Introduction: Tumor-infiltrating lymphocytes (TIL) are linked to responses to chemotherapy and immunotherapy and clinical outcomes, especially in high-risk breast carcinomas. MammaPrint® (MP) and BluePrint® (BP) are genomic tests designed to provide risk stratification and molecular classification for early-stage hormone receptor (HR)-positive breast carcinomas, which could include tumors with HER2-low expression. We investigated correlations between TIL measurements, HER2 status, and MP/BP assays in early-stage HR-positive breast carcinomas. Materials and Methods: 167 early-stage HR-positive breast carcinomas with known MP/BP risk categorization were evaluated for TIL using whole slide scanned images according to the International TILs Working Group 2014 guidelines. HER2-low breast cancers were identified by IHC scores of 1+ and 2+ without HER2 amplification. A subset of high-TIL, high-risk cases underwent TSO500 (Illumina) next-generation sequencing (NGS). Results: The patients had a mean age of 51 years, ranging from 26 to 75 years. Among the profiled cases, 97% were either luminal A (96/167) or luminal B (66/167) breast carcinomas, with only five cases classified as HER2-enriched (n = 2) or basal-like (n = 3) carcinomas. Tumor grade was strongly associated with recurrence risk (p<0.001). The prevalence of the HER2-low phenotype was 65%, including 46/69 (67%) high-risk cases. TIL levels ranged from 0 to 70% and were low (≤10%) in the majority (75%) of cases in the cohort. However, high TIL levels were more frequently observed in cases with high recurrence risk (56% vs. 39%, p = 0.03). Additionally, TIL-enriched high-recurrence risk carcinomas contained targetable genomic alterations, including PIK3CA, BRCA1, BRCA2, and HER2 mutations. Conclusions: TIL levels are higher in early-stage HR-positive breast carcinomas with a high recurrence risk. These tumors also harbor targetable genomic alterations, suggesting that TIL measurement and genomic profiling could enhance risk stratification and identify patients who might benefit from targeted therapies. Her-2 low expression in high-risk patients provides a consideration for including novel ADC therapies in this subset of patients. Citation Format: Zoran Gatalica, Inga Rose, Faruk Skenderi, Nataliya Kuzmova, Semir Beslija, Timur Ceric, Inga Marijanovic, Ilir Kurtishi, Semir Vranic. High Tumor-Infiltrating Lymphocyte Levels Correlate with High MammaPrint® Recurrence Risk in Early-Stage Breast Carcinomas [abstract]. In: Proceedings of the San Antonio Breast Cancer Symposium 2024; 2024 Dec 10-13; San Antonio, TX. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(12 Suppl):Abstract nr P1-11-17.

Introductory programming courses are widely known for their difficulty among students. Success in courses is commonly measured in the form of final grades, which might not capture the challenges students face during their learning process. In this paper, we predict students’ success and their future compiler errors based on previously made errors. Furthermore, we examine the effect of applying two clustering techniques before making the predictions and identify key weeks and errors that have the greatest impact on predictions. Experimental results show that students’ compiler errors observed through the semester are an important predictor of students’ achievement and future struggles. Predictions are further improved using sentence encoder-generated embeddings with K-Means algorithm. Our study suggests that students’ errors, particularly the most recent ones, enable meaningful clustering that enhances performance prediction after only three weeks of the semester.

Introductory programming courses present significant challenges for novice learners, often leading to frustration and difficulty in identifying learning gaps. This research aims to develop an AI-driven tool that provides personalized guidance, moving beyond traditional "one-size-fits-all" approaches. Recognizing the limitations of relying solely on digital interaction logs in the era of generative AI, we explore the integration of student personal characteristics and fine-grained programming interactions to predict learning behavior and performance. We will investigate how to accurately predict student outcomes early in the semester, analyze the dynamics of learning behaviors, and design an AI-assisted tool to recommend tailored learning materials and feedback. Our goal is to foster effective learning and mitigate the risks associated with over-reliance on general-purpose AI, ultimately enhancing knowledge retention and problem-solving skills.

