Platelet dysfunction and coagulation assessment in patients of tuberculous meningitis

Analysis of risk factors for long-term mortality in patients with stage II and III tuberculous meningitis

OBJECTIVE

To investigate risk factors associated with long-term mortality in patients with stage II and III tuberculous meningitis (TBM).

METHODS

This retrospective analysis examined patients who were first diagnosed with stage II and III TBM at West China Hospital of Sichuan University between January 1, 2018 and October 1, 2019. Patients were followed via telephone and categorized into survival and mortality groups based on 4-year outcomes. Multivariate logistic regression identified independent risk factors for long-term mortality in stage II and III TBM.

RESULTS

In total, 178 patients were included, comprising 108 (60.7%) males and 36 (20.2%) non-survivors. Mean age was 36 ± 17 years. Compared to survivors, non-survivors demonstrated significantly higher age, heart rate, diastolic blood pressure, blood glucose, rates of headache, neurological deficits, cognitive dysfunction, impaired consciousness, hydrocephalus, and basal meningeal inflammation. This group also exhibited significantly lower Glasgow Coma Scale (GCS) scores, blood potassium, albumin, and cerebrospinal fluid chloride. Multivariate analysis revealed age (OR 1.042; 95% CI 1.015-1.070; P = 0.002), GCS score (OR 0.693; 95% CI 0.589-0.814; P < 0.001), neurological deficits (OR 5.204; 95% CI 2.056-13.174; P < 0.001), and hydrocephalus (OR 2.680; 95% CI 1.081-6.643; P = 0.033) as independent mortality risk factors. The ROC curve area under age was 0.613 (95% CI 0.506-0.720; P = 0.036) and 0.721 (95% CI 0.615-0.826; P < 0.001) under GCS score.

CONCLUSION

Advanced age, reduced GCS scores, neurological deficits, and hydrocephalus were identified as independent risk factors for mortality in stage II and III TBM patients.

Explainable machine learning for early predicting treatment failure risk among patients with TB-diabetes comorbidity

The present study aims to assess the treatment outcome of patients with diabetes and tuberculosis (TB-DM) at an early stage using machine learning (ML) based on electronic medical records (EMRs). A total of 429 patients were included at Chongqing Public Health Medical Center. The random-forest-based Boruta algorithm was employed to select the essential variables, and four models with a fivefold cross-validation scheme were used for modeling and model evaluation. Furthermore, we adopted SHapley additive explanations to interpret results from the tree-based model. 9 features out of 69 candidate features were chosen as predictors. Among these predictors, the type of resistance was the most important feature, followed by activated partial throm-boplastic time (APTT), thrombin time (TT), platelet distribution width (PDW), and prothrombin time (PT). All the models we established performed above an AUC 0.7 with good predictive performance. XGBoost, the optimal performing model, predicts the risk of treatment failure in the test set with an AUC 0.9281. This study suggests that machine learning approach (XGBoost) presented in this study identifies patients with TB-DM at higher risk of treatment failure at an early stage based on EMRs. The application of a convenient and economy EMRs based on machine learning provides new insight into TB-DM treatment strategies in low and middle-income countries.

Construction and Validation of a Diagnostic Scoring System for Predicting Active Pulmonary Tuberculosis in Patients with Positive T-SPOT Based on Indicators Associated with Coagulation and Inflammation: A Retrospective Cross-Sectional Study

Introduction

Tuberculosis (TB) is a life-threatening single infectious disease, which remains a major global public health concern. This study was to establish and validate a clinically practical diagnostic scoring system for predicting active pulmonary tuberculosis (APTB) in patients with positive tuberculosis T cell spot test [T-SPOT] using indicators associated with coagulation and inflammation.

