Bayesian Belief Propagation Research Articles

Adverse Events of Oral GLP-1 Receptor Agonist (Semaglutide Tablets): A Real-World Study Based on FAERS from 2019 to 2023.

Glucagon-like peptide-1 receptor agonists (GLP-1RAs) have attracted much attention because of their significant hypoglycemic and weight-loss effects. Previous preparations can only be subcutaneously injected. Oral administration of GLP-1RAs semaglutide helps to broaden treatment options, but its safety in the real world still needs to be observed. This study is based on FDA adverse event reporting system (FAERS) database to mine adverse drug events (ADE) of oral semaglutide, and provide references for the clinical safe use of this drug. To analyze the signal quality of oral semaglutide, which is a drug used in the FAERS database from the third quarter of 2019 to the third quarter of 2023, we collected ADE data and performed data mining by using disproportionate analysis. Then, we standardized the data and used a variety of signal-quantification techniques, including reported odds ratio (ROR), proportional reporting ratio (PRR), Bayesian belief propagation neural network (BCPNN), and multiple empirical Bayesian gamma Poisson contractions (MGPS), for further analysis. We screened 2398 reports on the use of semaglutide tablets, involving a total of 5653 ADE. These reports were mainly submitted by consumers, and the reporting country was mainly the United States. A total of 23 system organ classes (SOC) and 93 preferred terms (PT) were mined for the signals of semaglutide tablets. The three most common SOC were gastrointestinal disorders, general disorders and administration site conditions, and investigations. At the PT level, metabolism and nutrition disorders exhibit the highest number of signals, with the top three being thyroid cyst, acute cholecystitis, and ketosis. Gastrointestinal disorders rank second, primarily involving eructation, pancreatitis, impaired gastric emptying, and regurgitation. In addition, vith nerve paralysis occurs and the signal intensity is high. Our study provides a deeper and broader understanding of the safety of oral semaglutide. The results of the ROR, PRR, BCPNN, and MGPS algorithms exhibit high consistency, with metabolism and nutrition-related disorders having the highest number of signals. The conclusions align with the technical specifications of the product. Notably, other unexpected effects are reported, including acute cholecystitis, paralysis of the abducens nerve, and positional vertigo.

Post-marketing safety of immunomodulatory drugs in multiple myeloma: A pharmacovigilance investigation based on the FDA adverse event reporting system.

Objective: In recent years, the emergence of immunomodulatory drugs (IMiDs) has significantly improved clinical outcomes in patients with multiple myeloma (MM); however, serious adverse events (AEs) have hindered their safe clinical application. This study aimed to characterize the safety profiles and differences in IMiDs through a disproportionality analysis using the U.S. Food and Drug Administration Adverse Event Reporting System (FAERS), a post-marketing surveillance database. Methods: This study filtered reports of thalidomide, lenalidomide, and pomalidomide as primary suspect drugs in FAERS files from January 2013 to December 2021. AEs in the reports were retrieved according to the preferred terms (PTs) of the Medical Dictionary for Regulatory Activities. Furthermore, we detected safety signals using the reporting odds ratio (ROR), proportional reporting ratio (PRR), and Bayesian belief propagation neural network (BCPNN). When all three algorithms showed an association between the target drug and the AE, a positive signal was generated. Results: We extracted 9,968 thalidomide, 231,926 lenalidomide, and 55,066 pomalidomide AE reports. AEs were more common in male patients and in those >44 years old. Important safety signals were detected based on the system organ classes (SOC), including thalidomide (cardiac disorders: ROR, 2.87; PRR, 2.79; IC 1.22), lenalidomide (gastrointestinal disorders: ROR, 2.38; PRR, 2.27; IC 0.75), and pomalidomide (respiratory, thoracic, and mediastinal disorders: ROR, 2.14; PRR, 2.09; IC 0.85). Within the PT level, we identified novel risk signals: the thalidomide-induced second primary malignancy (SPM) signal was significant; lenalidomide reduced the success rate of hematopoietic stem cell collection; and three IMiDs may cause human chorionic gonadotropin increase, but this needs to be proven by clinical data. Pneumonia, sepsis, and renal failure are common risk factors for death due to IMiDs. Compared with thalidomide and lenalidomide, pomalidomide has a lower risk of venous thromboembolism (VTE) and is beneficial to patients with renal insufficiency. Conclusion: Mining data from FAERS resulted in novel AE signals, including adenocarcinoma of colon, harvest failure of blood stem cells, and increased levels of human chorionic gonadotropin. Further investigation is required to verify the significance of these signals. Moreover, IMiDs showed differences in safety reports, which should be emphasized by clinicians.

