Bayesian Methodology Research Articles

A real-world disproportionality analysis of FDA Adverse Event Reporting System (FAERS) events for ramucirumab

ABSTRACT Background Ramucirumab (IMC-1121B) is a fully human immunoglobulin G1 monoclonal antibody, approved by the US Food and Drug Administration (FDA) for treating various cancers, including gastric, colorectal, liver, and non-small cell lung cancer. This study aimed to investigate the adverse events (AEs) associated with ramucirumab by utilizing data mining techniques on the FDA Adverse Event Reporting System (FAERS). Methods We collected ramucirumab-related data from the FAERS database, spanning from January 2014 to June 2023. Our analysis incorporated both Frequentist and Bayesian methodologies in disproportionality analysis to determine the relationship between the drug and specific AEs. Results Among the 14,605,547 reports in FAERS database, 12,692,407 were identified as primary suspected AEs related to ramucirumab. These AEs involved 26 different organ systems, with 24 significant disproportionality Preferred Terms (PTs) identified across four algorithms. Notably, unexpected significant AEs, such as peripheral neuropathy, hemolytic uremic syndrome, rectal stenosis, anaphylactic shock, bladder tamponade, hydronephrosis, and spontaneous pneumothorax, were also observed. Conclusion This study makes a significant contribution to the field by emphasizing the importance of long-term monitoring of approved agents to further expand on potential adverse events and to distinguish between events that are disease-related versus those more directly related to the particular treatment.

Rainfall data modeling using improved adaptive type-II progressively censored Weibull-exponential samples

To get enough data from experiments that last for a long time, a recently unique improved adaptive Type-II progressive censoring technique has been suggested. This study, taking this scheme into consideration, concentrates on some conventional and Bayesian estimation tasks for parameter and reliability indicators, where the underlying distribution is the Weibull-exponential. From a traditional point of view, the likelihood methodology is explored for gaining point and approximate confidence interval estimates. Apart from the standard method, the Bayesian methodology is investigated to obtain the Bayesian point and credible intervals by taking advantage of the Markov chain Monte Carlo technique and the squared error loss function. To differentiate between the traditional and Bayesian estimates, a simulation analysis proceeds under various conditions. In order to put the suggested strategies into application, a pair of rainfall data sets are evaluated and numerous precision criteria are employed to pick the best progressive censoring plan.

Estimation of the Real Incidence of a Contagious Disease Through a Bayesian Multilevel Model: Study of COVID-19 in Spanish Provinces.

Pandemic outbreaks have emerged as a significant global threat, with the potential to cause waves of infections that challenge public health systems and disrupt societal norms. Understanding the underlying behavior of disease transmission can be of great use in the design of informed and timely public health policies. It is very common for many contagious diseases not to have actual incidence but rather incidence in a given subgroup. For example, in Spain, as of 28 March 2022, the incidence of COVID-19 in people under 60 years of age is not registered. This work provides a Bayesian methodology to model the incidence of any infectious disease in the general population when its cases are only registered in a specific subgroup of that population. The case study used was the coronavirus disease (COVID-19), with data for 52 Spanish provinces during the period of 1 January 2020 to 29 August 2022. Explicitly, two multilevel models were proposed, one for people over or of 60 years of age and the other for people under 60 years of age. Performance of the models was 5.9% and 12.7% MAPE, respectively. Despite the limitations of the data and the complexity and uncertainty in the propagation of COVID-19, the models were able to fit the data well and predict incidence with very low MAPE.

Thromboembolism prophylaxis timing is associated with center mortality in traumatic brain injury: A Trauma Quality Improvement Program retrospective analysis.

