Materiały źródłowe

• #1 Using an Artificial Intelligence Approach to Predict the Adverse Effects and Prognosis of Tuberculosis

  https://www.mdpi.com/2075-4418/13/6/1075

  Using an Artificial Intelligence Approach to Predict the Adverse Effects and Prognosis of Tuberculosis […] Tuberculosis (TB) is one of the leading causes of death worldwide and a major cause of ill health. […] Without treatment, the mortality rate of TB is approximately 50%; with treatment, most patients with TB can be cured. […] Our study aimed to build models using an artificial intelligence/machine learning approach to predict acute hepatitis, acute respiratory failure, and mortality after TB treatment. […] The results showed that our models using the six AI algorithms all had a high area under the receiver operating characteristic curve (AUC) in predicting acute hepatitis, respiratory failure, and mortality, and the AUCs ranged from 0.920 to 0.766, 0.884 to 0.797, and 0.834 to 0.737, respectively.

• #2 Factors predictive of the success of tuberculosis treatment: A systematic review with meta-analysis | PLOS One

  https://journals.plos.org/plosone/article%3Fid=10.1371%2Fjournal.pone.0226507

  A total of 151 studies met the criteria for inclusion in this review. The success rate for the treatment of drug-sensitive TB in adults was 80.1% (95% CI: 78.481.7). America had the lowest treatment success rate, 75.9% (95% CI: 73.877.9), and Oceania had the highest, 83.9% (95% CI: 75.291.0). In children, the success rate was 84.8% (95% CI: 77.790.7); in patients coinfected with HIV, it was 71.0% (95% CI: 63.777.8), in patients with multidrug-resistant TB, it was 58.4% (95% CI: 51.464.6), in patients with and extensively drug-resistant TB it was 27.1% (12.744.5). Patients with negative sputum smears two months after treatment were almost three times more likely to be successfully treated (OR 2.7; 1.54.8), whereas patients younger than 65 years (OR 2.0; 1.72.4), nondrinkers (OR 2.0; 1.62.4) and HIV-negative patients (OR 1.9; 1.62.5) were two times more likely to be successfully treated. […] The success of TB treatment at the global level was good, but was still below the defined threshold of 85%. Factors such as age, sex, alcohol consumption, smoking, lack of sputum conversion at two months of treatment and HIV affected the success of TB treatment.

• #3

  https://link.springer.com/article/10.1007/s40121-023-00887-x

  Evaluating therapy efficacy is crucial for patients with tuberculosis (TB), especially those with drug-resistant tuberculosis (DR-TB). […] There is an urgent need for dependable biomarkers to evaluate therapy efficacy in patients with PTB. […] Although some biomarkers have potential in evaluating the efficacy of therapy in patients with PTB, they also have some limitations. […] Further research, validation, and optimization are required to identify the most reliable and effective alternative biomarkers and apply them to clinical practice. […] Evaluating the efficacy of pulmonary tuberculosis (PTB) therapy is vital for treatment decision-making, improving the cure rate, and preventing the transmission of tuberculosis. […] The conventional methods for evaluating efficacy of therapy for PTB have limitations, including low sensitivity and a long culture period.

• #4

  https://link.springer.com/article/10.1007/s40121-023-00887-x

  Further studies are needed to identify the most reliable and effective alternative biomarkers and apply them to clinical practice. […] Early evaluation of TB therapy efficacy is beneficial for timely adjustment of therapy and improvement of cure rates, which can help control the spread of TB. […] Evaluating treatment outcomes, determining therapy efficacy, and adjusting treatment plans earlier are important steps in the course of therapy to prevent disease progression. […] Traditional evaluation methods have certain drawbacks, which have led to the investigation of new biomarkers and imaging techniques for monitoring the efficacy of ATTB treatment. […] These novel biomarkers and imaging techniques can predict ATTB therapy efficacy earlier and faster, thereby improving clinical outcomes and controlling pulmonary tuberculosis (PTB) outbreaks.