Applying Bayesian networks and belief propagation to error correction coding

Telecommunication standards utilise numerous different subsystems to improve the quality of voice and data communications. One of these subsystems is tasked with error detection and control within the transmitted streams. This is accomplished using numerous different error correction codes for various scenarios. This article investigates the use of a Bayesian network as a universal channel decoder for the two main branches of algebraic codes. This graph-based approach is visually intuitive and is found to produce similar results to the best performing decoders in use today. A graphical representation of a multi-path channel equaliser is incorporated into the Bayesian network, obtaining near optimal performance. References G. Colavolpe. On LDPC codes over channels with memory. IEEE T. Wirel. Commun., 5(7):1757–1766, 2006. doi:10.1109/TWC.2006.1673087. C. Douillard, M. Jezequel, C. Berrou, A. Picart, P. Didier, and A. Glavieux. Iterative correction of intersymbol interference: Turbo-equalization. Eur. T. Telecommun., 6(5):507–511, 1995. doi:10.1002/ett.4460060506. R. G. Gallager. Low-density parity-check codes. PhD thesis, Massachusetts Institute of Technology, 1963. http://www.rle.mit.edu/rgallager/documents/ldpc.pdf. R. J. McEliece, D. J. C. MacKay, and J.-F. Cheng. Turbo decoding as an instance of Pearl's ``belief propagation'' algorithm. IEEE J. Sel. Area. Comm., 16(2):140–152, 1998. doi:10.1109/49.661103 H. C. Myburgh, J. C Olivier, and A. J. van Zyl. Reduced complexity turbo equalization using a dynamic bayesian network. EURASIP J. Adv. Sig. Pr., 2012:136, 2012. doi:10.1186/1687-6180-2012-136. J. Pearl. Fusion, propagation, and structuring in belief networks. Artif. Intell., 29(3):241–288, 1986. doi:10.1016/0004-3702(86)90072-X. J. Pearl. Probabilistic reasoning in intelligent systems: networks of plausible inference. Morgan Kaufmann Publishers, 1988. J. G. Proakis and D. G. Manolakis. Digital communications McGraw-Hill New York, 1995. International Telecommunication Union. Requirements related to technical performance for IMT-Advanced radio interface(s). Technical report, http://www.itu.int/pub/R-REP-M.2134-2008, 2008. A. J. Viterbi. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE T. Inform. Theory, 13(2):260–269, 1967. doi:10.1109/TIT.1967.1054010.

Shadow Detection and Reconstruction in High-Resolution Satellite Images via Morphological Filtering and Example-Based Learning

The shadows in high-resolution satellite images are usually caused by the constraints of imaging conditions and the existence of high-rise objects, and this is particularly so in urban areas. To alleviate the shadow effects in high-resolution images for their further applications, this paper proposes a novel shadow detection algorithm based on the morphological filtering and a novel shadow reconstruction algorithm based on the example learning method. In the shadow detection stage, an initial shadow mask is generated by the thresholding method, and then, the noise and wrong shadow regions are removed by the morphological filtering method. The shadow reconstruction stage consists of two phases: the example-based learning phase and the inference phase. During the example-based learning phase, the shadow and the corresponding nonshadow pixels are first manually sampled from the study scene, and then, these samples form a shadow library and a nonshadow library, which are correlated by a Markov random field (MRF). During the inference phase, the underlying land-cover pixels are reconstructed from the corresponding shadow pixels by adopting the Bayesian belief propagation algorithm to solve the MRF. Experimental results on QuickBird and WorldView-2 satellite images have demonstrated that the proposed shadow detection algorithm can generate accurate and continuous shadow masks and also that the estimated nonshadow regions from the proposed shadow reconstruction algorithm are highly compatible with their surrounding nonshadow regions. Finally, we examine the effects of the reconstructed image on the application of classification by comparing the classification maps of images before and after shadow reconstruction.