Timing of venous thromboembolism chemoprophylaxis (VTEPPx) in traumatic brain injury (TBI) is complex given concerns for potential worsening of hemorrhage. While timing of VTEPPx for TBI patients is known to vary at the patient level, to our knowledge, variation at the hospital level and correlation with quality metrics have not been quantified in a cohort of nonneurosurgical patients. This was a retrospective cohort study of the Trauma Quality Improvement database from 2018 to 2021. The primary outcome was variation in VTEPPx timing. This was ascertained by empirical Bayesian methodology using multilevel mixed-effects logistic regression. Secondary outcomes included the association of risk-adjusted VTEPPx timing and hospital characteristics such as volume and risk-adjusted mortality, which was assessed through Pearson's correlation coefficient (r). Risk-adjusted mortality was similarly calculated using multilevel mixed-effects modeling. Of 132,028 patients included in the current study, 38.7% received care at centers in the earliest quartile of VTEPPx timing, classified as Early (others labeled Delayed). Patients receiving care at Early centers presented with severe TBI at a similar rate to Delayed (17.4% vs. 19.0%; absolute standardized mean difference, 0.04). Early center patients more commonly received unfractionated heparin as opposed to low-molecular-weight heparin compared with Delayed (40.5% vs. 27.6%; absolute standardized mean difference, 0.28). At the center level, 12% of observed variation in VTEPPx was attributable to differential hospital practices. Overall trauma volume (r = -0.22, p < 0.001) and TBI volume (r = -0.19, p < 0.001) were inversely associated with risk-adjusted VTEPPx timing. In addition, centers initiating VTEPPx earlier had lower overall (r = 0.17, p < 0.001) and TBI-related mortality (r = 0.17, p < 0.001). There is significant center-level variation in timing of VTEPPx among TBI patients. Earlier VTEPPx was associated with improved center outcomes overall and among TBI patients, supporting usage of VTEPPx timing as a holistic measure of quality. Prognostic and Epidemiological; Level III.

Bayesian Analytical Methods in Cardiovascular Clinical Trials: Why, When, and How

The Bayesian analytical framework is clinically intuitive, characterized by the incorporation of previous evidence into the analysis, and allowing an estimation treatment effects and their associated uncertainties. The application of Bayesian statistical inference is not new to the cardiovascular field, as illustrated by various recent randomized trials that applied a primary Bayesian analysis. Given the guideline-shaping character of trials, a thorough understanding of the concepts and technical details of Bayesian statistical methodology is of utmost importance to the modern practicing cardiovascular physician. Therefore, this Review aims to present a step-by-step guide to interpreting and performing a Bayesian (re-)analysis of cardiovascular clinical trials, while highlighting the main advantages of Bayesian inference for the clinical reader. After an introduction of the concepts of frequentist and Bayesian statistical inference and reasons to apply Bayesian methods, key steps for performing a Bayesian analysis are presented, including: the verification of the clinical appropriateness of the research question, the quality and completeness of the trial design, as well as the adequate elicitation of the prior (i.e., ones belief towards a certain treatment before the current evidence becomes available), identification of the likelihood, and their combination into a posterior distribution. Examination of this posterior distribution offers the possibility of not only determining the probability of treatment superiority, but also the probability of exceeding any chosen minimal clinically important difference. Multiple priors should be transparently prespecified, limiting post-hoc manipulations. Using this guide, three cardiovascular randomized controlled trials are re-analysed, demonstrating the clarity and versatility of Bayesian inference.

Untangling the Exposure-Response Relationship of Allopurinol in the Setting of Chronic Kidney Disease and Diuretic Use: Implications for Dosing.

Allopurinol dose reduction proportional to creatinine clearance (CLcr) results in suboptimal urate lowering in patients with gout. Similarly, diuretic therapy reduces oxypurinol clearance but is unexpectedly associated with the need for higher allopurinol doses to achieve the serum urate target (<0.36 mmol/L). The authors aimed to clarify the relationship between oxypurinol exposure and urate-lowering response in patients with gout at different stages of chronic kidney disease and those taking diuretics to determine the implications for maintenance dose selection. Oxypurinol and urate data from 5 clinical studies were available. Model-derived steady-state oxypurinol areas under the concentration-time curves (AUCss0-tau) were estimated using a Bayesian methodology. The observed response metrics included the percentage reduction in urate from baseline and achievement of the target urate level. Exposure-response was explored graphically and using logistic regression. In addition, the influence of chronic kidney disease and diuretic use on the allopurinol dose and oxypurinol AUCss0-tau requirements to achieve the serum urate target were explored. Data from 258 patients with gout taking allopurinol representing 1288 paired steady-state oxypurinol and serum urate measurements were available. Higher oxypurinol exposure seems to be required for urate-lowering response normalization and achieve the serum urate target in individuals with reduced kidney function and those taking diuretics. However, allopurinol dose requirements were reduced by 2-fold at the extremes of kidney function and unchanged in those taking or not taking diuretics. A lower allopurinol maintenance dose was required in patients with reduced kidney function (CLcr <30 mL/min), but this was not proportional to CLcr. Diuretic therapy did not influence allopurinol dose requirements.

