Two-year death prediction models among patients with Chagas Disease using machine learning-based methods.

Chagas disease (CD) is recognized by the World Health Organization as one of the thirteen most neglected tropical diseases. More than 80% of people affected by CD will not have access to diagnosis and continued treatment, which partly supports the high morbidity and mortality rate. Machine Learning (ML) can identify patterns in data that can be used to increase our understanding of a specific problem or make predictions about the future. Thus, the aim of this study was to evaluate different models of ML to predict death in two years of patients with CD. ML models were developed using different techniques and configurations. The techniques used were: Random Forests, Adaptive Boosting, Decision Tree, Support Vector Machine, and Artificial Neural Networks. The adopted settings considered only interview variables, only complementary exam variables, and finally, both mixed. Data from a cohort study with CD patients called SaMi-Trop were analyzed. The predictor variables came from the baseline; and the outcome, which was death, came from the first follow-up. All models were evaluated in terms of Sensitivity, Specificity and G-mean. Among the 1694 individuals with CD considered, 134 (7.9%) died within two years of follow-up. Using only the predictor variables from the interview, the different techniques achieved a maximum G-mean of 0.64 in predicting death. Using only the variables from complementary exams, the G-mean was up to 0.77. In this configuration, the protagonism of NT-proBNP was evident, where it was possible to observe that an ML model using only this single variable reached G-mean of 0.76. The configuration that mixed interview variables and complementary exams achieved G-mean of 0.75. ML can be used as a useful tool with the potential to contribute to the management of patients with CD, by identifying patients with the highest probability of death. Trial Registration: This trial is registered with ClinicalTrials.gov, Trial ID: NCT02646943.

Therapeutic perceptions in antisense RNA-mediated gene regulation for COVID-19.

COVID-19 was first reported in Wuhan, China, in December 2019. It is widely accepted that the world will not return to its prepandemic normality until safe and effective vaccines are available and a global vaccination program has been successfully implemented. Antisense RNAs are single-stranded RNAs that occur naturally or are synthetic and enable hybridizing and protein-blocking translation. Therefore, the main objective of this study was to identify target markers in the RNA of the severe acute respiratory syndrome coronavirus, or SARS-CoV-2, with a length between 21 and 28 bases that could enable the development of vaccines and therapies based on antisense RNA. We used a search algorithm in C language to compare 3159 complete nucleotide sequences from SARS-CoV-2 downloaded from the repository of the National Center for Biotechnology Information. The objective was to verify whether any common sequences were present in all 3159 strains of SARS-CoV-2. In the first of three datasets (SARS-CoV-2), the algorithm found two sequences each of 21 nucleotides (Sequence 1: CTACTGAAGCCTTTGAAAAAA; Sequence 2: TGTGGTTATACCTACTAAAAA). In the second dataset (SARS-CoV) and third dataset (MERS-CoV), no sequences of size N between 21 and 28 were found. Sequence 1 and Sequence 2 were input into BLAST® ≫ blastn and recognized by the platform. The gene identified by the sequences found by the algorithm was the ORF1ab region of SARS-CoV-2. Considerable progress in antisense RNA research has been made in recent years, and great achievements in the application of antisense RNA have been observed. However, many mechanisms of antisense RNA are not yet understood. Thus, more time and money must be invested into the development of therapies for gene regulation mediated by antisense RNA to treat COVID-19 as no effective therapy for this disease has yet been found.

Local tissue electrical parameters predict oral mucositis in HNSCC patients: A diagnostic accuracy double-blind, randomized controlled trial.

Oral Mucositis (OM) is a common adverse effect of head and neck squamous cell carcinoma (HNSCC) treatment. The purpose of this study was to investigate the significance of early changes in tissue electrical parameters (TEPs) in predicting the development of OM in HNSCC patients receiving radiation therapy (RT). The current study combined two study designs. The first was a case-control study. The control group comprised of RT patients who did not receive head and neck RT, and patients with HNSCC who received RT comprised the case group. In the second part of the study, the case group was included in a parallel cohort. A total of 320 patients were assessed for eligibility, and 135 patients were enrolled. Double blinding was performed, and neither the patients nor the care providers knew the measured parameters. The primary outcome was the detection of between-group changes in local TEPs over the follow-up period. The secondary outcome was the appearance of OM grades II, III, or IV and the predictive value of local TEPs in determining the incidence of OM after RT. The variables, impedance module, resistance, reactance, phase angle, and capacitance, were analyzed by the receiver operator curves (ROC). The case and control groups did not differ in demographic and clinical characteristics. Radiation therapy increased the local impedance module, resistance, reactance, and phase angle and reduced the local tissue capacitance in both groups. Evaluation of TEPs in the first week of RT correlated with the development of OM lesions during cancer therapy. ROC analysis showed that local impedance module and resistance presented higher specificity than did other parameters in predicting OM. In conclusion, local tissue electrical parameters measured at the first RT week can be useful tools to predict oral mucositis.