Screening for active pulmonary tuberculosis: Development and applicability of artificial neural network models

Supervised Machine Learning Methods for Seasonal Influenza Diagnosis

Influenza has been a stationary disease in Mexico since 2009, and this causes a high cost for the national public health system, including its detection using RT-qPCR tests, treatments, and absenteeism in the workplace. Despite influenza's relevance, the main clinical features to detect the disease defined by international institutions like the World Health Organization (WHO) and the United States Centers for Disease Control and Prevention (CDC) do not follow the same pattern in all populations. The aim of this work is to find a machine learning method to facilitate decision making in the clinical differentiation between positive and negative influenza patients, based on their symptoms and demographic features. The research sample consisted of 15480 records, including clinical and demographic data of patients with a positive/negative RT-qPCR influenza tests, from 2010 to 2020 in the public healthcare institutions of Mexico City. The performance of the methods for classifying influenza cases were evaluated with indices like accuracy, specificity, sensitivity, precision, the f1-measure and the area under the curve (AUC). Results indicate that random forest and bagging classifiers were the best supervised methods; they showed promise in supporting clinical diagnosis, especially in places where performing molecular tests might be challenging or not feasible.

Population-based active screening strategy contributes to the prevention and control of tuberculosis

Despite the achievements obtained worldwide in the control of tuberculosis in recent years, many countries and regions including China still face challenges such as low diagnosis rate, high missed diagnosis rate, and delayed diagnosis of the disease. The discovery strategy of tuberculosis in China has changed from "active discovery by X-ray examination" to "passive discovery by self-referral due to symptoms", and currently the approach is integrated involving self-referral due to symptoms, active screening, and physical examination. Active screening could help to identify early asymptomatic and untreated cases. With the development of molecular biology and artificial intelligence-assisted diagnosis technology, there are more options for active screening among the large-scale populations. Although the implementation cost of a population-based active screening strategy is high, it has great value in social benefits, and active screening in special populations can obtain better benefits. Active screening of tuberculosis is an important component of the disease control. It is suggested that active screening strategies should be optimized according to the specific conditions of the regions to ultimately ensure the benefit of the tuberculosis control.

dos Santos Lara1,3 C, Amorim4 G, C. Silva1,5,6,7 E, Lineu Kritski1 A, Cristina C. Carvalho1,2 A. Clinical, laboratory, and radiographic aspects of patients with pulmonary tuberculosis and dysglycemia and tuberculosis treatment outcomes

Objective: To analyze the association of dysglycemia with clinical, laboratory, and radiographic characteristics of patients with pulmonary tuberculosis (PTB), as well as with their tuberculo-sis treatment outcomes. Methods: This was a longitudinal study involving 140 patients diag-nosed with PTB (positive cultures for Mycobacterium tuberculosis or positive Xpert MTB/RIF results from sputum samples). Patients were evaluated at diagnosis (M0), after completing the second month of treatment (M2), and at the end of treatment (MEND). At M0, the pati-ents were classified into three groups: normoglycemia+PTB (NGTB); pre-diabetes melli-tus+PTB (PDMTB), and diabetes mellitus+PTB (DMTB), in accordance with glycated hemoglo-bin levels (< 5.7%, 5.7%-6.4%, and = 6.5%, respectively). Treatment outcomes were classified as favorable (cure or treatment completion) and unfavorable (death, loss to follow-up, or treatment failure). Results: In our sample, 76 patients (61.4%) had dysglycemia, 20 of whom (14.3%) had DM at M0. The patients with dysglycemia, in comparison with those in the NGTB group, more frequently presented with positive sputum smear microscopy (94.2% vs. 75.9%; p = 0.003); cavities (80.2% vs. 63.0%; p = 0.03); bilateral lesions (67.4% vs. 46.0%; p = 0.02); and higher median of affected thirds of the lungs (3.0 vs. 2.0; p = 0.03) on chest radiography. No significant differences regarding outcomes were found among the groups, but tuberculosis lethality was higher in the DMTB group than in the PDMTB and NGTB groups (20% vs. 2.2%). Conclusions: PTB patients with dysglycemia had laboratory and radiographic manifestations indicative of more advanced disease, and the risk of death was higher in the DMTB group. These findings reinforce the recommendation for early screening for DM in patients with newly diagnosed tuberculosis in order to reduce the risk of death during treatment.

Impact of a computer system as a triage tool in the management of pulmonary tuberculosis in a HIV reference center in Brazil

Background:

The Neural Clinical Score for tuberculosis (NCS-TB) is a computer system developed to improve the triage of presumed pulmonary TB (pPTB).

Methods:

A study was performed with cohorts of pPTB patients cared for at a reference hospital in Northeast Brazil.

Results:

The NCS-TB sensitivity was 76.5% for TB diagnosis, which shortened the time from triage to smear microscopy results (3.3 to 2.5 days; p<0.001) and therapy initiation (6.7 to 4.1 days; p=0.045).

Conclusions:

Although the NCS-TB was not suitable as a screening tool, it was able to optimize laboratory diagnosis and shorten the time to treatment initiation.

