School of Public Health, University of Minnesota, Minneapolis, Minnesota.
South African National Bioinformatics Institute, University of the Western Cape, Cape Town, South Africa.
Am J Trop Med Hyg. 2024 Jul 16;111(3):546-553. doi: 10.4269/ajtmh.23-0789. Print 2024 Sep 4.
No accurate and rapid diagnostic test exists for tuberculous meningitis (TBM), leading to delayed diagnosis. We leveraged data from multiple studies to improve the predictive performance of diagnostic models across different populations, settings, and subgroups to develop a new predictive tool for TBM diagnosis. We conducted a systematic review to analyze eligible datasets with individual-level participant data (IPD). We imputed missing data and explored three approaches: stepwise logistic regression, classification and regression tree (CART), and random forest regression. We evaluated performance using calibration plots and C-statistics via internal-external cross-validation. We included 3,761 individual participants from 14 studies and nine countries. A total of 1,240 (33%) participants had "definite" (30%) or "probable" (3%) TBM by case definition. Important predictive variables included cerebrospinal fluid (CSF) glucose, blood glucose, CSF white cell count, CSF differential, cryptococcal antigen, HIV status, and fever presence. Internal validation showed that performance varied considerably between IPD datasets with C-statistic values between 0.60 and 0.89. In external validation, CART performed the worst (C = 0.82), and logistic regression and random forest had the same accuracy (C = 0.91). We developed a mobile app for TBM clinical prediction that accounted for heterogeneity and improved diagnostic performance (https://tbmcalc.github.io/tbmcalc). Further external validation is needed.
目前尚无准确、快速的结核性脑膜炎（TBM）诊断检测方法，导致诊断延误。我们利用来自多个研究的数据，改进了不同人群、环境和亚组的诊断模型的预测性能，从而开发了一种新的 TBM 诊断预测工具。我们进行了系统评价，以分析具有个体水平参与者数据（IPD）的合格数据集。我们对缺失数据进行了插补，并探索了三种方法：逐步逻辑回归、分类和回归树（CART）和随机森林回归。我们通过内部-外部交叉验证，使用校准图和 C 统计量评估性能。我们纳入了来自 14 项研究和 9 个国家的 3761 名个体参与者。共有 1240 名（33%）参与者根据病例定义患有“明确”（30%）或“可能”（3%）TBM。重要的预测变量包括脑脊液（CSF）葡萄糖、血糖、CSF 白细胞计数、CSF 差异、隐球菌抗原、HIV 状态和发热存在。内部验证表明，IPD 数据集之间的性能差异很大，C 统计值在 0.60 到 0.89 之间。在外部验证中，CART 的表现最差（C = 0.82），逻辑回归和随机森林具有相同的准确性（C = 0.91）。我们开发了一个 TBM 临床预测的移动应用程序，该应用程序考虑了异质性并提高了诊断性能（https://tbmcalc.github.io/tbmcalc）。还需要进一步的外部验证。