• #5 Development and validation of a prediction model for unsuccessful treatment outcomes in patients with multi-drug resistance tuberculosis | BMC Infectious Diseases | Full Text

  https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-023-08193-0

  The World Health Organization has reported that the treatment success rate of multi-drug resistance tuberculosis is approximately 57% globally. […] The factors associated with unsuccessful treatment outcomes have been widely examined, but only a few studies have developed prediction models. […] We aimed to develop and validate a simple clinical prediction model for unsuccessful treatment outcomes in patients with multi-drug resistance pulmonary tuberculosis (MDR-PTB). […] After LASSO regression and multivariate logistic analyses, no health education, advanced age, being male, and larger extent lung involvement were identified as prognostic factors. […] These four prognostic factors were used to build the prediction nomograms. […] This indicated that the model was accurate in predicting unsuccessful treatment outcomes.

• #6 Development and validation of a prediction model for unsuccessful treatment outcomes in patients with multi-drug resistance tuberculosis | BMC Infectious Diseases | Full Text

  https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-023-08193-0

  We found that a year increase in age led to a 4% increase in unsuccessful treatment outcomes. […] Previous studies have reported that unsuccessful treatment outcomes are associated with age. […] A study from the Philippines reported that better general TB knowledge could protect patients with MDR-TB from being lost to follow-up. […] Therefore, health education should be provided to patients with MDR-TB. […] As shown in our study, no health education patients had 1.56 times higher odds of unsuccessful treatment outcomes than patients who received health education. […] Our model has a few advantages. First, the four factors used in the model are baseline characteristics that can be acquired easily. […] Despite these limitations, we developed an accurate predictive model for unsuccessful treatment outcomes in patients with MDR-TB. […] A predictive model and nomogram for predicting unsuccessful treatment outcomes in patients with MDR-PTB were built and showed good discrimination and calibration.

• #7 A Clinical Prediction Model for Unsuccessful Pulmonary Tuberculosis Treatment Outcomes

  https://pmc.ncbi.nlm.nih.gov/articles/PMC8946703/

  We detail the development and internal validation of a prognostic model, including 7 easily collected variables that accurately predict unsuccessful pulmonary tuberculosis treatment outcome. […] The prediction model developed in this study performed well compared with external validation of the Costa-Veiga model, which had, at best, a c-statistic of 0.68 (95% CI, .64.71). […] The model can be implemented with pen and paper, a nomogram, or using a web application. […] The individual risks derived from the model may be useful in future studies to allocate resources or target interventions to patients at the highest risk of unsuccessful outcomes.

• #8 A Clinical Prediction Model for Unsuccessful Pulmonary Tuberculosis Treatment Outcomes

  https://pmc.ncbi.nlm.nih.gov/articles/PMC8946703/

  Despite widespread availability of curative therapy, tuberculosis (TB) treatment outcomes remain suboptimal. […] Using baseline clinical data, we developed a prediction model for unsuccessful TB treatment outcome and evaluated the incremental value of human immunodeficiency virus (HIV) related severity and isoniazid acetylator status. […] The final model included 7 baseline predictors: hemoglobin, HIV infection, drug use, diabetes, age, education, and tobacco use. […] The model demonstrated good discrimination (c-statistic=0.77; 95% confidence interval, .73.80) and was well calibrated (optimism-corrected intercept and slope, 0.12 and 0.89, respectively). […] Using information readily available at treatment initiation, the prediction model performed well in this population. […] The findings may guide future work to allocate resources or inform targeted interventions for high-risk patients.

• #9 Development and validation of a prediction model for unsuccessful treatment outcomes in patients with multi-drug resistance tuberculosis | BMC Infectious Diseases | Full Text

  https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-023-08193-0

  We built a predictive model and established a nomogram for unsuccessful treatment outcomes of multi-drug resistance pulmonary tuberculosis based on baseline characteristics. […] This predictive model showed good performance and could be used as a tool by clinicians to predict who among their patients will have an unsuccessful treatment outcome. […] Prediction models can help clinicians identify patients at risk of unsuccessful treatment outcomes. […] A prediction model for the treatment outcomes of sensitive tuberculosis has been developed in China. […] However, few studies have developed models to predict the treatment outcomes of MDR-TB. […] Our goal was to develop a prediction model to help clinicians identify patients with MDR pulmonary tuberculosis (MDR-PTB) at risk of unsuccessful treatment outcomes.

