Classification Issues Research Articles

Creating Refined Datasets for Better Chaos Detection

In recent years, the analysis of signal properties (especially biomedical signals) has become an important research direction. One interesting feature of signals is their potential to be chaotic. This article concerns the issues of classification of real signals or synthetic ones in the context of detecting chaotic properties. In previous works, datasets of synthetic signals were created based on well-known chaotic and non-chaotic dynamical systems. They were published and used to train classifiers. This paper extends the previous studies and proposes a method for obtaining/extracting signals to force classifiers to learn to detect chaos. The proposed method allows the generation of groups of signals with similar initial conditions. The property of chaotic dynamical systems was used here, which consists of the strong dependence of the signal courses on a small change in the initial conditions. This method is based on reconstructing multidimensional phase space and data clustering. An additional goal of the work is to create referential datasets with so-called refined signals using the described method and to make them publicly available. The usefulness of the new datasets was confirmed during a simple experiment with the usage of the LSTM neural network.

ADET MODEL: Real time autism detection via eye tracking model using retinal scan images

Background Deficits in concentration with social stimuli are more common in children affected by autism spectrum disorder (ASD). Developing visual attention is one of the most vital elements for detecting autism. Eye tracking technology is a potential method to identify an early autism biomarker based on children's abnormal visual patterns. Objective Eye tracking retinal scan path images can be generated by eyeball movement during the time of watching the screen and capture the eye projection sequences, which helps to analyze the behavior of the children. The Shi-Tomasi corner detection methodology uses open CV to identify the corners of the eye gaze movement in the images. Methods In the proposed ADET model, the corner detection-based vision transformer (CD-ViT) technique is utilized to diagnose autism at an early stage. Generally, the transformer model divides the input images into patches, which can be fed into the transformer encoder process. The vision transformer is fine-tuned to resolve binary classification issues once the features are extracted via remora optimization. Specifically, the vision transformer model acts as the cornerstone of the proposed work with the help of the corner detection technique. This study uses a dataset with 547 eye-tracking retinal scan path images for both autism and non-autistic children. Results Experimental results show that the suggested ADET frameworkachieves a better classification accuracy of 38.31%, 23.71%, 13.01%, 1.56%, 18.26%, and 44.56% than RM3ASD, MLP, SVM, CNN, SVM, and our proposed ADET methods. Conclusions This screening method strongly suggests that it be used to assist medical professionals in providing efficient and accurate autism detection.

Improving Multiclass Rainfall Prediction with Multilayer Perceptron and SMOTE: Addressing Class Imbalance Challenges

Rainfall is a key climate element that affects weather patterns and human activities, especially in agriculture and daily life. Therefore, accurately classifying rainfall is crucial for predicting future rainfall amounts. This study uses the Multilayer Perceptron (MLP) classification method, a neural network algorithm, to classify rainfall. The dataset, sourced from the BMKG website, has a class imbalance, requiring using the SMOTE (Synthetic Minority Over-sampling Technique) technique. The research compares the performance of MLP with and without SMOTE. The results show that the best model was achieved with SMOTE. MLP without SMOTE achieved an accuracy of 75%, sensitivity of 40.34%, specificity of 86.15%, and an AUC of 63.25%. In comparison, MLP with SMOTE achieved an accuracy of 71.27%, sensitivity of 71.14%, specificity of 90.30%, and an AUC of 80.72%. Although accuracy decreased, the overall evaluation, particularly the AUC, improved significantly. Therefore, the SMOTE technique effectively addresses the class imbalance issue in rainfall classification.

Condition monitoring and multi-fault classification of hydraulic systems using multivariate functional data analysis.

