Internal Medicine Service, Osakidetza/Basque Health Service, Mendaro Hospital, Gipuzkoa, Spain.
Mycobacterial Infection Study Group (GEIM), From the Spanish Infectious Diseases Society, Spain.
PLoS One. 2021 Nov 4;16(11):e0259203. doi: 10.1371/journal.pone.0259203. eCollection 2021.
To analyze the performance of adenosine deaminase in pleural fluid combined with other parameters routinely measured in clinical practice and assisted by machine learning algorithms for the diagnosis of pleural tuberculosis in a low prevalence setting, and secondly, to identify effusions that are non-tuberculous and most likely malignant.
We prospectively analyzed 230 consecutive patients diagnosed with lymphocytic exudative pleural effusion from March 2013 to June 2020. Diagnosis according to the composite reference standard was achieved in all cases. Pre-test probability of pleural tuberculosis was 3.8% throughout the study period. Parameters included were: levels of adenosine deaminase, pH, glucose, proteins, and lactate dehydrogenase, red and white cell counts and lymphocyte percentage in pleural fluid, as well as age. We tested six different machine learning-based classifiers to categorize the patients. Two different classifications were performed: a) tuberculous/non-tuberculous and b) tuberculous/malignant/other.
Out of a total of 230 patients with pleural effusion included in the study, 124 were diagnosed with malignant effusion and 44 with pleural tuberculosis, while 62 were given other diagnoses. In the tuberculous/non-tuberculous classification, and taking into account the validation predictions, the support vector machine yielded the best result: an AUC of 0.98, accuracy of 97%, sensitivity of 91%, and specificity of 98%, whilst in the tuberculous/malignant/other classification, this type of classifier yielded an overall accuracy of 80%. With this three-class classifier, the same sensitivity and specificity was achieved in the tuberculous/other classification, but it also allowed the correct classification of 90% of malignant cases.
The level of adenosine deaminase in pleural fluid together with cell count, other routine biochemical parameters and age, combined with a machine-learning approach, is suitable for the diagnosis of pleural tuberculosis in a low prevalence scenario. Secondly, non-tuberculous effusions that are suspected to be malignant may also be identified with adequate accuracy.
分析腺苷脱氨酶在胸腔积液中的表现，并结合临床实践中常规测量的其他参数，以及机器学习算法，以诊断低患病率环境下的胸腔结核，并其次，识别最有可能是非结核性和恶性的胸腔积液。
我们前瞻性分析了 2013 年 3 月至 2020 年 6 月期间连续 230 例诊断为淋巴细胞渗出性胸腔积液的患者。在整个研究过程中，所有病例均通过综合参考标准进行诊断。研究期间胸腔结核的预测试验概率为 3.8%。包括的参数有：胸腔液中腺苷脱氨酶、pH 值、葡萄糖、蛋白质和乳酸脱氢酶水平，红细胞和白细胞计数以及胸腔液中淋巴细胞百分比，以及年龄。我们测试了六种不同的基于机器学习的分类器来对患者进行分类。进行了两种不同的分类：a）结核/非结核和 b）结核/恶性/其他。
在总共 230 例胸腔积液患者中，124 例被诊断为恶性胸腔积液，44 例被诊断为胸腔结核，而 62 例被诊断为其他疾病。在结核/非结核分类中，考虑到验证预测，支持向量机产生了最佳结果：AUC 为 0.98，准确率为 97%，敏感度为 91%，特异性为 98%，而在结核/恶性/其他分类中，这种类型的分类器总体准确率为 80%。使用这种三分类分类器，在结核/其他分类中也可以达到相同的敏感度和特异性，并且还可以正确分类 90%的恶性病例。
胸腔液中的腺苷脱氨酶水平与细胞计数、其他常规生化参数和年龄相结合，并结合机器学习方法，适用于低患病率环境下的胸腔结核诊断。其次，也可以以足够的准确性识别出疑似恶性的非结核性胸腔积液。