Methods

A single-center retrospective cross-sectional study was performed to include patients with positive T-SOPT registered and hospitalized at Wuhan Jinyintan Hospital between January 2017 and December 2019. All patients were separated into the active pulmonary tuberculosis (APTB) group and the inactive pulmonary tuberculosis (IPTB) group, according to the diagnostic criteria from China's Expert Consensus for APTB and IPTB. Subsequently, the patients were randomized into a training set and a validation set at a ratio of 2:1. Indicators associated with coagulation and inflammation, including prothrombin time activity (PTA), activated partial thromboplastin time (APTT), thrombin time (TT), fibrinogen concentration (Fbg-C), C-reactive protein/albumin ratio (CAR), C-reactive protein/prealbumin ratio (CPR), neutrophils count/lymphocyte count ratio (NLR), platelet count/lymphocyte count ratio (PLR), monocyte count/lymphocyte count ratio (MLR), and erythrocyte sedimentation rate (ESR) were obtained from electronic medical record system (EMRS). Stepwise logistic regression was performed in the training set to build a diagnostic model for predicting APTB, which was transformed into an easily applicable scoring system via nomogram. Receiver operating characteristic (ROC) analysis, calibration curve (CC), and decision curve analysis (DCA) were conducted to evaluate the predictive performance of the established diagnostic scoring system.

Results

A total of 508 patients [training set (211 cases of APTB and 116 cases of IPTB) and validation set (103 cases of APTB and 78 cases of IPTB)] with positive T-SPOT were recruited in the study. Stepwise logistic regression showed that CPR, MLR, ESR, APTT and Fbg-C were independent predictors for APTB. The scoring system was subsequently formulated based on the abovementioned predictors, which correspond to scores of 10, 6, 7, 5, and 5, respectively. In addition, patients are more likely to be diagnosed as APTB when the cut-off score was ≥16 scores, while patients with <16 scores are more likely to be diagnosed as IPTB. The scoring system showed good predictive efficacy in both the training set [area under the curve (AUC): 0.887] and the validation set (AUC: 0.898). Furthermore, both CC and DCA confirmed the clinical utility of the scoring system.

Conclusion

The data suggest that the combination of indicators associated with coagulation and inflammation could serve as biomarkers to identify APTB in patients with positive T-SPOT. In addition, patients with positive T-SPOT were more prone to be diagnosed with APTB when having a combined total of scores ≥16 in the scoring system.

Prediction of recurrence of ischemic stroke within 1 year of discharge based on machine learning MRI radiomics

Purpose

This study aimed to investigate the value of a machine learning-based magnetic resonance imaging (MRI) radiomics model in predicting the risk of recurrence within 1 year following an acute ischemic stroke (AIS).

Methods

The MRI and clinical data of 612 patients diagnosed with AIS at the Second Affiliated Hospital of Nanchang University from March 1, 2019, to March 5, 2021, were obtained. The patients were divided into recurrence and non-recurrence groups according to whether they had a recurrent stroke within 1 year after discharge. Randomized splitting was used to divide the data into training and validation sets using a ratio of 7:3. Two radiologists used the 3D-slicer software to label the lesions on brain diffusion-weighted (DWI) MRI sequences. Radiomics features were extracted from the annotated images using the pyradiomics software package, and the features were filtered using the Least Absolute Shrinkage and Selection Operator (LASSO) regression analysis. Four machine learning algorithms, logistic regression (LR), Support Vector Classification (SVC), LightGBM, and Random forest (RF), were used to construct a recurrence prediction model. For each algorithm, three models were constructed based on the MRI radiomics features, clinical features, and combined MRI radiomics and clinical features. The sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC) were used to compare the predictive efficacy of the models.

Results

Twenty features were selected from 1,037 radiomics features extracted from DWI images. The LightGBM model based on data with three different features achieved the best prediction accuracy from all 4 models in the validation set. The LightGBM model based solely on radiomics features achieved a sensitivity, specificity, and AUC of 0.65, 0.671, and 0.647, respectively, and the model based on clinical data achieved a sensitivity, specificity, and AUC of 0.7, 0.799, 0.735, respectively. The sensitivity, specificity, and AUC of the LightGBM model base on both radiomics and clinical features achieved the best performance with a sensitivity, specificity, and AUC of 0.85, 0.805, 0.789, respectively.

Conclusion

The ischemic stroke recurrence prediction model based on LightGBM achieved the best prediction of recurrence within 1 year following an AIS. The combination of MRI radiomics features and clinical data improved the prediction performance of the model.

