Browse
Submit Data
Databases
API
Help

Dataset Information

16 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine-Learning-Based Approach to Differential Diagnosis in Tuberculous and Viral Meningitis.

ABSTRACT:

Background

Tuberculous meningitis (TBM) is the most severe form of tuberculosis, but differentiating between the diagnosis of TBM and viral meningitis (VM) is difficult. Thus, we have developed machine-learning modules for differentiating TBM from VM.

Material and methods

For the training data, confirmed or probable TBM and confirmed VM cases were retrospectively collected from five teaching hospitals in Korea between January 2000 - July 2018. Various machine-learning algorithms were used for training. The machine-learning algorithms were tested by the leave-one-out cross-validation. Four residents and two infectious disease specialists were tested using the summarized medical information.

Results

The training study comprised data from 60 patients with confirmed or probable TBM and 143 patients with confirmed VM. Older age, longer symptom duration before the visit, lower serum sodium, lower cerebrospinal fluid (CSF) glucose, higher CSF protein, and CSF adenosine deaminase were found in the TBM patients. Among the various machine-learning algorithms, the area under the curve (AUC) of the receiver operating characteristics of artificial neural network (ANN) with ImperativeImputer for matrix completion (0.85; 95% confidence interval 0.79 - 0.89) was found to be the highest. The AUC of the ANN model was statistically higher than those of all the residents (range 0.67 - 0.72, P <0.001) and an infectious disease specialist (AUC 0.76; P = 0.03).

Conclusion

The machine-learning techniques may play a role in differentiating between TBM and VM. Specifically, the ANN model seems to have better diagnostic performance than the non-expert clinician.

SUBMITTER: Jeong YS

PROVIDER: S-EPMC8032912 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Identification of protein biomarkers in host cerebrospinal fluid for differential diagnosis of tuberculous meningitis and other meningitis.

Project description:Background and purposeThe diagnosis of tuberculous meningitis (TBM) is difficult due to the lack of sensitive methods. Identification of TBM-specific biomarkers in the cerebrospinal fluid (CSF) may help diagnose and improve our understanding of TBM pathogenesis.Patients and methodsOf the 112 suspected patients with TBM prospectively enrolled in the study, 32 patients with inconclusive diagnosis, non-infectious meningitis, and long-term treatment with hormones and immunosuppressants were excluded. The expression of 8 proteins in the CSF was analyzed using ELISA in 22 patients with definite TBM, 18 patients with probable TBM, and 40 patients with non-TBM.ResultsSignificant differences in the expression of 7 proteins were detected between the TBM and non-TBM groups (P < 0.01). Unsupervised hierarchical clustering (UHC) analysis revealed a disease-specific profile consisting of 7 differentially expressed proteins for TBM diagnosis, with an accuracy of 82.5% (66/80). Logistic regression with forward stepwise analysis indicated that a combination of 3 biomarkers (APOE_APOAI_S100A8) showed a better ability to discriminate TBM from patients with non-TBM [area under the curve (AUC) = 0.916 (95%CI: 0.857-0.976)], with a sensitivity of 95.0% (95%CI: 83.1-99.4%) and a specificity of 77.5% (95%CI: 61.5-89.2%).ConclusionOur results confirmed the potential ability of CSF proteins to distinguish TBM from patients with non-TBM and provided a useful panel for the diagnosis of TBM.

| S-EPMC9393334 | biostudies-literature

Challenges in the diagnosis of tuberculous meningitis.

Project description:Tuberculosis (TB) continues to pose a significant public health problem. Tuberculous meningitis (TBM) is the most severe form of extra-pulmonary TB. TBM carries a high mortality rate, including for those receiving treatment for TB. Diagnosis of TBM is difficult for clinicians as it can clinically present similarly to other forms of meningitis. The difficulty in diagnosis often leads to a delay in treatment and subsequent mortality. Those who survive are left with long-term sequelae leading to lifelong disability. The microbiologic diagnosis of TBM requires the isolation of Mycobacterium tuberculosis from the cerebrospinal fluid (CSF) of an infected patient. The diagnosis of tuberculous meningitis continues to be challenging for clinicians. Unfortunately, many cases of TBM cannot be confirmed based on clinical and imaging findings as the clinical findings are nonspecific, while laboratory techniques are largely insensitive or slow. Until recently, the lack of accessible and timely tests has contributed to a delay in diagnosis and subsequent morbidity and mortality for many patients, particularly those in resourcelimited settings. The availability of Xpert Ultra and point-of-care lipoarabinomannan (LAM) testing could represent a new era of prompt diagnosis and early treatment of tuberculous meningitis. However, clinicians must be cautious when ruling out TBM with Xpert Ultra due to its low negative predictive value. Due to the limitations of current diagnostics, clinicians should utilize a combination of diagnostic modalities in order to prevent morbidity in patients with TBM.

| S-EPMC7240715 | biostudies-literature

Decision-making in the diagnosis of tuberculous meningitis.

