Cancer cell lines, which are cell cultures derived from tumor samples, represent one of the least expensive and most studied preclinical models for drug development. Accurately predicting drug ...responses for a given cell line based on molecular features may help to optimize drug-development pipelines and explain mechanisms behind treatment responses. In this study, we focus on DNA methylation profiles as one type of molecular feature that is known to drive tumorigenesis and modulate treatment responses. Using genome-wide, DNA methylation profiles from 987 cell lines in the Genomics of Drug Sensitivity in Cancer database, we used machine-learning algorithms to evaluate the potential to predict cytotoxic responses for eight anti-cancer drugs. We compared the performance of five classification algorithms and four regression algorithms representing diverse methodologies, including tree-, probability-, kernel-, ensemble-, and distance-based approaches. We artificially subsampled the data to varying degrees, aiming to understand whether training based on relatively extreme outcomes would yield improved performance. When using classification or regression algorithms to predict discrete or continuous responses, respectively, we consistently observed excellent predictive performance when the training and test sets consisted of cell-line data. Classification algorithms performed best when we trained the models using cell lines with relatively extreme drug-response values, attaining area-under-the-receiver-operating-characteristic-curve values as high as 0.97. The regression algorithms performed best when we trained the models using the full range of drug-response values, although this depended on the performance metrics we used. Finally, we used patient data from The Cancer Genome Atlas to evaluate the feasibility of classifying clinical responses for human tumors based on models derived from cell lines. Generally, the algorithms were unable to identify patterns that predicted patient responses reliably; however, predictions by the Random Forests algorithm were significantly correlated with Temozolomide responses for low-grade gliomas.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The accurate estimation of protein requirements for beef cattle is a key factor in increasing livestock profitability and decreasing the environmental impacts of excessive N excretion due to ...mismatching between assumed requirements and diet formulation. A meta-analysis was conducted to evaluate and validate a new equation to predict the net protein requirements for growth (NPg) of Zebu beef cattle. For the development of the new approach, a database of 552 observations comprised of bulls, steers, and heifers of different genetic groups (Zebu, beef crossbreed, and dairy crossbreed) was assembled. The new approach was evaluated and compared to current models devised by the international nutrient requirements system committees (Agricultural Research Council, 1980; Beef Cattle Nutrient Requirements Model, 2016; BR-CORTE, 2016) to predict NPg. The model evaluation was performed through the model evaluation system (version 3.1.16) using an independent data set (n = 177 observations). An equation was considered the best estimator of NPg if the following conditions were met: (1) the intercept and slope of the regression between ordinary residues and/or predicted NPg values must have been equal to zero and one, respectively; and (2) the greatest concordance correlation coefficient (CCC) and determination coefficient (R), and lowest mean squared error of prediction (MSEP) were attained. Based on the regression models of the observed v. predicted NPg of Zebu beef cattle, both the new approach and that of the ARC (1980) correctly estimated NPg, since the intercept and slope were not different (P > 0.05) from zero and one, respectively. Additionally, the new approach’s determination coefficient was the greatest and the closest to one. The fact that the new model achieved a higher CCC and lower MSEP than the existing models indicated its superior reproducibility and accuracy. The equations proposed by BR-CORTE (2016) and the BCNRM (2016) did not correctly estimate NPg in that the intercept and slope were different (P < 0.01) from zero and one, respectively. Thus, the equations proposed by the new approach and the ARC (1980) accurately and precisely estimated NPg and are recommended for Zebu cattle. Furthermore, the inclusion of equivalent empty BW (EQEBW) in the new approach improves the estimation of NPg. We suggest the use of the following equation to calculate NPg for Zebu beef cattle: NPg = 176.01 × EBG – 0.381 × EQEBW0.75 × EBG1.035 (R = 0.80 and CCC = 0.75); where NPg = net protein requirements for growth, EBG = empty body gain, and EQEBW = equivalent empty BW.