Condition monitoring and fault classification in engineering systems is a critical challenge within the scope of Prognostics and Health Management (PHM). The fault diagnosis of complex nonlinear systems, such as hydraulic systems, has become increasingly important due to advancements in big data analytics, machine learning (ML), Industry 4.0, and Internet of Things (IoT) applications. Multi-sensor data provides opportunities to predict component conditions; however, environments characterized by multiple sensors and diverse fault states across various components complicate the fault classification process. To address these challenges, this study introduces a novel multivariate Functional Data Analysis (FDA) framework based on Multivariate Functional Principal Component Analysis (MFPCA) for classifying failure conditions in hydraulic systems. The proposed method systematically tackles condition-based diagnostics and addresses fundamental issues in multi-fault classification. Experimental results demonstrate that this approach achieves high classification accuracy using raw multi-sensor data, establishing multivariate FDA as a powerful tool for fault diagnosis in complex systems.

Nonclassical dynamical behavior of solutions of partial differential-difference equations

<p>For partial differential-difference equations, a review of results regarding the relation between the type of the equation and dynamical properties of its solutions is provided. This includes the case of elliptic equations with timelike independent variables: Their solutions acquire dynamical properties (more exactly, behave as solutions of parabolic equations). The following approach to classify differential-difference equations into types, based on the property of differential-difference operators to be Fourier multipliers is applied in the following manner: An operator is treated to be elliptic if the real part of its symbol is positive, while the parabolic and hyperbolic types are defined correspondingly. It is shown that the proposed approach (being a natural extension of the classical notion of the ellipticity) is reasonable. On the other hand, fundamental novelties (compared with the classical theory of partial differential equations) occur as well. We provide conditions which guarantee the following results. For the half-space (half-plane) Dirichlet problem for elliptic equations, integral representations (of the Poisson type) of solutions are constructed, which are infinitely differentiable outside the boundary hyperplane (plane), and the asymptotic closeness of solutions (as the timelike independent variable unboundedly increases) takes place. For the Cauchy problem for parabolic equations, the same is valid, but we deal with the classical time instead of the timelike independent variable. For hyperbolic equations, multiparameter families of infinitely smooth global solutions are constructed. The said (sufficient) conditions restrict the sign of the real part of the symbol for the differential-difference operator with respect to spatial or spacelike independent variables. In a number of special cases, they might be weakened such that symbols with sign-changing real parts are admitted. The objective of the study is to observe the current stage of the classification issues for partial differential-difference equations in terms of the aforementioned approach: The ellipticity of a Fourier multiplier is defined by means of the sign (of there real part) of its symbol. Since both differential and translation operators are Fourier multipliers, methods of Fourier analysis are applicable in this study: We apply the Fourier transformation to the original partial differential-difference equation, solve the obtained ordinary differential equation, and apply the inverse Fourier transformation to the obtained solution. The main contribution obtained within this study is an efficient (workable) type concept for the fundamentally new extension of the class of partial differential equations, which is the class of partial differential-difference equations.</p>

Implementing A Naïve Bayes Classifier on Iris Data Using MATLAB, A Classification Method by Using Grid Parameters Optimization

Data mining categorization is crucial for predicting outcomes. Naive Bayes Classification (NBC) is a prominent approach used in data mining for classification purposes. It has the ability to anticipate outcomes and is generally more efficient than other techniques of categorization. Several Naive Bayes classification methods exhibit subpar performance when used to classification and regression issues. One of the factors contributing to the success of NBC is the reliance on assumptions of independence among predictors and the initial hyperparameters. Nevertheless, this robust assumption results in a decrease in precision. This work introduces a novel approach to enhance the precision of NBC. The suggested approach employs a grid search to enhance the accuracy of Naïve Bayes classification. The results obtained indicate that the technique utilised achieved a significant degree of accuracy in forecasting compared to the conventional built-in Matlab NBC. Thus, by assuming conditional independence, the accuracy of the NBC may be enhanced.