• #10 Development and validation of a risk prediction model for pulmonary tuberculosis among presumptive tuberculosis cases in Ethiopia | BMJ Open

  https://bmjopen.bmj.com/content/13/12/e076587

  We developed a risk score that combines TB contact, number of classical TB symptoms and CXR abnormality to estimate individual risk of pulmonary TB among patients with presumptive TB. […] The final prediction model included three factors with different scores: (1) TB contact history, (2) chest X-ray (CXR) abnormality and (3) two or more symptoms of TB. […] The optimal cut-off point for the risk score was 6 and was found to have a good discrimination accuracy (c-statistic=0.70, 95%CI: 0.65 to 0.75). […] The risk score has sensitivity of 51.1%, specificity of 79.9%, positive predictive value of 4.3% and negative predictive value of 98.9%. […] Though the score is easy to calculate and internally validated, it needs external validation before widespread implementation in a new setting.

• #11 Bacterial load slopes represent biomarkers of tuberculosis therapy success, failure, and relapse | Communications Biology

  https://www.nature.com/articles/s42003-021-02184-0

  Therefore, the time-to-extinction of all bacillary populations marks the required minimum duration of therapy in order to avoid relapse. […] The ability to prevent relapse is termed sterilizing activity because it is presumed to require killing nearly of all bacilli remaining after the initial phase of therapy. […] The slope decision rule based on s=0.15 has a sensitivity of 92% and a specificity of 89% in predicting relapses from failures. […] Thus, the biomarkers we derived were highly specific at identifying relapse-free cure, therapy failure, and relapse.

• #12 Bacterial load slopes represent biomarkers of tuberculosis therapy success, failure, and relapse | Communications Biology

  https://www.nature.com/articles/s42003-021-02184-0

  There is an urgent need to discover biomarkers that are predictive of long-term TB treatment outcomes, since treatment is expense and prolonged to document relapse. […] We computed bacterial kill rates, f for fast- and s for slow/non-replicating bacteria, using patient sputum data to determine treatment duration by computing time-to-extinction of all bacterial subpopulations. […] We then derived a s-slope-based rule using first 8 weeks sputum data, that demonstrated a sensitivity of 92% and a specificity of 89% at predicting relapse-free cure for 2, 3, 4, and 6 months TB regimens. […] These biomarkers will accelerate evaluation of novel TB regimens, aid better clinical trial designs and will allow personalization of therapy duration in routine treatment programs. […] Thus, it is of crucial importance to identify TB treatment regimens that are equally as effective in drug-resistant TB as in drug-susceptible TB, to identify regimens that can shorten therapy duration, and to identify early biomarkers that obviate the need for 2-year follow up.

• #13 Computational and Empirical Studies Predict Mycobacterium tuberculosis-Specific T Cells as a Biomarker for Infection Outcome | PLOS Computational Biology

  https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1004804

  Identifying biomarkers for tuberculosis (TB) is an ongoing challenge in developing immunological correlates of infection outcome and protection. […] A major hurdle in controlling TB is the lack of accurate biomarkers that correlate prognosis and progression to infection. […] A key step in developing effective vaccines and possibly shorter treatment regimens is the ability to identify biomarkers that correlate prognosis and progression to infection. […] We found that Mtb-specific frequencies of effector T cell phenotypes (i.e., both CD4+ and CD8+) in the blood can be targeted to distinguish infection outcomes, with a clear separation between median trajectories of active versus latent TB late during infection progression (~300 days). […] Overall, we predict that frequencies of Mtb-specific effector CD4+ and CD8+ T cells in blood are significantly higher (from 2- to 4- fold) in an active versus a latent Mtb-infected NHP and thus a combination of these cells and various time points post-infection should be targeted as potential biomarkers of Mtb infection progression.

