen 在预测不同地理环境中的 ILD 和前瞻性应用时表现出良好的测试性能。系统的 ILD-Screen 应用有可能减少诊断延迟并促进对 ILD 患者的早期干预。