Tests are scarce resources, especially in low and middle-income countries, and the optimization of testing programs during a pandemic is critical for the effectiveness of the disease control. Hence, ...we aim to use the combination of symptoms to build a predictive model as a screening tool to identify people and areas with a higher risk of SARS-CoV-2 infection to be prioritized for testing.
We performed a retrospective analysis of individuals registered in "Dados do Bem," a Brazilian app-based symptom tracker. We applied machine learning techniques and provided a SARS-CoV-2 infection risk map of Rio de Janeiro city.
From April 28 to July 16, 2020, 337,435 individuals registered their symptoms through the app. Of these, 49,721 participants were tested for SARS-CoV-2 infection, being 5,888 (11.8%) positive. Among self-reported symptoms, loss of smell (OR95%CI: 4.6 4.4-4.9), fever (2.6 2.5-2.8), and shortness of breath (2.1 1.6-2.7) were independently associated with SARS-CoV-2 infection. Our final model obtained a competitive performance, with only 7% of false-negative users predicted as negatives (NPV = 0.93). The model was incorporated by the "Dados do Bem" app aiming to prioritize users for testing. We developed an external validation in the city of Rio de Janeiro. We found that the proportion of positive results increased significantly from 14.9% (before using our model) to 18.1% (after the model).
Our results showed that the combination of symptoms might predict SARS-Cov-2 infection and, therefore, can be used as a tool by decision-makers to refine testing and disease control strategies.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Business Process Deviance Mining is a research area that aims to characterize deviations of a business process from its expected outcomes. Techniques within this area discover which features of a set ...of process executions are associated to changes in process performance, providing insights on which process behavior leads to the best performance and also revealing behaviors that result in undesired process outcomes. In this sense, performance may refer to time, cost, resource dimensions or to any domain-specific performance indicator. Existing techniques for business process deviance mining are based on the extraction of patterns from event logs, using different pattern mining approaches. Up to date these extraction patterns have limited expressiveness, since they are not able to capture complex relationships that may be present in highly-flexible processes. In this work, we propose a new encoding technique for vector-based representation of process instances, and then apply Treatment Learning as a novel approach in the context of Deviance Mining to identify the characteristics of a process that mostly impact its performance. The proposed encoding technique is based on the fulfillment of Declare constraint templates, which makes it able to discover more expressive treatments. We compare our proposal with current process encoding techniques in a series of experiments with publicly available event logs from real-life processes. The results showed that treatment learning, together with our proposed Declare-based encoding, produced relevant and more expressive insights from the event logs, being a practical application for process analysis.
•A novel method to analyze business process performance using treatment learning.•Analysis can consider any process performance indicator, at trace-level.•A comparison of techniques to derive features from process traces.•Declare-based encoding of process traces enhances expressiveness of trace features.•Experiments showed the presence of narrow funnel effect on real-life event logs.
The coronavirus disease 2019 (COVID-19) pandemic has highlighted inequalities in access to healthcare systems, increasing racial disparities and worsening health outcomes in these populations. This ...study analysed the association between sociodemographic characteristics and COVID-19 in-hospital mortality in Brazil.
A retrospective analysis was conducted on quantitative reverse transcription polymerase chain reaction–confirmed hospitalised adult patients with COVID-19 with a defined outcome (i.e. hospital discharge or death) in Brazil. Data were retrieved from the national surveillance system database (SIVEP-Gripe) between February 16 and August 8, 2020.
Clinical characteristics, sociodemographic variables, use of hospital resources and outcomes of hospitalised adult patients with COVID-19, stratified by self-reported race, were investigated. The primary outcome was in-hospital mortality. The association between self-reported race and in-hospital mortality, after adjusting for clinical characteristics and comorbidities, was evaluated using a logistic regression model.