A Scoring System Based on Laboratory Parameters and Clinical Features to Predict Unfavorable Treatment Outcomes in Multidrug- and Rifampicin-Resistant Tuberculosis Patients

Background

The growth of antibiotic resistance to Mycobacterium TB represents a major barrier to the goal of "Ending the global TB epidemics". This study aimed to develop and validate a simple clinical scoring system to predict the unfavorable treatment outcomes (UTO) in multidrug- and rifampicin-resistant tuberculosis (MDR/RR-TB) patients.

Methods

A total of 333 MDR/RR-TB patients were recruited retrospectively. The clinical, radiological and laboratory features were gathered and selected by lasso regression. These variables with area under the receiver operating characteristic curve (AUC)>0.6 were subsequently submitted to multivariate logistic analysis. The binomial logistic model was used for establishing a scoring system based on the nomogram at the training set (N = 241). Then, another independent set was used to validate the scoring system (N = 92).

Results

The new scoring system consists of age (8 points), education level (10 points), bronchiectasis (4 points), red blood cell distribution width-coefficient of variation (RDW-CV) (7 points), international normalized ratio (INR) (7 points), albumin to globulin ratio (AGR) (5 points), and C-reactive protein to prealbumin ratio (CPR) (6 points). The scoring system identifying UTO has a discriminatory power of 0.887 (95% CI=0.835-0.939) in the training set, and 0.805 (95% CI=0.714-0.896) in the validation set. In addition, the scoring system is used exclusively to predict the death of MDR/RR-TB and has shown excellent performance in both training and validation sets, with AUC of 0.930 (95% CI=0.872-0.989) and 0.872 (95% CI=0.778-0.967), respectively.

Conclusion

This novel scoring system based on seven accessible predictors has exhibited good predictive performance in predicting UTO, especially in predicting death risk.

Clinical analysis of 103 cases of tuberculous meningitis complicated with hyponatremia in adults

OBJECTIVE

Tuberculous meningitis (TBM) is a common infection of the central nervous system. TBM with hyponatremia is very common. If hyponatremia is not treated properly, it might affect the outcome of TBM patients.

METHODS

We included 226 patients diagnosed with TBM who were admitted from August 2010 to August 2015 and retrospectively analyzed the clinical data of patients with and without hyponatremia.

RESULTS

In total, 45.6% (103/226) patients had hyponatremia and 54.4% (123/226) patients did not have hyponatremia. Serum sodium and severity of TBM were independent prediction factors of poor outcomes in TBM. The prognosis of patients with hyponatremia was worse than that of patients without hyponatremia. The mortality was 3.9% (4/103) in the hyponatremia group, while 0% (0/123) in the non-hyponatremia group. The degree of hyponatremia was related to imaging, cerebrospinal fluid (CSF) cell count and protein, severity of TBM, time to correct hyponatremia, and prognosis. We analyzed the causes of hyponatremia and found syndrome of inappropriate secretion of antidiuretic hormone (SIADH) was the most common cause (77.7%, 80/103), followed by cerebral salt wasting (CSW) (17.5%, 18/103). Comparing SIADH and CSW, there was a significant difference in mean blood pressure, albumin, and hematocrit, and no significant difference in demographic characteristics, imaging, CSF cell count and protein, severity, occurrence and correction time of hyponatremia, or prognosis.

CONCLUSION

TBM with hyponatremia was dominated by moderate hyponatremia, which often manifested as SIADH. The more severe hyponatremia was, the longer the correction time of hyponatremia, which will affect the prognosis of TBM patients.

Neurologic Complications of Tuberculosis

PURPOSE OF REVIEW

This article describes the current epidemiology, common clinical characteristics, and up-to-date evidence-based approaches to the diagnosis and management of the most common neurologic complications of tuberculosis (TB): tuberculous meningitis, intracranial tuberculoma, and spinal TB.

RECENT FINDINGS

Central nervous system (CNS) TB remains common and associated with significant mortality and neurologic sequelae worldwide. Human immunodeficiency virus (HIV) co-infection is strongly associated with both the development of and mortality due to CNS TB. Strongyloides co-infection is associated with reduced CNS inflammation and improved outcomes in the setting of tuberculous meningitis. Stroke remains a common complication of tuberculous meningitis, and emerging evidence suggests aspirin may be used in this context. Although a recent nucleic acid amplification test has demonstrated suboptimal sensitivity in the diagnosis of CNS TB, emerging diagnostic techniques include cell-free DNA, peripheral blood microRNA, metagenomic next-generation sequencing, and advanced imaging techniques, but these are not yet well validated. CNS TB is associated with high mortality even with current treatment regimens, although novel, promising strategies for treatment are under investigation, including a combination of IV isoniazid and ethambutol and high-dose rifampicin.