Understanding the Republic of Malawi’s trade dynamics: A Bayesian gravity model approach

International trade enables countries to expand their markets, access more products, improve resource allocation, and boost economic growth by leveraging comparative advantage and specialization. The aim of this article is to analyze the primary factors that influence Malawi’s international trade flows. The study is relevant because it examines Malawi’s trade patterns with its main partners, which include surrounding nations and traditional trade allies. The novelty is that, through the analysis, the research offers valuable insights into the primary factors that influence Malawi’s international commerce. Panel data is gathered from various sources, including the International Monetary Fund (IMF) and World Bank, covering the period from 2000 to 2023 for 11 countries that are trading partners with Malawi. We employ the Bayesian Mindsponge gravity methodology. The results show that the economic size (characterized by the gross domestic product) of the origin and destination countries, bilateral agreements, and the population size of the destination country have a beneficial impact on Malawi’s exports. In conclusion, Malawi’s export performance is significantly enhanced by the economic size of both Malawi and its trading partners, the existence of bilateral agreements, and the population size of the destination countries, underscoring the importance of strategic economic partnerships and targeted trade policies in boosting Malawi’s international trade. We recommend Malawi authorities focus on strengthening bilateral agreements and targeting trade relationships with larger and more populous economies to boost international trade.

Understanding wildfire occurrence and size in Jalisco, Mexico: A spatio-temporal analysis

In recent years, the growing frequency and severity of wildfires, influenced by both human activities and climate change, have posed significant challenges worldwide. Among the regions most affected by wildfires in Mexico is the state of Jalisco, which has the largest accumulated burned area in the last five decades. In this paper, we present an in-depth analysis of the spatio-temporal patterns of wildfire occurrence and size in the state of Jalisco, spanning the period from 2001 to 2020. Our approach included modeling the spatial distribution of the area burned by wildfires, employing Bayesian methodology with Integrated Nested Laplace Approximation (INLA) and Stochastic Partial Differential Equations (SPDE). Our findings highlight the critical roles of vegetation, temperature, and human activities in shaping wildfire behavior. Additionally, our model suggests four distinct wildfire-prone regions within the state. The insights gained from this study can serve as a foundation for future research and localized studies, aiding in the development of more targeted and effective wildfire management strategies in Jalisco.

Bayesian control chart using variable sample size with engineering applications

In this study, we suggested an innovative approach by introducing an Adaptive Exponential Weighted Moving Average (AEWMA) control chart utilizing Variable Sample Size (VSS) under Bayesian methodology. The proposed methodology utilized an integer linear function to dynamically adjust sample sizes according to the AEWMA statistic. Another appealing feature of our adaptive framework is the integration of the smoothing constant of an EWMA chart, which enhances monitoring responsiveness. We reveal the superiority of our recommended control chart by extensive simulations to existing Bayesian EWMA and Bayesian AEWMA control charts using Fixed sample size (FSS). The offered Bayesian VAEWMA control chart is more sensitive to detection improvement, a decrease in the false alarm rate, and overall more effective than the existing methods. These findings provide additional justification for the basic notion that process control statistical tools needed to be dynamic, as the manufacturing process itself was dynamic. The results suggest the importance of introducing adaptive SPC methods in dynamic manufacturing environments. A real data application is performed to evaluate the validity and optimal performance of our recommended chart."Please check article if captured correctly."="Dear Editor we have checked and found corrrect."As per standard instruction, city is required for affiliations; however, this information is missing in affiliations [1, 5]. Please check if the provided city is correct and amend if necessary."Dear Editor we have checked and found correct. thanks youPlease check and confirm that the authors and their respective affiliations have been correctly identified and amend if necessary."Dear Editor we have checked and found correct. thank you"