Introduction: Quality health services is a priority in thehealth system. However, after the outbreak of the COVID-19 pandemic, the goals of the health system had tobe adapted to the changed circumstances, in order tomeet the health needs of patients and the expectationsof health workers related to ensuring safe working conditionsin a crisis.Aim: To examine the attitudes and opinions of patientson the quality of services provided during treatment forthe infection of COVID-19Research material and methods: The study includedpatients aged 18 and over at the Sarajevo Canton HealthCenter who were infected with the COVID-19 virus in thesecond (autumn 2020) and third (spring 2021) waves ofthe pandemic and who used primary health care servicesduring their treatment. To conduct the research, we surveyed a total of 524 patients in the period from15 September 2022 – 30 November 2022.Results: By the recommendations of the Crisis Staff ofthe Ministry of Health and the rules of the profession,the majority of respondents contacted the doctor onthe third day after the onset of symptoms, 193 of them(36.8%). During the second and third wave, the majorityof patients, 287 (54.8%) believed that there were nohealth workers during that period who did not behaveprofessionally during the treatment. During treatmentand visits to healthcare institutions, 72 (13.7%) patientsfelt that they always felt that healthcare professionalstreated them differently. During treatment for COVID-19, 78 (14.89%) patients believed that there werealways enough health workers during their treatment.Conclusion: a large number of respondents think thatthe healthcare professionals treated them professionallyduring the treatment, and that they had enough informationabout the situation, and that they acted in accordancewith the instructions published by the profession.

Abstract Background/Objectives Molar-Incisor Hypomineralisation (MIH) affects 14% of the global population, often leading to compromised first permanent molars (FPM). Early extraction of severely affected FPMs may temporarily affect proper eruption and alignment of second permanent molars (SPM) and second premolars (SP). This study aimed to evaluate the eruption patterns of SPMs and SPs, and the overeruption of opposing FPMs, after early FPM extraction using panoramic radiographs in 11-year-old patients. A secondary aim was to assess radiographic quality for these evaluations. Subjects and Methods This split-mouth trial included patients aged 6–9 with severe MIH requiring FPM extraction. Panoramic radiographs were taken pre-extraction (T0) and at age 11 (T1) to measure eruption length and angulation of SPMs and SPs. Radiographs were analysed using Facad software, and imaging errors were recorded. Paired t-tests compared extraction and non-extraction sides. Results Among 47 patients, 31 had maxillary and 25 mandibular FPM extractions. At T0, eruption length and angulation of SPMs and SPs were similar between sides. At T1, maxillary SPMs erupted faster (13.5mm vs. 10.8mm, p < 0.001) and more upright (72.9° vs. 62.1°, p < 0.001) on the extraction side, while SPs showed increased mesial angulation (82.5° vs. 89.3°, p < 0.05). Mandibular SPMs and SPs showed no differences. No overeruption of opposing FPMs was observed. Measurement reliability was excellent (ICC: 0.997–0.999), despite 75 of 94 radiographic contained errors. Limitations The three-year follow-up limits long-term insights, and radiographic distortions may affect reliability. Conclusions Early FPM extraction impacts maxillary but not mandibular SPM and SP eruption patterns without causing overeruption of opposing FPMs by age 11. Radiographic techniques are essential to minimize incorrect patient positioning, as such factors may impact measurement reliability.

Group recommender systems (GRSys) focus on the challenges of recommending to groups of users with possibly contradicting needs and preferences. Methodologically, we distinguish between approaches aiming to aggregate preferences of group members and aggregating per-user recommendations. In early GRSys research, this methodological duality did not affect the connected research objectives and evaluation methodology much. However, nowadays, we witness a gradual rift in the research induced by both algorithm classes. In this work, based on a survey of 110 recent GRSys papers, we aim to quantify this rift along several aspects, including involved communities, evaluation datasets, objectives, and baselines. We showcase how little both subtrees have in common nowadays and discuss missed opportunities this rift causes. In conclusion, we also highlight novel research avenues that may contribute towards bridging the rift to the benefit of both research areas.

