Dong Trinh Huu Khanh, Canas Liane S, Donovan Joseph, Beasley Daniel, Thuong-Thuong Nguyen Thuy, Phu Nguyen Hoan, Ha Nguyen Thi, Ourselin Sebastien, Razavi Reza, Thwaites Guy E, Modat Marc
Oxford University Clinical Research Unit, Viet Nam.
King's College London, United Kingdom.
PLoS One. 2025 May 23;20(5):e0321655. doi: 10.1371/journal.pone.0321655. eCollection 2025.
Tuberculous meningitis (TBM) leads to high mortality, especially amongst individuals with HIV. Predicting the incidence of disease-related complications is challenging, for which purpose the value of brain magnetic resonance imaging (MRI) has not been well investigated. We used a convolutional neural network (CNN) to explore the complementary contribution of brain MRI to the conventional prognostic determinants.
We pooled data from two randomised control trials of HIV-positive and HIV-negative adults with clinical TBM in Vietnam to predict the occurrence of death or new neurological complications in the first two months after the subject's first MRI session. We developed and compared three models: a logistic regression with clinical, demographic and laboratory data as reference, a CNN that utilised only T1-weighted MRI volumes, and a model that fused all available information. All models were fine-tuned using two repetitions of 5-fold cross-validation. The final evaluation was based on a random 70/30 training/test split, stratified by the outcome and HIV status. Based on the selected model, we explored the interpretability maps derived from the models.
215 patients were included, with an event prevalence of 22.3%. On the test set our non-imaging model had higher AUC (71.2% [Formula: see text] 1.1%) than the imaging-only model (67.3% [Formula: see text] 2.6%). The fused model was superior to both, with an average AUC = 77.3% [Formula: see text] 4.0% in the test set. The non-imaging variables were more informative in the HIV-positive group, while the imaging features were more predictive in the HIV-negative group. All three models performed better in the HIV-negative cohort. The interpretability maps show the model's focus on the lateral fissures, the corpus callosum, the midbrain, and peri-ventricular tissues.
Imaging information can provide added value to predict unwanted outcomes of TBM. However, to confirm this finding, a larger dataset is needed.
结核性脑膜炎（TBM）导致高死亡率，尤其是在艾滋病毒感染者中。预测疾病相关并发症的发生率具有挑战性，为此脑磁共振成像（MRI）的价值尚未得到充分研究。我们使用卷积神经网络（CNN）来探讨脑MRI对传统预后决定因素的补充作用。
我们汇总了越南两项针对临床TBM的艾滋病毒阳性和阴性成年人的随机对照试验数据，以预测受试者首次MRI检查后前两个月内死亡或新的神经系统并发症的发生情况。我们开发并比较了三种模型：以临床、人口统计学和实验室数据为参考的逻辑回归模型、仅利用T1加权MRI体积的CNN模型以及融合所有可用信息的模型。所有模型均使用5折交叉验证的两次重复进行微调。最终评估基于随机的70/30训练/测试分割，按结果和艾滋病毒状态分层。基于选定的模型，我们探索了从模型中得出的可解释性图谱。
纳入215例患者，事件发生率为22.3%。在测试集上，我们的非成像模型的AUC（71.2% [公式：见正文] 1.1%）高于仅成像模型（67.3% [公式：见正文] 2.6%）。融合模型优于两者，在测试集中平均AUC = 77.3% [公式：见正文] 4.0%。非成像变量在艾滋病毒阳性组中信息更多，而成像特征在艾滋病毒阴性组中预测性更强。所有三种模型在艾滋病毒阴性队列中表现更好。可解释性图谱显示模型关注外侧裂、胼胝体、中脑和脑室周围组织。
成像信息可为预测TBM的不良结局提供附加价值。然而，为证实这一发现，需要更大的数据集。