A Hybrid Approach for Intrusion Detection by Dragonfly Optimization and Bayesian Neural Network Methodologies

The technique of keeping an eye out for malicious activity or policy violations on a computer network or system is known as intrusion detection. It entails examining system logs, network traffic, and other data sources to spot potential security breaches, misuse, and illegal access. Network-based and host-based intrusion detection systems (IDS) are the two types available. The former analyzes network traffic and packets, while the latter concentrates on specific hosts or devices. This paper investigates how to improve intrusion detection systems in cyber security by combining dragonfly optimization (DFO) and Bayesian neural network (BNN) methodologies. The NSL-KDD dataset, which is tested and trained in the system, is the source of the dataset used in the study. By utilizing the optimization skills of DFO and the probabilistic reasoning powers of BNN, the hybrid technique improves the accuracy and flexibility of detecting and addressing network intrusions. This research illustrates the effectiveness of the suggested methodology in navigating dynamic network environments and identifying emerging dangers through a thorough examination. In addition to improving detection performance, the integration of BNN and DFO gives enterprises insightful information about infiltration patterns and the ability to take proactive measures to thwart hostile activity. The created model's enhanced intrusion detection performance is demonstrated by the experimental findings. These results are validated in terms of accuracy, precision, recall, execution time, and F1 score by comparing them with models that are currently in use.

Distributed adaptive moving horizon estimation for multi-sensor networks subject to quantization effects

This paper investigates the distributed state estimation problem for multi-sensor networks with quantized measurements. Within the Bayesian framework, a distributed adaptive moving horizon estimation algorithm is developed. Unlike the existing methods regarding quantized errors roughly as bounded uncertainties, the posterior distributions of the errors are demanded to be derived. To overcome the difficulty of evaluating the posterior distributions for series of the states and quantized errors jointly, the variational Bayesian methodology is adopted to approximate the true distributions. Based on the fixed-point iteration method, the update rules are analytically derived, with the convergence criterion provided. Furthermore, by incorporating the average consensus algorithm into the prediction process, all sensors can achieve consensus on their estimates in a distributed manner. Finally, a numerical example of target tracking under logarithmic and uniform quantization effects is given to illustrate the validity of the proposed algorithm.

Using removable sensors in structural health monitoring: A Bayesian methodology for attachment-to-attachment uncertainty quantification

Structural responses are vulnerable to perturbations when subjected to variable environmental and operational conditions, thereby contributing to the slow uptake of Structural Health Monitoring (SHM) beyond academic research. More importantly, SHM systems using removable sensors face additional sensing variability due to the inherent uncertainty in sensor reattachment compared to permanently attached sensors. In this study, a novel probabilistic approach is developed for output-only damage detection utilizing ultrasonic guided waves. Experimental uncertainties and sensor attachment factors are simultaneously considered for the first time in a Bayesian context. The uncertainty introduced by reattached sensors is incorporated into the likelihood function in a comprehensive way. Bayesian model class selection using an adaptive sampling scheme is adopted to evaluate the evidence of discrete damage classes. A reference case to an aluminum plate with progressive notches is utilized to demonstrate the significant effects of attachment uncertainty on guided wave signals. The optimal data normalization model for guided wave processing under different attachment states is evaluated using the Mahalanobis distance. The notch length is identified accurately along with the uncertainty, even though the latent adhesive parameters cannot be estimated directly.

From Earnings to Occupations: Understanding Intergenerational Mobility inTurkey

The studies analyzing intergenerational economic mobility have been rather scarce for developing countries due to unavailability of longitudinal datasets. This study uses data from Survey of Income and Living Condition (SILC) from2006- 2021, obtained from Turkish Statistical Institute to analyze the intergenerational income and occupational mobility in Turkey. Besides measuring the dynamics of income and occupational mobility across generations, we also analyze howdoes the association of children socioeconomic outcome with their family backgroundvary at different career levels of children. Our findings reveal that the associationwith parents income is much higher for daughters as compared to sons suggestingdaughters outcomes are more explained by their family socioeconomic status. Regarding the association of children’ outcome with family status at different career stage, the relationship is stronger when children are at the mid-career level. The Bayesian methodology and Pseudo-panel fixed effect model has beenemployed to estimate intergenerational income elasticity and for the rest of the analysis, Bayesian methodology has been utilized. Our finding also reveals higher intergenerational occupational persistence among children in higher income families while children from disadvantaged families have higher probability of switching career upon receiving good education and income perspective.

