The medical discourse entails the analysis of the modalities, which are far from unbiased, by which hypotheses and results are laid out in the dissemination of findings in scientific publications. This gives different emphases on the background, relevance, robustness, and assumptions that the audience takes for granted. This concept is extensively studied in socio-anthropology. However, it remains generally overlooked within the scientific community conducting the research. Yet, analyzing the discourse is crucial for several reasons: to frame policies that take into account an appropriately large screen of medical opportunities; to avoid overseeing promising but less walked paths; to grasp different types of representations of diseases, therapies, patients, and other stakeholders; to understand how these terms are conditioned by time and culture. While socio-anthropologists traditionally use manual curation methods–limited by the lengthy process–machine learning and AI may offer complementary tools to explore the vastness of an ever-growing body of medical literature. In this work, we propose a pipeline for the analysis of the medical discourse on the therapeutic approaches to rheumatoid arthritis using topic modeling and transformer-based emotion and sentiment analysis, overall offering complementary insights to previous curation.

This study introduces an explainable Artificial Intelligence (XAI) framework that couples legal-domain NLP with Structural Topic Modeling (STM) and WordNet semantic graphs to rigorously analyze over 1,900 GDPR enforcement decision summaries from a public dataset. Our methodology focuses on demonstrating the pipeline's validity respect to manual analyses by inspecting the results of four well-know research questions: (1) cross-country fine distribution disparities (automated metadata extraction); (2) the violation severity-fine amount relationship (keyness and semantic analysis); (3) structural text patterns (network analysis and STM); and (4) prevalent enforcement triggers (topic prevalence modeling) The pipeline's validity is underscored by its ability to replicate key findings from previous manual analyses while enabling a more nuanced exploration of GDPR enforcement trends. Our results confirm significant disparities in enforcement across EU member states and reveal that monetary penalties do not consistently correlate with violation severity. Specifically, serious infringements, particularly those involving video surveillance, frequently result in low-value fines, especially when committed by individuals or smaller entities. This highlights that a substantial proportion of severe violations are attributed to smaller actors. Methodologically, the framework's ability to quickly replicate such well-known patterns, alongside its transparency and reproducibility, establishes its potential as a scalable tool for transparent and explainable GDPR enforcement analytics.

Background Analysis of Electronic Health Records (EHRs) is crucial in real-world evidence (RWE), especially in oncology, as it provides valuable insights into the complex nature of the disease. The implementation of advanced techniques for automated extraction of structured information from textual data potentially enables access to expert knowledge in highly specialized contexts. In this paper, we introduce MISTIC, a Natural Language Processing (NLP) approach to classify the presence or absence of metastasis in Italian EHRs, in the breast cancer domain. Methods Our approach consists of a transformer-based framework designed for few-shot learning, requiring a small labelled dataset and minimal computational resources for training. The pipeline includes text segmentation to improve model processing and topic analysis to filter informative content, ensuring relevant input data for classification. Results MISTIC was evaluated across multiple data sources, and compared to several benchmark methodologies, ranging from a pattern-matching system, composed of regex and semantic rules, to BERT-based models implemented in a zero-shot learning setup and Large Language Models (LLMs). The results demonstrate the generalization of our approach, achieving an F-Score above 87% on all the sources, and outperforming the other experiments, with an overall F-Score of 91.2%. Conclusions MISTIC achieves high performance in the Italian metastasis classification task, outperforming rule-based systems, zero-shot BERT models, and LLMs. Its few-shot learning setup offers a computationally efficient alternative to large-scale models, while its segmentation and topic analysis steps enhance explainability by explicitly linking predictions to key textual elements. Furthermore, MISTIC demonstrates strong generalization across different data sources, reinforcing its potential as a scalable and transparent solution for clinical text classification. By extracting high-quality metastatic information from diverse textual data, MISTIC supports medical researchers in analyzing unstructured and highly informative content across a wide range of medical reports. In doing so, it enhances data accessibility and interpretability, addressing a critical gap in health informatics and clinical practice.