Development of a reliable trust management model in social internet of things

In this paper, we introduce the first application of the belief propagation algorithm in the design and evaluation of trust management systems with an introduction of a novel paradigm of social internet of things (SIoT), as ‘social network of intelligent objects’, that are based on the notion of social relationships among objects. Further, we address a trust-making process, where a person needs to make a judgement about the trustworthiness of another community member where they do not have any prior knowledge about each other. Our proposed model uses various performance measures such as: centrality and transitivity measures for SIoT analysis and then employs hybrid fuzzy nearest neighbour with Bayesian belief network and Bayesian belief network with conditional independence to represent a trust-based evaluation. Bayesian belief propagation technique is used here to infer trustworthiness in a social context. Finally, we perform non-parametric Friedman two tail test for statistical significance of the results obtained for various approaches. The evaluation of the model is done on datasets collected from epinion.com and slashdog.org shows promising results that enable us to steer the interaction among the billions of objects which will crowd the future IoT.

Spontaneous reportintg system data based on Shuxuetong injection adverse reactions signal warning analysis

In this study, January 2009-December 2012 national adverse drug reaction monitoring center Shuxuetong the SRS data for the study, using the reporting rate ratio method and Bayesian belief propagation neural network Shuxuetong ADR warning signal, and balanced use of propensity score methods confounders. The results showed that chills as a possible warning signal. Tip clinical use Shuxuetong injection when, for the elderly, children, liver and kidney dysfunction are more prone to adverse reactions in patients with other special populations, the need to pay attention to the prevention of systemic allergic reactions, in particular the prevention shivering.

Top-Down Feedback in an HMAX-Like Cortical Model of Object Perception Based on Hierarchical Bayesian Networks and Belief Propagation

Hierarchical generative models, such as Bayesian networks, and belief propagation have been shown to provide a theoretical framework that can account for perceptual processes, including feedforward recognition and feedback modulation. The framework explains both psychophysical and physiological experimental data and maps well onto the hierarchical distributed cortical anatomy. However, the complexity required to model cortical processes makes inference, even using approximate methods, very computationally expensive. Thus, existing object perception models based on this approach are typically limited to tree-structured networks with no loops, use small toy examples or fail to account for certain perceptual aspects such as invariance to transformations or feedback reconstruction. In this study we develop a Bayesian network with an architecture similar to that of HMAX, a biologically-inspired hierarchical model of object recognition, and use loopy belief propagation to approximate the model operations (selectivity and invariance). Crucially, the resulting Bayesian network extends the functionality of HMAX by including top-down recursive feedback. Thus, the proposed model not only achieves successful feedforward recognition invariant to noise, occlusions, and changes in position and size, but is also able to reproduce modulatory effects such as illusory contour completion and attention. Our novel and rigorous methodology covers key aspects such as learning using a layerwise greedy algorithm, combining feedback information from multiple parents and reducing the number of operations required. Overall, this work extends an established model of object recognition to include high-level feedback modulation, based on state-of-the-art probabilistic approaches. The methodology employed, consistent with evidence from the visual cortex, can be potentially generalized to build models of hierarchical perceptual organization that include top-down and bottom-up interactions, for example, in other sensory modalities.

Bayesian belief propagation and border-ownership signals in early visual cortex

Bayesian belief propagation and border-ownership signals in early visual cortex

Towards a mathematical theory of cortical micro-circuits.

The theoretical setting of hierarchical Bayesian inference is gaining acceptance as a framework for understanding cortical computation. In this paper, we describe how Bayesian belief propagation in a spatio-temporal hierarchical model, called Hierarchical Temporal Memory (HTM), can lead to a mathematical model for cortical circuits. An HTM node is abstracted using a coincidence detector and a mixture of Markov chains. Bayesian belief propagation equations for such an HTM node define a set of functional constraints for a neuronal implementation. Anatomical data provide a contrasting set of organizational constraints. The combination of these two constraints suggests a theoretically derived interpretation for many anatomical and physiological features and predicts several others. We describe the pattern recognition capabilities of HTM networks and demonstrate the application of the derived circuits for modeling the subjective contour effect. We also discuss how the theory and the circuit can be extended to explain cortical features that are not explained by the current model and describe testable predictions that can be derived from the model.

