Drent M, Jacobs J A, Cobben N A, Costabel U, Wouters E F, Mulder P G
Department of Pulmonology, University Hospital, Maastricht, The Netherlands.
Respir Med. 2001 Oct;95(10):781-6. doi: 10.1053/rmed.2001.1153.
Recently we developed a validated computer program based on polychotomous logistic regression analysis using bronchoalveolar avage fluid (BALF) results to distinguish between the three most common interstitial lung diseases (ILD): sarcoidosis, idiopathic pulmonary fibrosis (IPF) and extrinsic allergic alveolitis (EAA) or drug-induced pneumonitis. One of the limitations of this program was that it was not useful in discriminating between infectious disorders and non-infectious disorders. Therefore, we added BALF samples obtained from patients with a confirmed bacterial pulmonary infection based on culture results > or = 10(4) cfum l(-1) (group I: n=31) to the study population mentioned above (group II: n=272). Notably, just one variable, i.e. the percentage of polymorphonuclear neutrophils, allowed us to distinguish between infectious and non-infectious disorders. The agreement of predicted with the actual diagnostic group membership was 99.67% (groups I and II). Additionally, 91.2% of the cases with ILD were correctly classified. In conclusion, this updated Windows version 2000 of the validated computer program provides a very reliable prediction of the correct diagnosis for an arbitrary patient with suspected pneumonia or with ILD given information obtained from BALF analysis results, and is thought to improve the diagnostic power of BALF analysis.
最近，我们基于多分类逻辑回归分析开发了一个经过验证的计算机程序，该程序利用支气管肺泡灌洗（BALF）结果来区分三种最常见的间质性肺疾病（ILD）：结节病、特发性肺纤维化（IPF）和外源性过敏性肺泡炎（EAA）或药物性肺炎。该程序的局限性之一在于它无法区分感染性疾病和非感染性疾病。因此，我们将根据培养结果≥10⁴cfu/ml确诊为细菌性肺部感染的患者的BALF样本（第一组：n = 31）添加到上述研究人群（第二组：n = 272）中。值得注意的是，仅一个变量，即多形核中性粒细胞百分比，就能让我们区分感染性和非感染性疾病。预测结果与实际诊断分组的一致性为99.67%（第一组和第二组）。此外，91.2%的ILD病例被正确分类。总之，这个经过验证的计算机程序的更新版Windows 2000，根据从BALF分析结果获得的信息，能为任意疑似肺炎或ILD患者的正确诊断提供非常可靠的预测，并且被认为能提高BALF分析的诊断能力。