Participants in criminal proceedings: problematic issues of classification

The article analyzes the conceptual approach that was used by the legislator to classify participants in criminal proceedings. It is noted that the current classification into participants in criminal proceedings and participants in judicial proceedings looks very illogical, since the concept of criminal proceedings also includes judicial proceedings as a separate stage. In addition, the specified classification groups do not include a court and an investigating judge, but the secretary of the court session and the court administrator are present. The purpose of the article is to formulate proposals for improving the classification of participants in criminal proceedings on the basis of clarifying the functions they perform and taking into account the rights granted to them and the duties assigned to them. To achieve the set goal, the following main scientific tasks were solved: to analyze the norms of the Code of Criminal Procedure of Ukraine regarding the determination of the status and classification of participants in criminal proceedings; to analyze scientific publications after the adoption of the Code of Criminal Procedure of Ukraine in 2012, devoted to participants in criminal proceedings; using a systemic approach to determine the connections between participants in criminal proceedings with their distribution by stages of criminal proceedings and functions performed. Taking into account the fact that the institute of participants in criminal proceedings with their distribution into parties and other participants is a novelty in domestic criminal procedural legislation, it is proposed to consider the problem of their classification based on the application of a systemic approach. In particular, a classification of participants in criminal proceedings is proposed, built on the basis of the use of two bases – stages of criminal proceedings and the nature of the functions performed by participants in criminal proceedings. In the author's view, this makes sense from several points of view: 1) clarity in determining the regulatory and legal status of participants in criminal proceedings; 2) use of a systemic approach in scientific research; 3) performance of didactic tasks when teaching a training course on criminal proceedings.

EDCLoc: a prediction model for mRNA subcellular localization using improved focal loss to address multi-label class imbalance

BackgroundThe subcellular localization of mRNA plays a crucial role in gene expression regulation and various cellular processes. However, existing wet lab techniques like RNA-FISH are usually time-consuming, labor-intensive, and limited to specific tissue types. Researchers have developed several computational methods to predict mRNA subcellular localization to address this. These methods face the problem of class imbalance in multi-label classification, causing models to favor majority classes and overlook minority classes during training. Additionally, traditional feature extraction methods have high computational costs, incomplete features, and may lead to the loss of critical information. On the other hand, deep learning methods face challenges related to hardware performance and training time when handling complex sequences. They may suffer from the curse of dimensionality and overfitting problems. Therefore, there is an urgent need for more efficient and accurate prediction models.ResultsTo address these issues, we propose a multi-label classifier, EDCLoc, for predicting mRNA subcellular localization. EDCLoc reduces training pressure through a stepwise pooling strategy and applies grouped convolution blocks of varying sizes at different levels, combined with residual connections, to achieve efficient feature extraction and gradient propagation. The model employs global max pooling at the end to further reduce feature dimensions and highlight key features. To tackle class imbalance, we improved the focal loss function to enhance the model’s focus on minority classes. Evaluation results show that EDCLoc outperforms existing methods in most subcellular regions. Additionally, the position weight matrix extracted by multi-scale CNN filters can match known RNA-binding protein motifs, demonstrating EDCLoc’s effectiveness in capturing key sequence features.ConclusionsEDCLoc outperforms existing prediction tools in most subcellular regions and effectively mitigates class imbalance issues in multi-label classification. These advantages make EDCLoc a reliable choice for multi-label mRNA subcellular localization. The dataset and source code used in this study are available at https://github.com/DellCode233/EDCLoc.