Analysis of neutron time-of-flight spectra with a Bayesian unfolding methodology

We have developed an innovative methodology for obtaining the neutron energy distribution from a time-of-flight (TOF) measurement based on the iterative Bayesian unfolding method and accurate Monte Carlo simulations. This methodology has been validated through the analysis of a realistic virtual β-decay experiment, including the most relevant systematic effects in a real experiment. The proposed methodology allowed for obtaining accurate results over the energy range above the neutron detection threshold.

Consistency of Bayes factor estimates in Bayesian analysis of variance.

Factorial designs lend themselves to a variety of analyses with Bayesian methodology. The de facto standard is Bayesian analysis of variance (ANOVA) with Monte Carlo integration. Alternative, and readily available methods, are Bayesian ANOVA with Laplace approximation as well as Bayesian t tests for individual effects. This simulation study compared the three approaches regarding ordinal and metric agreement of the resulting Bayes factors for a 2 × 2 mixed design. Simulation results indicate remarkable disagreement of the three methods in certain cases, particularly when effect sizes are small and studies include small sample sizes. Findings further replicate and extend previous observations of substantial variability of ANOVAs with Monte Carlo integration across different runs of one and the same analysis. These observations showcase important limitations of current implementations of Bayesian ANOVA. Researchers should be mindful of these limitations when interpreting corresponding analyses, ideally applying multiple approaches to establish converging results. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Leveraging Bayesian methods for addressing multi-uncertainty in data-driven seismic liquefaction assessment

When assessing seismic liquefaction potential with data-driven models, addressing the uncertainties of establishing models, interpreting cone penetration tests (CPT) data and decision threshold is crucial for avoiding biased data selection, ameliorating overconfident models, and being flexible to varying practical objectives, especially when the training and testing data are not identically distributed. A workflow characterized by leveraging Bayesian methodology was proposed to address these issues. Employing a Multi-Layer Perceptron (MLP) as the foundational model, this approach was benchmarked against empirical methods and advanced algorithms for its efficacy in simplicity, accuracy, and resistance to overfitting. The analysis revealed that, while MLP models optimized via maximum a posteriori algorithm suffices for straightforward scenarios, Bayesian neural networks showed great potential for preventing overfitting. Additionally, integrating decision thresholds through various evaluative principles offers insights for challenging decisions. Two case studies demonstrate the framework's capacity for nuanced interpretation of in situ data, employing a model committee for a detailed evaluation of liquefaction potential via Monte Carlo simulations and basic statistics. Overall, the proposed step-by-step workflow for analyzing seismic liquefaction incorporates multifold testing and real-world data validation, showing improved robustness against overfitting and greater versatility in addressing practical challenges. This research contributes to the seismic liquefaction assessment field by providing a structured, adaptable methodology for accurate and reliable analysis.

Support for the Time-Varying Drift Rate Model of Perceptual Discrimination in Dynamic and Static Noise Using Bayesian Model-Fitting Methodology.

The drift-diffusion model (DDM) is a common approach to understanding human decision making. It considers decision making as accumulation of evidence about visual stimuli until sufficient evidence is reached to make a decision (decision boundary). Recently, Smith and colleagues proposed an extension of DDM, the time-varying DDM (TV-DDM). Here, the standard simplification that evidence accumulation operates on a fully formed representation of perceptual information is replaced with a perceptual integration stage modulating evidence accumulation. They suggested that this model particularly captures decision making regarding stimuli with dynamic noise. We tested this new model in two studies by using Bayesian parameter estimation and model comparison with marginal likelihoods. The first study replicated Smith and colleagues' findings by utilizing the classical random-dot kinomatogram (RDK) task, which requires judging the motion direction of randomly moving dots (motion discrimination task). In the second study, we used a novel type of stimulus designed to be like RDKs but with randomized hue of stationary dots (color discrimination task). This study also found TV-DDM to be superior, suggesting that perceptual integration is also relevant for static noise possibly where integration over space is required. We also found support for within-trial changes in decision boundaries ("collapsing boundaries"). Interestingly, and in contrast to most studies, the boundaries increased with increasing task difficulty (amount of noise). Future studies will need to test this finding in a formal model.