Project description:Tuberculous meningitis (TBM) is the most devastating form of tuberculosis (TB) but diagnosis is difficult and delays in initiating therapy increase mortality. All currently available tests are imperfect; culture of Mycobacterium tuberculosis from the cerebrospinal fluid (CSF) is considered the most accurate test but is often negative, even when disease is present, and takes too long to be useful for immediate decision making. Rapid tests that are frequently used are conventional Ziehl-Neelsen staining and nucleic acid amplification tests such as Xpert MTB/RIF and Xpert MTB/RIF Ultra. While positive results will often confirm the diagnosis, negative tests frequently provide insufficient evidence to withhold therapy. The conventional diagnostic approach is to determine the probability of TBM using experience and intuition, based on prevalence of TB, history, examination, analysis of basic blood and CSF parameters, imaging, and rapid test results. Treatment decisions may therefore be both variable and inaccurate, depend on the experience of the clinician, and requests for tests may be inappropriate. In this article we discuss the use of Bayes' theorem and the threshold model of decision making as ways to improve testing and treatment decisions in TBM. Bayes' theorem describes the process of converting the pre-test probability of disease to the post-test probability based on test results and the threshold model guides clinicians to make rational test and treatment decisions. We discuss the advantages and limitations of using these methods and suggest that new diagnostic strategies should ultimately be tested in randomised trials.

| S-EPMC7490569 | biostudies-literature

Novel approach based on one-tube nested PCR and a lateral flow strip for highly sensitive diagnosis of tuberculous meningitis.

Project description:Rapid and sensitive detection of Mycobacterium tuberculosis (M. Tb) in cerebrospinal fluid is crucial in the diagnosis of tuberculous meningitis (TBM), but conventional diagnostic technologies have limited sensitivity and specificity or are time-consuming. In this work, a novel, highly sensitive molecular diagnostic method, one-tube nested PCR-lateral flow strip test (OTNPCR-LFST), was developed for detecting M. tuberculosis. This one-tube nested PCR maintains the sensitivity of conventional two-step nested PCR and reduces both the chance of cross-contamination and the time required for analysis. The PCR product was detected by a lateral flow strip assay, which provided a basis for migration of the test to a point-of-care (POC) microfluidic format. The developed assay had an improved sensitivity compared with traditional PCR, and the limit of detection was up to 1 fg DNA isolated from M. tuberculosis. The assay was also specific for M. tuberculosis, and no cross-reactions were found in other non-target bacteria. The application of this technique to clinical samples was successfully evaluated, and OTNPCR-LFST showed 89% overall sensitivity and 100% specificity for TBM patients. This one-tube nested PCR-lateral flow strip assay is useful for detecting M. tuberculosis in TBM due to its rapidity, high sensitivity and simple manipulation.

| S-EPMC5662171 | biostudies-literature

Radiomics and machine learning for the diagnosis of pediatric cervical non-tuberculous mycobacterial lymphadenitis.

Project description:Non-tuberculous mycobacterial (NTM) infection is an emerging infectious entity that often presents as lymphadenitis in the pediatric age group. Current practice involves invasive testing and excisional biopsy to diagnose NTM lymphadenitis. In this study, we performed a retrospective analysis of 249 lymph nodes selected from 143 CT scans of pediatric patients presenting with lymphadenopathy at the Montreal Children's Hospital between 2005 and 2018. A Random Forest classifier was trained on the ten most discriminative features from a set of 1231 radiomic features. The model classifying nodes as pyogenic, NTM, reactive, or proliferative lymphadenopathy achieved an accuracy of 72%, a precision of 68%, and a recall of 70%. Between NTM and all other causes of lymphadenopathy, the model achieved an area under the curve (AUC) of 89%. Between NTM and pyogenic lymphadenitis, the model achieved an AUC of 90%. Between NTM and the reactive and proliferative lymphadenopathy groups, the model achieved an AUC of 93%. These results indicate that radiomics can achieve a high accuracy for classification of NTM lymphadenitis. Such a non-invasive highly accurate diagnostic approach has the potential to reduce the need for invasive procedures in the pediatric population.

| S-EPMC8863781 | biostudies-literature

The association between serum sodium level and tuberculous meningitis compared with viral and bacterial meningitis.