Factors of mild and moderate course of COVID-19 in non-immunized persons

Severity of COVID-19 is known to be related to various factors. The aim of the study was to perform comparative analysis of the features associated with mild and moderate course of infection caused by the SARS-CoV-2 virus in the absence of immunization against a new coronavirus infection, and looking for opportunities of binary classification. We performed the analysis of clinical and laboratory data of 59 medical staff members who had a mild (group No. 1), or moderate (group No. 2) forms of COVID-19. The results were analyzed using STATISTICA and GraphPad Prism programs. We have found that the patients with moderate course of the disease were 12% older, which numerically corresponded to a difference of 5 years (p = 0.019). Males were 1.5 times more likely to have a moderate course of the disease (p = 0.000). A part of respondents used non-specific immunoprophylactic agents. It was found that the intake of cholecalciferol, riamilovir/triazaverin did not affect the severity of disease, and the usage of human recombinant interferon alpha-2b in order to prevent SARS-CoV-2 virus infection was associated with subsequent mild course of COVID-19 (p = 0.000). More severe clinical course of COVID-19 was associated with simultaneous usage of several nonspecific immunoprophylactic agents, in particular, ascorbic acid, zinc compounds, umifenovir hydrochloride monohydrate (p = 0.000). Higher body mass index was also associated with a severe course of the disease (p = 0.034). The analysis showed that the issue of binary classification for the patients with mild and moderate COVID-19 in the absence of vaccination may be resolved (recognition accuracy is 90.9%, p 0.0001). The risk of moderate COVID-19 in non-immunized individuals is influenced by advanced age, gender factor, increased body mass index, presence of hypertension (70% hazard increase), as well as simultaneous use of several non-specific immunoprophylactic agents to prevent infection. Presence of allergic reactions and frequency of seasonal acute respiratory viral infections do not affect the severity of COVID-19. Prophylactic usage of human recombinant IFNa-2b is associated with milder course of infection caused by the SARS-CoV-2 virus.

ResDenseNet:Hybrid Convolutional Neural Network Model for Advanced Classification of Diabetic Retinopathy(DR) in Retinal Image Analysis

Preventing vision loss in diabetic retinopathy (DR) requires early and precise detection. Although strong feature extraction is required and there is class imbalance in the current methods, deep learning (DL) techniques have showed promise in DR classification. With components from both the ResNeXt and DenseNet designs, a unique DL architecture for DR classification is proposed in this work. A unique DL architecture that integrates DenseNet and ResNeXt components is proposed in this work.To address unique issues in DR classification, the proposed method integrates channel-wise masking with an attention mechanism. The network is able to learn from the less frequent DR stages because the channel-wise masking reduces the influence of the majority class and the attention method concentrates the network on important features. To improve interpretability and confidence in the model's predictions, the incorporation of Explainable AI (XAI) approaches is also covered.Our findings show that the suggested approach outperforms current architectures, achieving better sensitivity for differentiating DR phases at 0.82 and accuracy at 0.87. This shows that this new method has promise for improving DR categorization, which could result in earlier diagnoses and better patient outcomes.

Current concepts of chronic gastritis and gastropathies: new international consensus RE.GA.IN

Recent decades have been marked by several important milestones in the field of gastritis. New epidemiological reports were received, especially from countries with a high incidence of gastric cancer, and H.pylori infection was recognized as the most important cause of gastritis, due to which it was quickly included in the primary infectious oncogenic agents. Clinical strategies for the detection and eradication of H.pylori infection were developed, the previously unsuspected clinical and pathological significance of gastric microbiota was established, and extraordinary progress was made in the technology of esophagogastroduodenoscopy. Histolo­gical determination of gastritis in terms of stage (that is, risk stratification of stomach cancer) was implemented into clinical practice. In addition to the Sydney and Houston gastritis classifications, the six editions of the Maastricht Consensus (1996–2022) and the Kyoto Global Consensus deserve special attention, thanks to which broad agreements and significant scientific achievements became possible in the most controversial issues of the entire spectrum of gastritis, with a special emphasis on H.pylori gastritis, which accounts for more than 90 % of all forms of gastritis worldwide. The Real-world Gastritis Initiative (RE.GA.IN) marks the next step in the ongoing search to achieve a better understanding of various gastric conditions. The RE.GA.IN consensus was concluded in Venice in November 2022 after 8 months of intensive global scientific reasonings. RE.GA.IN mission itself has been focused on critically reviewing, updating, sharing and building consensus on the current scientific knowledge of inflammatory gastric lesions. It includes eight sections on clinicopathological topics, each consisting of preamble, which presents brief statements and corresponding explanatory texts. For each statement, the level of evidence (assessed according to a predefined four-level scale) and the strength of recommendations on the GRADE system are reported. The following topics were considered in the consensus: 1) definition and classification issues of gastritis; 2) spectrum of H.pylori gastritis; 3) key diagnosis of H.pylori gastritis; 4) H.pylori gastritis: clinical results; 5) autoimmune gastritis; 6) gastritis of low prevalence; 7) gastritis and gastric microbiota; 8) epidemiology of gastritis and associated precancerous and neoplastic lesions. Thus, the most controversial aspects of gastritis were addressed, a comprehensive and diverse body of knowledge was brought together to use patient-oriented evidence to assist physicians in their real-world clinical practice.