Group Recommender Systems (GRSys) are designed to recommend items that address the needs of groups of people. Compared to individual users, groups are dynamic entities where interpersonal relationships, group dynamics, emotional contagion, etc., substantially affect the group’s needs. Nevertheless, these characteristics are often poorly defined or overlooked in system modeling. The fourth GMAP workshop brought together a community of scholars focused on group modeling, adaptation, and personalization. The event was dedicated to exploring the challenges and opportunities of supporting collective decision-making, fostering interdisciplinary dialogue, and forging new collaborations. The four presented papers covered a diverse range of topics: (i) an exploratory analysis of LLM applications to group meeting transcripts, (ii) an extensive review of the growing methodological divide in group recommender systems, (iii) a novel application of group modeling for personalizing public displays, and (iv) a detailed examination of prompt design for group recommendations using LLMs.

Understanding how students perceive and utilize Large Language Models (LLMs) and how these interactions relate to their learning behavior and individual differences is crucial for optimizing educational process and outcomes. This paper introduces a novel dataset comprising weekly self-reported data from students in an introductory programming course, i.e., students’ AI tool usage, perceived difficulty of weekly subject areas, personality traits, preferred learning styles, and general attitudes toward AI. We present a descriptive overview of the collected data and conduct a correlation analysis to gain first insights into the students’ individual differences and their learning outcomes, frequency of AI tools usage, as well as their attitudes toward AI. The findings reveal that while individual student characteristics did not show significant correlations with final performance or frequency of AI tool usage, the combination of students’ expectations for success and their perceived value of the task (constructs of expectancy theory) were significantly associated with both course outcomes and how often they used the AI tool. Additionally, motivational factors may be the key to fostering positive attitudes toward AI, while personality traits, particularly those related to negative emotionality, may play a more significant role in shaping resistance. This initial analysis lays the groundwork for future investigations on the prospects of AI in support of the students’ learning process.

Group Recommender Systems aim to support groups in making collective decisions, and research has consistently shown that the more we understand about group members and their interactions, the better support such systems can provide. In this work, we propose a conceptual framework for modeling group dynamics from group chat interactions, with a particular focus on decision-making scenarios. The framework is designed to support the development of intelligent agents that provide advanced forms of decision support to groups. It consists of modular, loosely coupled components that process and analyze textual and multimedia content, which is shared in group interactions, to extract user preferences, emotional states, interpersonal relationships, and behavioral patterns. By incorporating sentiment analysis, summarization, dialogue state tracking, and conflict resolution profiling, the framework captures both individual and collective aspects of group behavior. Unlike existing approaches, our model is intended to operate dynamically and adaptively during live group interactions, offering a novel foundation for group recommender and decision support systems.

Echinococcus multilocularis, the causative agent of alveolar echinococcosis (AE), is a parasitic zoonosis of increasing public health significance in Europe. Although previously confirmed in red foxes in Bosnia and Herzegovina, this study provides the first report of E. multilocularis in golden jackals (Canis aureus) in the country. Between December 2024 and March 2025, a total of 44 golden jackals were examined across 15 localities in Bosnia and Herzegovina, with E. multilocularis detected in 6.8 % of the samples from three sites in Western and Central Bosnia and Herzegovina. Adult Echinococcus spp. worms were first detected using the intestinal scraping technique and identified by microscopy. To confirm these findings and differentiate between Echinococcus species, DNA extracted from adult worms was then subjected to species-specific PCR targeting a fragment of the mitochondrial 12S ribosomal RNA gene. PCR-positive samples for E. multilocularis were further validated by next-generation sequencing (NGS) of a 203 bp amplicon of the 12S rRNA gene. These findings indicate an expanding distribution of E. multilocularis in Bosnia and Herzegovina, highlighting the role of golden jackals as definitive hosts for the parasite. Given the growing jackal population in the country and the increasing public health concerns, enhanced surveillance and further research are warranted, particularly regarding human cases of E. multilocularis infection, to better understand the associated epidemiological risks.