During the study period, Brazil had 3,018,397 confirmed COVID-19 cases and 100,648 deaths. The study population included 228,196 COVID-19–positive adult in-hospital patients with a defined outcome; the median age was 61 years, 57% were men, 35% (79,914) self-reported as Black/Brown and 35.4% (80,853) self-reported as White. The total in-hospital mortality was 37% (85,171/228,196). Black/Brown patients showed higher in-hospital mortality than White patients (42% vs 37%, respectively), were admitted less frequently to the intensive care unit (ICU) (32% vs 36%, respectively) and used more invasive mechanical ventilation (21% vs 19%, respectively), especially outside the ICU (17% vs 11%, respectively). Black/Brown race was independently associated with high in-hospital mortality after adjusting for sex, age, level of education, region of residence and comorbidities (odds ratio = 1.15; 95% confidence interval = 1.09–1.22).
Among hospitalised Brazilian adults with COVID-19, Black/Brown patients showed higher in-hospital mortality, less frequently used hospital resources and had potentially more severe conditions than White patients. Racial disparities in health outcomes and access to health care highlight the need to actively implement strategies to reduce inequities caused by the wider health determinants, ultimately leading to a sustainable change in the health system.
•Analysis of 228,196 adult hospital admissions for coronavirus disease 2019 in Brazil.•The in-hospital mortality rate was 37% (85,171/228,196).•Sociodemographic variables were strongly associated with in-hospital mortality.•Black/Brown patients showed higher in-hospital mortality than White patients.•The findings reveal racial disparities on outcomes and access to health care in Brazil.
Nonsteroidal anti‐inflammatory drugs (NSAIDs) were thought to increase the severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) virus entrance into cells. Hence, it was suggested in the media ...that NSAIDs could lead to a higher risk of infection and/or disease severity. To determine the existence or absence of this association, we aimed to systematically evaluate the risk of SARS‐CoV‐2 infection and mortality and the risk of severe coronavirus disease 2019 (COVID‐19) associated with previous exposure to NSAIDs.
MEDLINE, Cochrane Central Register of Controlled Trials (CENTRAL), and EMBASE were searched in February 2021 for controlled studies. The results were calculated through random‐effect meta‐analyses and reported in terms of odds ratios (ORs) with 95% confidence intervals (CIs). Heterogeneity was assessed with I2 test.
Eleven studies were included, comprising a total of 683 715 patients. NSAID exposure did not increase the risk of having a positive test for SARS‐CoV‐2 infection (OR, 0.97; 95%CI, 0.85‐1.11, I2 = 24%; 5 studies). The exposure to NSAIDs did not increase the risk of severe/critical COVID‐19 disease (OR, 0.92; 95%CI, 0.80‐1.05; I2 = 0%; 5 studies) nor all‐cause mortality among patients with COVID‐19 (OR, 0.86; 95%CI, 0.75‐0.99; I2 = 14%, 4 studies).
Our data did not suggest that exposure to NSAIDs increases the risk of having SARS‐CoV‐2 infection or increases the severity of COVID‐19 disease. Also, the fragility of the studies included precludes definite conclusions and highlights the need for further robust data.
The lack of precise definitions and terminological consensus about the impact studies of COVID-19 vaccination leads to confusing statements from the scientific community about what a vaccination ...impact study is.
The present work presents a narrative review, describing and discussing COVID-19 vaccination impact studies, mapping their relevant characteristics, such as study design, approaches and outcome variables, while analyzing their similarities, distinctions, and main insights.
The articles screening, regarding title, abstract, and full-text reading, included papers addressing perspectives about the impact of vaccines on population outcomes. The screening process included articles published before June 10, 2022, based on the initial papers' relevance to this study's research topics. The main inclusion criteria were data analyses and study designs based on statistical modelling or comparison of pre- and post-vaccination population.
The review included 18 studies evaluating the vaccine impact in a total of 48 countries, including 32 high-income countries (United States, Israel, and 30 Western European countries) and 16 low- and middle-income countries (Brazil, Colombia, and 14 Eastern European countries). We summarize the main characteristics of the vaccination impact studies analyzed in this narrative review.
Although all studies claim to address the impact of a vaccination program, they differ significantly in their objectives since they adopt different definitions of impact, methodologies, and outcome variables. These and other differences are related to distinct data sources, designs, analysis methods, models, and approaches.