Machine learning in the loop for tuberculosis diagnosis support

The use of machine learning (ML) for diagnosis support has advanced in the field of health. In the present paper, the results of studying ML techniques in a tuberculosis diagnosis loop in a scenario of limited resources are presented. Data are analyzed using a tuberculosis (TB) therapy program at a health institution in a main city of a developing country using five ML models. Logistic regression, classification trees, random forest, support vector machines, and artificial neural networks are trained under physician supervision following physicians' typical daily work. The models are trained on seven main variables collected when patients arrive at the facility. Additionally, the variables applied to train the models are analyzed, and the models' advantages and limitations are discussed in the context of the automated ML techniques. The results show that artificial neural networks obtain the best results in terms of accuracy, sensitivity, and area under the receiver operating curve. These results represent an improvement over smear microscopy, which is commonly used techniques to detect TB for special cases. Findings demonstrate that ML in the TB diagnosis loop can be reinforced with available data to serve as an alternative diagnosis tool based on data processing in places where the health infrastructure is limited.

Application of machine learning tools: Potential and useful approach for the prediction of type 2 diabetes mellitus based on the gut microbiome profile

The gut microbiota plays an important role in the regulation of the immune system and the metabolism of the host. The aim of the present study was to characterize the gut microbiota of patients with type 2 diabetes mellitus (T2DM). A total of 118 participants with newly diagnosed T2DM and 89 control subjects were recruited in the present study; six clinical parameters were collected and the quantity of 10 different types of bacteria was assessed in the fecal samples using quantitative PCR. Taking into consideration the six clinical variables and the quantity of the 10 different bacteria, 3 predictive models were established in the training set and test set, and evaluated using a confusion matrix, area under the receiver operating characteristic curve (AUC) values, sensitivity (recall), specificity, accuracy, positive predictive value and negative predictive value (npv). The abundance of Bacteroides, Eubacterium rectale and Roseburia inulinivorans was significantly lower in the T2DM group compared with the control group. However, the abundance of Enterococcus was significantly higher in the T2DM group compared with the control group. In addition, Faecalibacterium prausnitzii, Enterococcus and Roseburia inulinivorans were significantly associated with sex status while Bacteroides, Bifidobacterium, Enterococcus and Roseburia inulinivorans were significantly associated with older age. In the training set, among the three models, support vector machine (SVM) and XGboost models obtained AUC values of 0.72 and 0.70, respectively. In the test set, only SVM obtained an AUC value of 0.77, and the precision and specificity were both above 0.77, whereas the accuracy, recall and npv were above 0.60. Furthermore, Bifidobacterium, age and Roseburia inulinivorans played pivotal roles in the model. In conclusion, the SVM model exhibited the highest overall predictive power, thus the combined use of machine learning tools with gut microbiome profiling may be a promising approach for improving early prediction of T2DM in the near feature.

The Promise of Clinical Decision Support Systems Targetting Low-Resource Settings

Low-resource clinical settings are plagued by low physician-to-patient ratios and a shortage of high-quality medical expertise and infrastructure. Together, these phenomena lead to over-burdened healthcare systems that under-serve the needs of the community. Alleviating this burden can be undertaken by the introduction of clinical decision support systems (CDSSs); systems that support stakeholders (ranging from physicians to patients) within the clinical setting in their day-to-day activities. Such systems, which have proven to be effective in the developed world, remain to be under-explored in low-resource settings. This review attempts to summarize the research focused on clinical decision support systems that either target stakeholders within low-resource clinical settings or diseases commonly found in such environments. When categorizing our findings according to disease applications, we find that CDSSs are predominantly focused on dealing with bacterial infections and maternal care, do not leverage deep learning, and have not been evaluated prospectively. Together, these highlight the need for increased research in this domain in order to impact a diverse set of medical conditions and ultimately improve patient outcomes.

Diagnostic Value and Effectiveness of an Artificial Neural Network in Biliary Atresia

Objectives: Biliary atresia (BA) is a devastating pediatric liver disease. Early diagnosis is important for timely intervention and better prognosis. Using clinical parameters for non-invasive and efficient BA diagnosis, we aimed to establish an artificial neural network (ANN). Methods: A total of 2,384 obstructive jaundice patients from 2012 to 2017 and their 137 clinical parameters were screened for eligibility. A standard binary classification feed-forward ANN was employed. The network was trained and validated for accuracy. Gamma-glutamyl transpeptidase (GGT) level was used as an independent predictor and a comparison to assess the network effectiveness. Results: We included 46 parameters and 1,452 patients for ANN modeling. Total bilirubin, direct bilirubin, and GGT were the most significant indicators. The network consisted of an input layer, 3 hidden layers with 12 neurons each, and an output layer. The network showed good predictive property with a high area under curve (AUC) (0.967, sensitivity 97.2% and specificity 91.0%). Five-fold cross validation showed the mean accuracy for training data of 93.2% and for validation data of 88.6%. Conclusions: The high accuracy and efficiency demonstrated by the ANN model is promising in the noninvasive diagnosis of BA and could be considered as in a low-cost and independent expert diagnosis system.