• #14

  https://link.springer.com/article/10.1007/s40121-023-00887-x

  The changes in certain host immune markers vary between patients with drug-sensitive PTB and patients with drug-resistant PTB, and even within the same patient group, the same type of immune marker may exhibit different changes under different Mycobacterium tuberculosis (MTB) antigen stimuli. […] Therefore, there is an urgent need for improved biomarkers that can accurately reflect therapy efficacy and guide treatment decisions to control PTB outbreaks. […] The emergence of new biomarkers, including those derived from MTB itself and its host, as well as advancements in detection methods, offer the possibility of rapid, accurate, and efficient monitoring of PTB therapy efficacy. […] Monitoring changes in MTB-specific immune factors, intracellular immune factors, and T cell subsets during ATTB treatment can be useful for assessing therapy efficacy and predicting prognosis in the early stages.

• #15

  https://link.springer.com/article/10.1007/s40121-023-00887-x

  Monitoring MTB-nonspecific host biomarkers during ATTB treatment, including those identified through omics analysis, is a promising approach. […] These biomarkers can improve the specificity of prediction, although they may involve complex procedures and have high requirements. […] Monitoring MTB-nonspecific host biomarkers during ATTB treatment, including those identified through omics analysis, is a promising approach. […] The alterations in host immune markers differ between patients with drug-sensitive PTB and patients with drug-resistant PTB, and even within the same patient group, the same type of immune marker may display distinct changes in response to different MTB antigen stimuli. […] It is hoped that through these biomarkers, a simple and feasible tool for evaluating therapy efficacy can be established, thereby reducing the incidence and mortality of PTB and achieving the goal of ending tuberculosis as soon as possible.

• #16 Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning | BMC Infectious Diseases | Full Text

  https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-025-10609-y

  Tuberculosis (TB) continues to pose a significant threat to global public health. Enhancing patient prognosis is essential for alleviating the disease burden. […] This study aims to evaluate TB prognosis by incorporating treatment discontinuation into the assessment framework, expanding beyond mortality and drug resistance. […] Analysis of 1,086 TB cases showed that a K-Nearest Neighbor classifier with Mutual Information feature selection achieved an area under the receiver operation curve (AUC) of 0.87 (95% CI: 0.830.92). Key predictors of treatment failure included elevated levels of 5-nucleotidase, uric acid, globulin, creatinine, cystatin C, and aspartate transaminase. SHAP analysis highlighted 5-nucleotidase, uric acid, and globulin as having the most significant influence on predicting treatment discontinuation.

• #17 Prediction of tuberculosis treatment outcomes using biochemical makers with machine learning | BMC Infectious Diseases | Full Text

  https://bmcinfectdis.biomedcentral.com/articles/10.1186/s12879-025-10609-y

  Our model provides valuable insights into TB outcomes based on initial patient tests, potentially guiding prevention and control strategies. Elevated biomarker levels before therapy are associated with increased risk of treatment discontinuation, indicating their potential as early warning indicators. […] The six biomarkers identified in our study 5-NT, uric acid, globulin, creatinine, cystatin C, and AST emerged as critical predictors of TB treatment outcomes. Notably, 5-NT, globulin, and AST are closely linked to liver function. At the same time, uric acid, creatinine, and cystatin C reflect kidney function. […] This study successfully constructed a model to predict TB treatment outcomes by combining multiple feature selection methods with machine learning algorithms. Based on patients initial admission test results, the model demonstrated high predictive accuracy (AUC reached 0.87), highlighting the importance of treatment discontinuation as a key component in assessing TB prognosis. The research found that elevated levels of 5-NT, uric acid, globulin, creatinine, cystatin C, and aspartate transaminase are closely associated with treatment failure. SHAP analysis further validated the critical role of these biomarkers in predicting treatment failure.

• #18 Using an Artificial Intelligence Approach to Predict the Adverse Effects and Prognosis of Tuberculosis

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10047137/

  Background: Tuberculosis (TB) is one of the leading causes of death worldwide and a major cause of ill health. Without treatment, the mortality rate of TB is approximately 50%; with treatment, most patients with TB can be cured. […] Our study aimed to build models using an artificial intelligence/machine learning approach to predict acute hepatitis, acute respiratory failure, and mortality after TB treatment. […] The results showed that our models using the six AI algorithms all had a high area under the receiver operating characteristic curve (AUC) in predicting acute hepatitis, respiratory failure, and mortality, and the AUCs ranged from 0.920 to 0.766, 0.884 to 0.797, and 0.834 to 0.737, respectively. […] Our AI models were good predictors and can provide clinicians with a valuable tool to detect the adverse prognosis in TB patients early.