Objectives The aims this research were to analyze self-reported oral health-related quality of life (OHRQoL) and dental fear and anxiety (DFA) in 11-year-old patients after either restorative treatment or after extraction of first permanent molars (FPM) affected by severe molar incisor hypomineralization (MIH). The research question focused on whether these treatments lead to different outcomes of DFA and OHRQoL over time. Materials and methods GuREx-MIH, a multicenter trial, was conducted involving 83 children aged 6–9 years who were diagnosed with severe MIH in FPMs. Patients were randomly assigned to receive either restorative treatment with resin composite or extraction. Patient comfort was assessed through OHRQoL and DFA, using the Swedish version of the Child Perceptions Questionnaire (CPQ11-14) and the Children’s Fear Survey Schedule-Dental Subscale (CFSS-DS), which were administered before treatment (T0) and at follow-up when patients were 11 years old (T1). Descriptive statistical analyses were conducted and comparisons between the restorative and extraction groups were performed using T-tests. Results A total of 79 patients completed the study, with 43 allocated to restorative treatment and 36 to extraction. At follow-up, the mean OHRQoL score was 8.9 (standard deviation [SD] 7.3) for patients in the restorative group and 9.6 (SD 6.7) for those in the extraction group (p: 0.337, T-test). The mean DFA score was 21.5 (SD 5.5) for the restorative group and 23.1 (SD 6.8) for the extraction group (p: 0.130, T-test). Conclusions Restorative treatment and extraction of FPMs affected by MIH lead to similar impact on DFA and OHRQoL at 11 years of age.

Among numerous global problems, one of the most significant is air pollution. In this paper, unwashed (U) and water-washed (W) needles of two conifers—European larch and Douglas fir—were used to assess their capacity for the retention and accumulation of heavy metals. The needle samples were used to represent the atmospheric deposition of heavy metals located on the surface of the needles. The sampled European larch and Douglas fir plantations were situated at three locations in Serbia: a least polluted (Kučevo), a moderately polluted (Avala), and a very polluted (Lazarevac) site. The content of five heavy metals (Ni, Cu, Co, Cd, Pb) was investigated in the study. The concentration of cadmium (Cd) was higher in the European larch needles compared to Douglas fir, while the differences in the content of the other heavy metals between the species studied were insignificant. For both species, the following trend applied with respect to the heavy metal content in their needles: Ni ˃ Cu ˃ Co ˃ Pb ˃ Cd. Based on the results obtained, we deduced that the concentrations of all investigated heavy metals at all three locations for both species were within the allowed limits, except for nickel (Ni) content, which was over the predicted limit values for both species in the highly polluted area (Lazarevac). A PCA (principal component analysis) undertaken suggests that European larch has a greater ability to accumulate Co than Douglas fir on sites contaminated with heavy metals. The predictive foliar metal accumulation index (MAI) value was slightly higher in Douglas fir (4.14) than in European larch (3.76); therefore, the results suggest that this species would be a good planting choice, particularly in urban and industrial environments.

The Radiological Society of North America (RSNA) Lumbar Degenerative Imaging Spine Classification (LumbarDISC) dataset is the largest publicly available dataset of adult MRI lumbar spine examinations annotated for degenerative changes. The dataset includes 2,697 patients with a total of 8,593 image series from 8 institutions across 6 countries and 5 continents. The dataset is available for free for non-commercial use via Kaggle and RSNA Medical Imaging Resource of AI (MIRA). The dataset was created for the RSNA 2024 Lumbar Spine Degenerative Classification competition where competitors developed deep learning models to grade degenerative changes in the lumbar spine. The degree of spinal canal, subarticular recess, and neural foraminal stenosis was graded at each intervertebral disc level in the lumbar spine. The images were annotated by expert volunteer neuroradiologists and musculoskeletal radiologists from the RSNA, American Society of Neuroradiology, and the American Society of Spine Radiology. This dataset aims to facilitate research and development in machine learning and lumbar spine imaging to lead to improved patient care and clinical efficiency.