This paper proposes a novel methodology for automatic detection and localization of gastrointestinal (GI) anomalies in endoscopic video frame sequences. Training is performed with weakly annotated images, using only image-level, semantic labels instead of detailed, pixel-level annotations. This makes it a cost-effective approach for the analysis of large videoendoscopy repositories. Other advantages of the proposed methodology include its capability to suggest possible locations of GI anomalies within the video frames, and its generality, in the sense that abnormal frame detection is based on automatically derived image features. It is implemented in three phases: a) It classifies the video frames into abnormal or normal using a Weakly Supervised Convolutional Neural Network (WCNN) architecture; b) detects salient points from deeper WCNN layers, using a Deep Saliency Detection (DSD) algorithm; and c) localizes GI anomalies using an Iterative Cluster Unification (ICU) algorithm. ICU is based on a Pointwise Cross-Feature-Map (PCFM) descriptor extracted locally from the detected salient points using information derived from the WCNN. Results from extensive experimentation using publicly available collections of gastrointestinal endoscopy video frames, are presented. The datasets used include a variety of GI anomalies. Both the anomaly detection and the localization performance achieved, in terms of the Area Under receiver operating Characteristic (AUC), were >80%. The highest AUC for anomaly detection was obtained on conventional gastroscopy images, reaching 96%, and the highest AUC for anomaly localization was obtained on wireless capsule endoscopy images, reaching 88%.

The rapid development of generative artificial intelligence (AI) is expected to have a profound impact on various aspects of human society, including mathematics education. Nevertheless, there is a noticeable lack of research, particularly in Greece, that focuses on the development and assessment of lesson plans and math worksheets tailored for students with special educational needs. To address this research gap, we designed and conducted a nine-hour teaching intervention in a general mathematics classroom in Greece, involving two 8th grade students with special educational needs as the subjects of the study. The intervention utilized worksheets generated by the ChatGPT 3.5 application, which were customized based on the current curriculum, as well as the special educational needs and interests of the two participating students. The data were collected through interviews, tasks, and e-questionnaires, and analyzed using a new theoretical framework based on the concept of mathematical familiarity. The results indicated that students were actively engaged in the educational process, felt safe and confident, satisfactorily met the learning objectives, and developed positive attitudes towards the mathematics course. The paper concludes with a list of good practices, teaching suggestions and restrictions that could be useful to teachers and education policy makers. The target audience for the current study is, mainly, mathematics teachers who serve at all levels of education and have students with special educational needs in their classrooms. Furthermore, the article may also prove of interest to students, parents and teachers who are interested in the interaction between mathematics education and generative AI.

The Covid-19 pandemic made a significant impact on society, including the widespread implementation of lockdowns to prevent the spread of the virus. This measure led to a decrease in face-to-face social interactions and, as an equivalent, an increase in the use of social media platforms, such as Twitter. As part of Industry 4.0, sentiment analysis can be exploited to study public attitudes toward future pandemics and sociopolitical situations in general. This work presents an analysis framework by applying a combination of natural language processing techniques and machine learning algorithms to classify the sentiment of each tweet as positive, or negative. Through extensive experimentation, we expose the ideal model for this task and, subsequently, utilize sentiment predictions to perform time series analysis over the course of the pandemic. In addition, a change point detection algorithm was applied in order to identify the turning points in public attitudes toward the pandemic, which were validated by cross-referencing the news report at that particular period of time. Finally, we study the relationship between sentiment trends on social media and, news coverage of the pandemic, providing insights into the public’s perception of the pandemic and its influence on the news.

Health Care Professionals (HCPs) are the main end-users of digital clinical tools such as electronic prescription systems. For this reason, it is of high importance to include HCPs throughout the design, development and evaluation of a newly introduced system to ensure its usefulness, as well as confirm that it tends to their needs and can be integrated in their everyday clinical practice. In the context of the PrescIT project, an electronic prescription platform with three services was developed (i.e., Prescription Check, Prescription Suggestion, Therapeutic Prescription Monitoring). To allow an iterative process of discovery through user feedback, design and implementation, a two-phase evaluation was carried out, with the participation of HCPs from three hospitals in Northern Greece. The two-phase evaluation included presentations of the platform, followed by think-aloud sessions, individual platform testing and the collection of qualitative as well as quantitative feedback, through standard questionnaires (e.g., SUS, PSSUQ). Twenty one HCPs (8 in the first, 18 in the second phase, and five present in both) participated in the two-phase evaluation. HCPs comprised clinicians varying in their specialty and one pharmacist. Clinicians' feedback during the first evaluation phase already deemed usability as "excellent" (with SUS scores ranging from 75 to 95/100, showing a mean value of 86.6 and SD of 9.2) but also provided additional user requirements, which further shaped and improved the services. In the second evaluation phase, clinicians explored the system's usability, and identified the services' strengths and weaknesses. Clinicians perceived the platform as useful, as it provides information on potential adverse drug reactions, drug-to-drug interactions and suggests medications that are compatible with patients' comorbidities and current medication. The developed PrescIT platform aims to increase overall safety and effectiveness of healthcare services. Therefore, including clinicians in a two-phase evaluation confirmed that the introduced system is useful, tends to the users' needs, does not create fatigue and can be integrated in their everyday clinical practice to support clinical decision and e-prescribing.