ANALYSIS ON RELATIONSHIP BETWEEN LAYOUT OF DISPLAY CASES AND PURCHASE BEHAVIOR BY BAYESIAN NETWORK

By using Bayesian network and Belief propagation, we made relationship clear between layout of display cabinets and purchase behavior in mass-market discounter of medium scale shop, selling childhood product after observing customers' behaviors. Probability that customers pass around entrances several times and at the far wall of shop more than once is higher than pass center of it (customers walk along walls instead of watching center shelves). Then, though customers who buy clothes walk only in front of clothes' shelves, customers who buy big commodities walk around widely in shop and pass through front of same shelves several times.

ANALYSIS ON PURCHASE BEHAVIOR ACCORDING TO DISPLAY WAY OF MERCHANDISE BY BAYESIAN NETWORK

By using Bayesian network and Belief propagation, we made relationship clear between display way of merchandise and purchase behavior in mass-market discounter of medium scale shop, selling childhood product after observing and recording customers behaviors. Followings are characteristics of customers' behaviors towards clothes in shelves, displayed by “Face-out”, “Sleeve-out” and “Folded”. On “Face-out”, they tend to act same ways on shelf just after upper one. On “Sleeve-out” and “Folded”, they tend to act same way side by side (particularly, on “Folded” they see both sides (they don't tend to pick up or buy them)).

A general method for human activity recognition in video

In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a feature vector comprising both trajectory information (position and velocity), and a set of local motion descriptors. Action recognition is achieved via probabilistic search of image feature databases representing previously seen actions. Hidden Markov Models (HMM) which encode scene rules are used to smooth sequences of actions. High-level behaviour recognition is achieved by computing the likelihood that a set of predefined HMMs explains the current action sequence. Thus, human actions and behaviour are represented using a hierarchy of abstraction: from person-centred actions, to actions with spatio-temporal context, to action sequences and, finally, general behaviours. While the upper levels all use Bayesian networks and belief propagation, the lowest level uses non-parametric sampling from a previously learned database of actions. The combined method represents a general framework for human behaviour modelling. We demonstrate results from broadcast tennis sequences and surveillance footage for automated video annotation.

Stereo matching using belief propagation

In this paper, we formulate the stereo matching problem as a Markov network and solve it using Bayesian belief propagation. The stereo Markov network consists of three coupled Markov random fields that model the following: a smooth field for depth/disparity, a line process for depth discontinuity, and a binary process for occlusion. After eliminating the line process and the binary process by introducing two robust functions, we apply the belief propagation algorithm to obtain the maximum a posteriori (MAP) estimation in the Markov network. Other low-level visual cues (e.g., image segmentation) can also be easily incorporated in our stereo model to obtain better stereo results. Experiments demonstrate that our methods are comparable to the state-of-the-art stereo algorithms for many test cases.

Hierarchical Bayesian inference in the visual cortex.

Traditional views of visual processing suggest that early visual neurons in areas V1 and V2 are static spatiotemporal filters that extract local features from a visual scene. The extracted information is then channeled through a feedforward chain of modules in successively higher visual areas for further analysis. Recent electrophysiological recordings from early visual neurons in awake behaving monkeys reveal that there are many levels of complexity in the information processing of the early visual cortex, as seen in the long-latency responses of its neurons. These new findings suggest that activity in the early visual cortex is tightly coupled and highly interactive with the rest of the visual system. They lead us to propose a new theoretical setting based on the mathematical framework of hierarchical Bayesian inference for reasoning about the visual system. In this framework, the recurrent feedforward/feedback loops in the cortex serve to integrate top-down contextual priors and bottom-up observations so as to implement concurrent probabilistic inference along the visual hierarchy. We suggest that the algorithms of particle filtering and Bayesian-belief propagation might model these interactive cortical computations. We review some recent neurophysiological evidences that support the plausibility of these ideas.