Psychotropic Taxonomies: Constructing a Therapeutic Framework for Psychiatry.

Pharmacological interventions are a cornerstone of psychiatric practice. The taxonomies used to classify these interventions influence the treatment and interpretation of psychiatric symptoms. Disease-based classification systems (e.g., 'antidepressant' and 'antipsychotic') do not reflect the fact that psychotropic agents are used across diagnostic categories, nor account for the dimensional nature of both the psychopathology and biology of psychiatric illnesses. In this review we discuss the history of psychotropic drug taxonomies and their influence on both clinical practice and drug development. We frame taxonomies as existing on a spectrum, with high-level disease-based approaches at one end and target-based molecular approaches at the other. Finally, we consider how data-driven methods might address the issue of classification at an intermediate level, based around transdiagnostic neurobiological and psychopathological markers.

Analysis of legislation and judicial practice regarding the legal status and social guarantees of employees of digital platforms in EU countries: challenges and perspectives

In today’s world, the rapid development of digital technologies and the gig economy has led to the emergence of new forms of employment that significantly change traditional labor relations. The platform economy, based on short­term contracts and freelance work, has become an important element of the labor market, offering new opportunities for workers, but at the same time presenting them with numerous challenges. The legal status of platform workers remains uncertain in many countries. Platforms often classify their workers as «independent contractors», «economically dependent independent workers» or «self-employed», which allows them to avoid obligations related to labor laws. This leads to legal gaps that jeopardize the social protection of workers on digital platforms. Different approaches to the legal status and social guarantees of workers in different countries create additional complexities in regulation. The issue of legal classification of digital platform workers remains unresolved, affecting their labor rights and social security. The authors consider the challenges that arise in connection with new forms of employment that displace traditional labor relations. The main attention is paid to the legal uncertainty of the status of gig workers, their social protection and the lack of a unified approach to the regulation of this sphere in different EU countries. The article analyzes legislative initiatives and case law in France, Germany, Austria and Spain, where the legal status of platform workers varies from employed to self-employed. Particular attention is paid to recent court decisions that affect the classification of platform workers and their social rights. The study reveals significant differences in the national legislation and judicial practice of different EU countries, which indicates the need to develop a unified European approach to the regulation of new forms of work. The authors emphasize the need to adapt national legislation to the new realities of the labor market, in light of the new EU Directive (Directive of the European Parliament and of the Council on improving working conditions in platform work), which aims to ensure the correct classification of employment status and the protection of the rights of gig workers.