• #19 Using an Artificial Intelligence Approach to Predict the Adverse Effects and Prognosis of Tuberculosis

  https://pmc.ncbi.nlm.nih.gov/articles/PMC10047137/

  To our knowledge, this is the first study to use AI and ML models to early detect acute hepatitis, respiratory failure, and mortality simultaneously in patients with TB after receiving anti-TB medications. […] Our predictive random forest models accuracy, sensitivity, specificity, and AUC were 0.819, 0.812, 0.820, and 0.884, respectively. […] In conclusion, we created a model based on laboratory data and patient characteristics that has significant value in the early detection of hepatitis, respiratory failure, and mortality in patients with TB who received anti-TB treatment.

• #20 Benchmarking Machine Learning Models to Assist in the Prognosis of Tuberculosis

  https://www.mdpi.com/2227-9709/8/2/27

  The main focus of our work is to evaluate machine learning models to aid TB prognosis and associated decision making by predicting the probability of death using patient demographic, clinical and laboratory data. Comparisons with extant research is complicated by the difference in goals and data used. Consequently, we benchmark nine machine learning models used in extant machine learning studies related to TB detection—Logistic Regression (LR), Linear Discriminant Analysis (LDA), K-Nearest Neighbor (KNN), Naive Bayes (NB), Decision Trees (DT), Support Vector Machine (SVM), Gradient Boosting (GB), Random Forest (RF) and Multi-Layer Perceptron (MLP). Our benchmarking methodology focuses on disease prognosis, not detection, and is designed to (a) identify the most relevant fields using feature selection techniques; (b) apply a randomized search technique to select the optimal hyperparameters of the machine learning models; and (c) propose an ensemble model that combines two or more machine learning models in order to achieve better results and reduce the risk associated with using a sub-optimal or inappropriate models.

• #21 Mortality prediction model for patients with PTB | IDR

  https://www.dovepress.com/development-and-validation-of-a-risk-mortality-prediction-model-for-pa-peer-reviewed-fulltext-article-IDR

  The mortality rate from pulmonary tuberculosis (PTB) complicated by severe community-acquired pneumonia (SCAP) in the intensive care unit (ICU) remains high. We aimed to develop a rapid and simple model for the early assessment and stratification of prognosis in these patients. […] This prognostic tool was designed to rapidly evaluate the 28-day mortality risk in individuals with PTB complicated by SCAP. It can stratify this patient group into relevant risk categories, guide targeted interventions, and enhance clinical decision making, thereby optimizing patient care and improving outcomes. […] Outcome prediction systems for PTB complicated by SCAP are rarely explored. Therefore, we developed a simple PTSI score model using simple clinical data, including long-term glucocorticoid use, a BMI of 18.5 kg/m2, diabetes, a BUN level 7.14 mmol/L, a PO2/FiO2 ratio of 150 mmHg, and vasopressor use. This PTSI score model was assessed using the AUC, calibration curve analysis, and DCA, demonstrating robust performance and accuracy in predicting the 28-day mortality risk of patients with PTB complicated by SCAP. […] A PTSI score model was developed to predict the 28-day mortality risk in patients with PTB complicated by SCAP, demonstrating good discrimination and calibration. Our model can help clinicians accurately assess prognosis and manage patients with PTB complicated by SCAP.

• #22 The effect of empirical and laboratory-confirmed tuberculosis on treatment outcomes | Scientific Reports

  https://www.nature.com/articles/s41598-021-94153-0

  Clinically diagnosed TB was associated with higher rate ratio among both the HIV infected (aRR 1.35 (95 CI 1.10 to 1.65) and not infected (aRR 2.15 (95% CI 1.74 to 2.67) compared to bacteriologically confirmed TB cases. […] The real effect of overdiagnosis of TB includes withholding appropriate management for the actual condition, and undergoing prolonged anti-tuberculosis therapy with its known potential adverse effects, and early death. […] Future research is recommended to improve our understanding of the underlying causes of the high mortality amongst the clinically diagnosed TB patients by systematically screening for other diseases in sub-Saharan Africa settings.

Zobacz więcej