Background

Clinical differentiation of fibrotic hypersensitivity pneumonitis (f-HP) remains challenging given variable and overlapping presentations with other fibrotic interstitial lung disease (f-ILD).

Objective

We derived a multivariable model for predicting histopathologic f-HP to better inform multidisciplinary team discussion (MDD) diagnosis, particularly when biopsy may be unsafe or cannot be achieved.

Methods

Patients with histopathologically-defined f-HP and other overlapping f-ILD were reviewed for distinguishing clinical and radiological variables. Using elastic net logistic regression, a penalized regression approach to minimize overfitting, a clinical model built on non-invasive assessments was derived for the prediction of histopathologic f-HP. This model was then validated in an independently derived external cohort from three sites.

Results

The derivation and validation cohorts consisted of 248 (84 cHP and 164 other f-ILD) and 157 (82 f-HP and 75 other f-ILD) histopathologically-defined patients, respectively (total study N = 405). Variables retained from the elastic net model included age in years (regression coefficient 0.033), male sex (−1.109), positive exposure history (1.318), percent predicted forced vital capacity (−0.021), radiologic peribronchovascular axial ILD distribution (0.199), mid (−0.22) or lower lobe (−0.839) craniocaudal or patchy (0.287) ILD distribution, upper (1.188) or equivalent upper and lower lobe (0.237) traction bronchiectasis, mosaic attenuation (1.164), and centrilobular nodules (2.045). Bias corrected AUC was 0.84 (standard error = 0.02) for the derivation cohort and 0.80 (CI 0.73–0.87) for the validation cohort.

Conclusions

This multivariable model demonstrated good predictive performance for delineating histopathologically-defined f-HP from other f-ILD as a means of avoiding or justifying biopsy and supporting MDD diagnostic confidence.

中文翻译：

---

组织病理学纤维化过敏性肺炎预测模型的推导和验证

背景

鉴于与其他纤维化间质性肺病 (f-ILD) 的多变和重叠表现，纤维化过敏性肺炎 (f-HP) 的临床鉴别仍然具有挑战性。

客观的

我们推导出了一个用于预测组织病理学 f-HP 的多变量模型，以更好地为多学科团队讨论 (MDD) 诊断提供信息，特别是在活检可能不安全或无法实现时。

方法

对具有组织病理学定义的 f-HP 和其他重叠 f-ILD 的患者进行了审查，以区分临床和放射学变量。使用弹性网络逻辑回归，一种惩罚回归方法，以尽量减少过度拟合，推导出建立在非侵入性评估基础上的临床模型，用于预测组织病理学 f-HP。然后，该模型在来自三个站点的独立派生的外部队列中得到验证。

结果

推导和验证队列分别由 248 名（84 名 cHP 和 164 名其他 f-ILD）和 157 名（82 名 f-HP 和 75 名其他 f-ILD）组织病理学定义的患者组成（总研究 N = 405）。从弹性网模型中保留的变量包括年龄（回归系数 0.033）、男性（-1.109）、阳性暴露史（1.318）、预测用力肺活量百分比（-0.021）、放射学支气管血管周围轴向 ILD 分布（0.199）、中部 (-0.22) 或下叶 (-0.839) 头尾或斑片状 (0.287) ILD 分布，上叶 (1.188) 或等效的上叶和下叶 (0.237) 牵引性支气管扩张，马赛克衰减 (1.164) 和小叶中心结节 (2.045)。推导队列的偏差校正 AUC 为 0.84（标准误差 = 0.02），验证队列的偏差校正 AUC 为 0.80（CI 0.73-0.87）。

结论

这种多变量模型展示了从其他 f-ILD 中描绘组织病理学定义的 f-HP 的良好预测性能，作为避免或证明活检和支持 MDD 诊断信心的手段。