Project description:We evaluated the association between hyponatremia and tuberculous meningitis (TBM) with the aim of providing additional information for differential diagnosis from other types of infectious meningitis, especially viral meningitis (VM). Cross-sectional and longitudinal data involving 5026 participants older than 18 years were analyzed in the total population and a propensity-matched population. The initial and lowest sodium levels and longitudinal changes in TBM, bacterial meningitis (BM), and VM patients were compared. Participants in the TBM group were enrolled when they were diagnosed as possible, probable, or definite TBM according to the Marais' criteria. The initial serum sodium level was significantly lower in TBM patients than in BM and VM patients (136.9 ± 5.9 vs. 138.3 ± 4.7 mmol/L, p < 0.001 for TBM vs. BM, and 139.0 ± 3.1, p < 0.001 for TBM vs. VM), and it decreased significantly more steeply to lower levels in both the TBM and BM patients compared with VM patients. The lowest serum sodium level was in the order of TBM < BM < VM patients, and the change was statistically significant in all subgroups (131.8 ± 6.4, 133.1 ± 5.1, 137.4 ± 3.7, respectively, p < 0.001). Participants with lower serum sodium level were more likely to have a diagnosis of TBM rather than VM, and this association was more pronounced for the lowest sodium level than the initial sodium level [OR 4.6 (95% CI 2.4-8.8, p < 0.001)]. These findings indicate that baseline and longitudinal evaluation of serum sodium level can provide information for differential diagnosis of TBM from BM or VM.

| S-EPMC8149664 | biostudies-literature

Genome-wide miRNA analysis reveals different miRNAs between Tuberculous and viral Meningitis

Project description:In order to identify the potential biomarkers for discriminating tuberculous meningitis (TBM) and viral meningitis (VM) and to reveal the different pathophysiological processes between TBM and VM, a genome-wide miRNA screenings of peripheral blood mononuclear cells (PBMCs) from TBM, VM, and healthy controls (HCs) using microarray assay was performed (12 samples). Twenty-eight differentially expressed miRNAs were identified between TBM and VM, and 11 differentially expressed miRNAs were identified between TBM and HCs. The 6 overlapping miRNAs detected in both TBM vs. VM and TBM vs. HCs were verified by qPCR analysis and showed a 100% consistent result with that in microarray test.

2019-10-02 | GSE131708 | GEO

Tuberculous Meningitis in Pediatric Patients

Project description:Whole blood transcriptional profiles in children with or without tuberculous meningitis (TBM) were compared using RNA-Seq and a biomarker signature driven by inflammasome activation and signaling was identified

2019-08-06 | GSE111459 | GEO

Structural switching electrochemical DNA aptasensor for the rapid diagnosis of tuberculous meningitis.

Project description:BackgroundTuberculous meningitis (TBM) is the most devastating manifestation of extra-pulmonary tuberculosis. About 33% of TBM patients die due to very late diagnosis of the disease. Conventional diagnostic methods based on signs and symptoms, cerebrospinal fluid (CSF) smear microscopy or liquid culture suffer from either poor sensitivity or long turnaround time (up to 8 weeks). Therefore, in order to manage the disease efficiently, there is an urgent and unmet need for a rapid and reliable diagnostic test.MethodsIn the current study, to address the diagnostic challenge of TBM, a highly rapid and sensitive structural switching electrochemical aptasensor was developed by combining the electrochemical property of methylene blue (MB) with the molecular recognition ability of a ssDNA aptamer. To demonstrate the clinical diagnostic utility of the developed aptasensor, a blinded study was performed on 81 archived CSF specimens using differential pulse voltammetry.ResultsThe electrochemical aptasensor developed in the current study can detect as low as 10 pg HspX in CSF background and yields a highly discriminatory response (P<0.0001) for TBM and not-TBM categories with ~95% sensitivity and ~97.5% specificity and has the ability to deliver sample-to-answer in ≤30 minutes.ConclusionIn summary, we demonstrate a new aptamer-based electrochemical biosensing strategy by exploiting the target-induced structural switching of H63 SL-2 M6 aptamer and electroactivity of aptamer-tagged MB for the detection of HspX in CSF samples for the diagnosis of TBM. Further, the clinical utility of this sensor could be extended for the diagnosis of other forms of tuberculosis in the near future.

| S-EPMC6440448 | biostudies-literature

Gene Expression Profiling of Tuberculous Meningitis

Project description:Tuberculous meningitis is one of the fatal forms of extra pulmonary disease associated with high mortality and severe neurological defects in affected individuals. We have carried out transcriptome level analysis using whole human genome microarrays to identify differential expression of genes between tuberculous meningitis and normals. In our gene expression analysis, we found 2,434 genes that were differentially erexpressed with 2 or more than 2 fold changes between tuberculous meningitis compared to normal cases. Most of the genes encoded many of the proteins, which involves metabolism, energy pathways, cell growth and/or maintenance, transport and cell communication and signal transduction. We have performed immunohistochemistry for the validation of some of the novel candidates identified in our microarray studies.!Series_overall_design = Present study carried out mRNA expression profiling of five samples from patients diagnosed with tuberculous meningitis and four head injury cases were used as controls. We have used 4X44K arrays from agilent plaform. To validate our microarray results, we have done Immunohistochemistry on 15 TBM cases with control groups.

2011-07-01 | GSE23074 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data