SUMMARY

TB can affect the nervous system in various ways and is associated with high mortality. Diagnosis remains challenging in endemic settings, with empiric treatment often initiated without a definitive diagnosis. Furthermore, optimal treatment regimens remain uncertain because current treatment for all forms of CNS TB is extrapolated from trials of tuberculous meningitis whereas the role of steroids in people with HIV and tuberculous meningitis remains controversial.

Host Directed Therapies for Tuberculous Meningitis

A dysregulated host immune response significantly contributes to morbidity and mortality in tuberculous meningitis (TBM). Effective host directed therapies (HDTs) are critical to improve survival and clinical outcomes. Currently only one HDT, dexamethasone, is proven to improve mortality. However, there is no evidence dexamethasone reduces morbidity, how it reduces mortality is uncertain, and it has no proven benefit in HIV co-infected individuals. Further research on these aspects of its use, as well as alternative HDTs such as aspirin, thalidomide and other immunomodulatory drugs is needed. Based on new knowledge from pathogenesis studies, repurposed therapeutics which act upon small molecule drug targets may also have a role in TBM. Here we review existing literature investigating HDTs in TBM, and propose new rationale for the use of novel and repurposed drugs. We also discuss host variable responses and evidence to support a personalised approach to HDTs in TBM.

Host Directed Therapies for Tuberculous Meningitis

A dysregulated host immune response significantly contributes to morbidity and mortality in tuberculous meningitis (TBM). Effective host directed therapies (HDTs) are critical to improve survival and clinical outcomes. Currently only one HDT, dexamethasone, is proven to improve mortality. However, there is no evidence dexamethasone reduces morbidity, how it reduces mortality is uncertain, and it has no proven benefit in HIV co-infected individuals. Further research on these aspects of its use, as well as alternative HDTs such as aspirin, thalidomide and other immunomodulatory drugs is needed. Based on new knowledge from pathogenesis studies, repurposed therapeutics which act upon small molecule drug targets may also have a role in TBM. Here we review existing literature investigating HDTs in TBM, and propose new rationale for the use of novel and repurposed drugs. We also discuss host variable responses and evidence to support a personalised approach to HDTs in TBM.

Integrating serum microRNAs and electronic health records improved the diagnosis of tuberculosis

Background

To verify the differential expression of miR‐30c and miR‐142‐3p between tuberculosis patients and healthy controls and to investigate the performance of microRNA (miRNA) and subsequently models for the diagnosis of tuberculosis (TB).

Methods

We followed up 460 subjects suspected of TB, and finally enrolled 132 patients, including 60 TB patients, 24 non‐TB disease controls (TB‐DCs), and 48 healthy controls (HCs). The differential expression of miR‐30c and miR‐142‐3p in serum samples of the TB patients, TB‐DCs, and HCs were identified by reverse transcription–quantitative real‐time PCR. Diagnostic models were developed by analyzing the characteristics of miRNA and electronic health records (EHRs). These models evaluated by the area under the curves (AUC) and calibration curves were presented as nomograms.

Results

There were differential expression of miR‐30c and miR‐142‐3p between TB patients and HCs (p < 0.05). Individual miRNA has a limited diagnostic value for TB. However, diagnostic performance has been both significantly improved when we integrated miR‐142‐3p and ordinary EHRs to develop two models for the diagnosis of tuberculosis. The AUC of the model for distinguishing tuberculosis patients from healthy controls has increased from 0.75 (95% CI: 0.66–0.84) to 0.96 (95% CI: 0.92–0.99) and the model for distinguishing tuberculosis patients from non‐TB disease controls has increased from 0.67 (95% CI: 0.55–0.79) to 0.94 (95% CI: 0.89–0.99).

Conclusions

Integrating serum miR‐142‐3p and EHRs is a good strategy for improving TB diagnosis.