The increasing availability of clinical reports offers valuable opportunities for natural language processing (NLP) applications in healthcare. Large Language Models (LLMs), such as BERT-based architectures and generative models, have shown great promise in text classification, summarization, and semantic analysis. However, applying LLMs to Electronic Health Records (EHRs) poses challenges due to token limits and the complexity of clinical text. Sentence Boundary Detection (SBD), which segments text into meaningful units, is a critical preprocessing step to address token constraints and improve model interpretability, particularly for tasks like text classification. This study benchmarks several SBD methods, including traditional approaches (e.g., NLTK, Stanza, PySBD) and state-of-the-art transformer-based models, such as Segment Any Text (SAT), fine-tuned using low-rank adaptation (LoRA) for the clinical domain. The models were evaluated on a dataset of clinical reports in Italian, sourced from the Gemelli hospital of Rome, using metrics like F1-score to measure segmentation quality. The results reveal that PySBD achieved the best performance, closely aligning with the gold standard, with a median F1-Score of 83%. We also assessed the impact of segmentation on a downstream metastasis classification task, comparing the performance of a transformer-based model applied to unsegmented reports versus reports processed with PySBD. Segmentation outperformed the entire report scenario, with a higher F1-Score of 92% versus 88%, demonstrating that SBD improves text classification by ensuring semantic coherence, adhering to token constraints, and providing sentence-level explainability. In conclusion, this study highlights the importance of SBD in enhancing both the quality and interpretability of downstream NLP tasks in healthcare. By benchmarking traditional and transformer-based SBD models, we validate the role of segmentation as a critical preprocessing step to advance clinical NLP applications, offering insights for improving performance and clinical relevance in the processing of EHRs.

This work presents the analysis model of the study data available in the LMS platforms specifically designed to analyze potential critical issues as a functional indicator for the possible achievement of the training objectives and completion of the course. The illustrated system highlights how the use of statistical indicators and predictability can be an effective tool for the early identification of possible critical issues in the field of training results, as well as design and organizational inconsistencies that can weigh on the effectiveness of the training system made available. Our work explains how adopting a data analysis model applied to training environments provides the tutoring system with adequate information on potential critical issues to favor targeted interventions on the participants to prevent risks of training ineffectiveness. At the same time, it analyzes the global quality of the courses made available through a perspective of data exploration that starts from the learning experience and enhances the data already present in the LMS platforms.

The medical discourse, entails the analysis of the modalities, far from unbiased, by which hypotheses and results are laid out in the dissemination of findings in scientific publications, giving different emphases on the background, relevance, robustness, and assumptions that the audience should take for granted. While this concept is extensively studied in socio-anthropology, it remains generally overlooked within the scientific community conducting the research. Yet, analyzing the discourse is crucial for several reasons: to frame policies that take into account an appropriately large screen of medical opportunities, to avoid overseeing promising but less walked paths, to grasp different types of representations of diseases, therapies, patients, and other stakeholders, understanding and being aware of how these very terms are conditioned by time, culture and so on. While socio-anthropologists traditionally use manual curation methods, automated approaches like topic modeling offer a complementary way to explore the vast and ever-growing body of medical literature. In this work, we propose a complementary analysis of the medical discourse regarding the therapies offered for rheumatoid arthritis using topic modeling and large language model-based emotion and sentiment analysis.

Topic Modelling (TM) is a widely adopted generative model used to infer the thematic organization of text corpora. When document-level covariate information is available, so-called Structural Topic Modelling (STM) is the state-of-the-art approach to embed this information in the topic mining algorithm. Usually, TM algorithms rely on unigrams as the basic text generation unit, whereas the quality and intelligibility of the identified topics would significantly benefit from the detection and usage of topical phrasemes. Following on from previous research, in this paper we propose the first iterative algorithm to extend STM with n-grams, and we test our solution on textual data collected from four well-known ToR drug marketplaces. Significantly, we employ a STM-guided n-gram selection process, so that topic-specific phrasemes can be identified regardless of their global relevance in the corpus. Our experiments show that enriching the dictionary with selected n-grams improves the usability of STM, allowing the discovery of key information hidden in an apparently "mono-thematic" dataset.

In this paper we introduce the Mathematical Desk for Italian Industry, a project based on applied and industrial mathematics developed by a team of researchers from the Italian National Research Council in collaboration with two major Italian associations for applied mathematics, SIMAI and AIRO. The scope of this paper is to clarify the motivations for this project and to present an overview on the activities, context and organization of the Mathematical Desk, whose mission is to build a concrete bridge of common interests between the Italian scientific community of applied mathematics and the world of the Italian enterprises. Some final considerations on the strategy for the future development of the Mathematical Desk project complete the paper.