Проблемні аспекти припинення підприємницької діяльності фізичними особами-підприємцями в Україні

Abstract. The article includes the definition and systematization of the main reasons and consequences that encourage entrepreneurs to stop their activities, the analysis of the legislative framework that regulates this process, as well as the development of recommendations for improving legal conditions to minimize the negative consequences of the cessation of activities for business entities and the country's economy in general . In particular, the issue of termination of business activities of individual entrepreneurs in Ukraine is investigated, emphasizing its relevance due to economic, legislative, social and tax aspects. The article examines major economic changes, such as globalization and technological development, that force entrepreneurs to adapt or cease operations, affecting the economy and the legal sphere. Analysis of legislation reveals innovations in the regulation of this process and their effectiveness. Emphasis is placed on understanding and legal aspects of termination of economic activity of an individual entrepreneur, in particular, voluntary and forced termination are distinguished. It is established that most authors describe this process as a complex legal procedure with various legal consequences and discuss the problems of imperfection of legislation in the context of modern trends towards the unification of legal norms. In addition, the article covers the issue of classification of the grounds for termination of the activity of an individual entrepreneur depending on the will of the owners and the legality of the process, with an emphasis on social and legal realities that shape business practice in Ukraine. It is concluded that the termination of entrepreneurial activity by a natural person-entrepreneur is a legal process regulated by numerous regulatory documents, in particular the Civil Code of Ukraine and other legislative acts. Termination of activity can be initiated by the entrepreneur himself or due to forced circumstances, such as bankruptcy. This analysis is important for understanding the processes governing the termination of the FOP, and can serve as practical material for lawyers, entrepreneurs, and law students. Keywords: Civil Code of Ukraine; Economic Code of Ukraine; subjects of economic activity; termination of business entity activity; natural persons-entrepreneurs; liquidation; termination.

On the criminological classification of persons inclined to glorify the enemy

Based on the study of sources of scientific, journalistic and statistical information, as well as on the results of the criminological analysis of the independently formed empirical base, the article reveals the issue of criminological classification of persons prone to glorification of the enemy. The article emphasizes that the specific criteria for dividing the entire mass of glorifiers into certain classes are the method of their involvement and the motivation for joining harmful ideas. It is noted that in the vast majority of cases, the process of involvement is dominated by its “soft” forms(mythologizing, © Батиргареєва В.С., Куковинець Д.О., 2024 mentioning authorities, persuasion, offers, bribery, promises, etc.), although there are others that are focused on using violent tactics. Attention is drawn to the fact that the main motivation for glorification of the aggressor is mostly ideological. At the same time, it is noted that, in addition to the above, the motivation for such a criminal act may be based on a selfish component, the desire to imitate the positions of relatives, friends, a certain part of the population of the region, etc., and may be supported by a sense of fear, the need for survival, and the expectation of intangible benefits. The study of these key aspects makes it possible, firstly, to identify four main types of glorifiers, including persistent ones; conformists or imitators; victims of an aggressive environment (adherents of the “lesser evil”), as well as prudent ones, secondly, to establish their characteristics and traits, which, in turn, allows us to form the basis for developing special measures to counter their illegal actions.

Label-Based Disentanglement Measure among Hidden Units of Deep Learning

The capability to disentangle underlying factors hidden in the observable data, thereby obtaining their abstract representations, is considered one important ingredient for the subsequent success of deep networks in various application scenarios. Recently, numerous practical measures and learning strategies have been established for disentanglement, showcasing their potential in improving the model’s explainability, controlability, and robustness. However, when the downstream tasks come to the classification issues, there is still no consensus in the community on the definition or measurement for disentanglement, and its connection to the generalization capacity remains not very clear. Aiming at this, we explore the highly non-linear effect of a specified hidden layer on the generalization capacity from an information perspective and obtain a tight bound. Upon decompsing the bound, we find that besides the unsupervised disentanglement measure term in the conventional sense, a new supervised disentanglement term also emerges with a nonnegligible effect on the generality. Consequently, a novel label-based disentanglement measure (LDM) is naturally introduced as the discrepancy between these two terms under the supervised learning settings to substitute the commonly used unsupervised disentanglement measure. The theoretical analysis reveals an inverse relationship between the defined LDM and the generalization capacity. Finally, using LDM as regularizer, the experiments show that the deep neural networks (DNNs) can effectively reduce generalization error while improving classification accuracy when noise is added to the data features or labels, which strongly supports our points.