Methodological approaches to assessing the genetic predisposition of osteochondrosis of the tarsocrural joint in the Pura Raza Española horses

Osteochondrosis (OC) is a developmental orthopaedic disease of significant concern in numerous sport horse breeds, with significant international relevance. Using digital radiographs, we assessed the occurrence of hock (tarsocrural joint) OC in 3 048 Pura Raza Española (PRE) horses which took part in a morpho-functional test, in three specific locations in the tarsus limbs: the Distal Intermediate Ridge of the Tibia (DIRT), the lateral trochlear ridges of the talus (LTT), and the medial trochlear ridges of the talus (MTT). An incidence rate of 13.3% was found for hock OC in the analysed sample, with the highest incidence rate observed in DIRT (10.0%) and the lowest in MTT (0.2%). Estimates of genetic predisposition to hock OC were carried out using three genetic approaches: 1a) a binomial threshold model based on the presence or absence of OC, 1b) a multinomial threshold model, on a scale from 0 (absence) to 3 (maximum), and 2) a linear model. The effects considered in the models included sex, genetic origin and stud class. All the analyses were based on the Bayesian inference methodology, using the THRGIBBS3F90 software. The binomial threshold model yielded the most suitable results, with an estimated heritability for Overall hock OC of 0.71 ± 0.055 on the underlying scale (0.53 on the observed scale), ranging in different locations from 0.48 ± 0.087 (LTT) to 0.66 ± 0.063 (DIRT) on the underlying scale (0.10 and 0.38 on the observed scale, respectively). The highest significative genetic correlation was observed between Overall and DIRT (0.97) for approach 1a, and the lowest significant genetic correlation was between Overall and LTT (0.49), for approach 2. This study contributes valuable insights into the genetic predisposition towards, as well as for the potential for selective breeding against, hock OC in PRE horses, and provides a basis for future research and breeding programmes aimed at minimising the occurrence of hock OC and promoting the overall health of this breed.

Bayesian group testing regression models for spatial data

Spatial patterns are common in infectious disease epidemiology. Disease mapping is essential to infectious disease surveillance. Under a group testing protocol, biomaterial from multiple individuals is physically combined into a pooled specimen, which is then tested for infection. If the pool tests negative, all contributing individuals are generally assumed to be uninfected. If the pool tests positive, the individuals are usually retested to determine who is infected. When the prevalence of infection is low, group testing provides significant cost savings over traditional individual testing by reducing the number of tests required. However, the lack of statistical methods capable of producing maps from group testing data has limited the use of group testing in disease mapping. We develop a Bayesian methodology that can simultaneously map disease prevalence using group testing data and identify risk factors for infection. We illustrate its real-world utility using two datasets from vector-borne disease surveillance.

Bayesian inference with Gaussian processes for the determination of parton distribution functions

We discuss a Bayesian methodology for the solution of the inverse problem underlying the determination of parton distribution functions (PDFs). In our approach, Gaussian processes (GPs) are used to model the PDF prior, while Bayes’ theorem is used in order to determine the posterior distribution of the PDFs given a set of data. We discuss the general formalism, the Bayesian inference at the level of both parameters and hyperparameters, and the simplifications which occur when the observable entering the analysis is linear in the PDF. We benchmark the new methodology in two simple examples for the determination of a single PDF flavor from a set of deep inelastic scattering (DIS) data and from a set of equal-time correlators computed using lattice QCD. We discuss our results, showing how the proposed methodology allows for a well-defined statistical interpretation of the different sources of errors entering the PDF uncertainty, and how results can be validated a posteriori.