The diagnosis of tuberculous meningitis in adults and adolescents: protocol for a systematic review and individual patient data meta-analysis to inform a multivariable prediction model

Diagnostic Prediction Model for Tuberculous Meningitis: An Individual Participant Data Meta-Analysis

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.

The application value of cerebrospinal fluid immunoglobulin in tuberculous meningitis

This article aims to study the value of cerebrospinal fluid (CSF) immunoglobulin in differential diagnosis, prediction, and prognosis of tuberculous meningitis (TBM). The clinical data of 65 patients with TBM in our hospital were collected, and 65 patients with cryptococcal meningitis (CM) were enrolled in 1:1 matching. Relevant data were collected for comparison. CSFs IgG [331.51 (164.85, 645.00) vs 129.00 (55.05, 251.00) ng/mL], IgM [22.38 (8.52, 40.18) vs 6.08 (2.19, 23.30) ng/mL], and IgA [64.11 (21.44, 115.48) vs 16.55 (4.76, 30.36) ng/mL] in the TBM group were higher than those in the CM group (P < 0.001). In the TBM group, after 24 weeks of treatment, the CSFs IgG, IgM, and IgA were significantly decreased, and the difference was statistically significant (P < 0.05). The predictive results of CSF immunoglobulin for TBM showed that IgG, IgM, and IgA all had some predictive value for TBM, and the combined predictive value of the three was the highest, with an area under the curve of 0.831 (95% CI: 0.774-0.881). Logistic regression analysis of CSF immunoglobulins and TBM prognosis showed that IgG [odds ratio (OR) = 4.796, 95% confidence interval (CI): 2.575-8.864], IgM (OR = 3.456, 95% CI: 2.757-5.754), and IgA (OR = 4.371, 95% CI: 2.731-5.856) were TBM risk factors for poor prognosis in patients. The levels of IgG, IgM, and IgA in CSF were positively correlated with the severity of cranial magnetic resonance imaging (MRI) in TBM patients (R2 = 0.542, F = 65.392, P < 0.05). CSFs IgG, IgM, and IgA can be used as a routine monitoring index for TBM patients, which has a certain reference value in differential diagnosis and efficacy evaluation.

IMPORTANCE

In clinical practice, physicians can determine the physical conditions of patients based on the levels of cerebrospinal fluids (CSFs) IgG, IgM, and IgA. Higher levels of CSFs IgG, IgM, and IgA suggest more possibility of tuberculous meningitis and worse prognosis and magnetic resonance imaging manifestations.

Modern Machine-Learning Predictive Models for Diagnosing Infectious Diseases

Controlling infectious diseases is a major health priority because they can spread and infect humans, thus evolving into epidemics or pandemics. Therefore, early detection of infectious diseases is a significant need, and many researchers have developed models to diagnose them in the early stages. This paper reviewed research articles for recent machine-learning (ML) algorithms applied to infectious disease diagnosis. We searched the Web of Science, ScienceDirect, PubMed, Springer, and IEEE databases from 2015 to 2022, identified the pros and cons of the reviewed ML models, and discussed the possible recommendations to advance the studies in this field. We found that most of the articles used small datasets, and few of them used real-time data. Our results demonstrated that a suitable ML technique depends on the nature of the dataset and the desired goal. Moreover, heterogeneous data could ensure the model's generalization, while big data, many features, and a hybrid model will increase the resulting performance. Furthermore, using other techniques such as deep learning and NLP to extract vast features from unstructured data is a powerful approach to enhancing the performance of ML diagnostic models.

Improving Technology to Diagnose Tuberculous Meningitis: Are We There Yet?

Diagnosis of tuberculous meningitis (TBM) remains challenging due to a paucity of high-performance diagnostics. Even those that have reasonable sensitivity are not adequate to 'rule out' TBM. Therefore, a combination of clinical factors alongside microbiological, molecular, and radiological investigations are utilized, depending on availability. A low threshold for starting empiric therapy in the appropriate clinical scenario remains crucial for good outcomes in many cases. Herein, we review the current TBM diagnostics landscape with a focus on limitations frequently encountered, such as diagnostic test performance, cost, laboratory infrastructure, and clinical expertise. Though molecular technologies, particularly GeneXpert MTB/Rif Ultra, have been a step forward, diagnosis of TBM remains difficult. We also provide an overview of promising technologies, such as cerebrospinal fluid (CSF) lactate, a new lipoarabinomannan test (FujiLAM), metagenomic next-generation sequencing, and transcriptomics that may further improve our TBM diagnostic capacity and lead to better outcomes.