Current Status of Stratigraphy of the Proterozoic Cuddapah Basin, Southern India

ABSTRACT The Cuddapah basin in southern India is one of the large Proterozoic basins with rich and strategic mineral resources. As a repository of sedimentary and tectonic records spanning from the Paleoproterozoic to the Neoproterozoic, the intracratonic Cuddapah basin holds vital clues to regional crustal development, paleogeography and tectonic underpinnings of passive margin sedimentation. In this article, a brief overview of the stratigraphy of the basin is presented with emphasis on recent developments in our understanding of the physical stratigraphy controlled by multiple unconformity bound sequences suggesting multiple transgressions of the sea, the emerging geochronological constraints, and broad sedimentary environments of different formation level units. Some issues of stratigraphic classification originating from allochthonus nature of the deformed rock successions of the Nallamalai fold belt have also been examined.

Luci e ombre nella riforma del lavoro sportivo

The Legislative Decree No. 36/2021 has had a significant impact on the regulation of labour relations in the sport sector, overcoming, among other things, the traditional legislative disregard for amateur work. The reform increases labour protections for individuals who professionally engage in sports activities, but at the same time aims to respect the specific nature of sports as an autonomous order, especially when it comes to the economic burden of sports organizations. The article starts by analysing the new concept of worker in the sector, which spans both professional and amateur sports. Then, the article proceeds by addressing the issue of classification between subordination and self-employment. The reform confirms the traditional dichotomy between professionals, which are subject to a stringent presumption of subordinate work, and amateurs, which in most cases are self-employed under article 409, No. 3 of the Italian Civil Procedure Code, with limited employment protections. In the final section the article briefly addresses the issue of voluntary work in the sport sector.

An Effective Hybrid Feature Selection Method Based on an Improved Artificial GTO Algorithm for Medical Datasets

Feature subset selection is considered as the most essential pre-processing step. Metaheuristic approaches may be employed to discover a solution to difficulties in feature selection, which can be viewed as an optimisation problem. The aim of the system is to provide a hybrid binary metaheuristic algorithm that combines gorilla troop optimisation and genetic algorithm to handle the feature selection issue effectively. This new method is called GTO-GA. To ensure that the optimisation technique converges fast and properly and to enhance the exploration process, the GA were used. The suggested technique is tested for stability and robustness using 16 medical datasets taken from the Kaggle and UCI repositories. To evaluate the chosen features’ performance in classification issues further. The results show that the algorithm outperforms 10 top-tier optimisation methods, including PSO, ALO, the original GTO and the SCA algorithm. The results highlighted the statistical difference, superiority and importance of the suggested feature selection strategies.

Molecular testing in mesenchymal neoplasms: What, when, and how to test? : Areview with aspecial focus on the value of next-generation immunochemistry as a substitute for molecular testing

With the widespread use of diverse modern molecular testing tools, the last two decades have seen significant advances in the classification of soft tissue neoplasms. Specifically, numerous molecularly defined new entities have been introduced and many established older entities have received more insightful molecular studies that have developed their classification further. The discrepant therapeutic and prognostic implications of this evolving complexity of the nosology of neoplastic diseases make the precise subtyping of soft tissue neoplasms unavoidable. However, these rapid developments of the modern diagnostic molecular pathology did not only offer efficient solutions to many complex classification issues, but they were accompanied by similarly complex and diverse emerging problems. Most importantly, these advances have not only challenged the historical dogma of some phenotypes that were once considered specific, but they also have questioned the value of diagnostic immunohistochemistry compared to emerging modern diagnostic molecular tools. Moreover, the central question of when to test, what to test, and how to test became more confusing. This review addresses the major molecular categories in soft tissue neoplasms, their characteristics, and the criteria to be used for selecting the most appropriate molecular diagnostic tool to be used in individual cases with aspecial focus on the value of next generation immunohistochemistry as asubstitute for molecular testing.