Breast cancer is the most common cancer among women worldwide. Treatment decision-making in multidisciplinary tumor boards is complex, involving integration of clinical guidelines, patient data, and preferences. We retrospectively evaluated MammaBoardGPT, an few-shot in-context learning and Retrieval Augmented Generation (RAG) enhanced GPT-4 model with European guidelines and five Tumor Board labeled cases, against standard GPT-4 in 25 breast cancer cases discussed at a German hospital. After recursive prompting, MammaBoardGPT achieved complete agreement with tumor board decisions in 84 % of cases, partial agreement in 16 % and no disagreements; standard GPT-4 showed 76 % complete agreement, 20 % partial agreement, and 4 % complete disagreements. A significant difference was observed in MammaBoardGPT's (Stuart-Maxwell P = 0.0048) but not for GPT-4 agreement with tumor board decisions before versus after recursive prompting (Stuart-Maxwell P = 0.135), neither for MammaBoardGPT and GPT-4 in their tumor board decision agreement post-recursive prompting (Stuart-Maxwell P = 0.37). These findings support MammaBoardGPT's potential for tumor board decision support, warranting prospective validation and real-time assessment.

Introduction: Acute appendicitis (AA) is a common cause of abdominal pain that can lead to complications like perforation and intra-abdominal abscesses, increasing morbidity and mortality, often requiring emergency surgery. Nevertheless, appendectomy is performed in up to 95% of uncomplicated cases, while complications like perforation and intra-abdominal abscesses increase morbidity and mortality. The current study compares the accuracy of GPT-4.5, DeepSeek R1, and machine learning in assisting with surgical decision-making for patients presenting with lower abdominal pain at the Emergency Department. Methods: In this multicenter retrospective study, 63 histopathologically confirmed appendicitis patients and 50 control patients with right abdominal pain presenting at the Emergency Department at two German hospitals between October 2022 and October 2023 were included. Using each patient’s clinical, laboratory, and radiological findings, DeepSeek (with and without Retrieval-Augmented Generation using 2020 Jerusalem guidelines) was compared in terms of accuracy with GPT-4.5 and a random forest-based machine-learning model, with a board-certified surgeon (reference standard) to determine the optimal treatment approach (laparoscopic exploration/appendectomy versus conservative antibiotic therapy). Results: Accuracy of agreement with board-certified surgeons in the decision-making of appendectomy versus conservative therapy increased non-significantly from 80.5% to 83.2% with DeepSeek and from 70.8 to 76.1% when GPT-4.5 was provided with the World Journal of Emergency Surgery 2020 Jerusalem guidelines on the diagnosis and treatment of acute appendicitis. The estimated machine-learning model training accuracy was 84.3%, while the validation accuracy for the model was 85.0%. Discussion: GPT-4.5 and DeepSeek R1, as well as the machine-learning model, demonstrate promise in aiding surgical decision-making for appendicitis, particularly in resource-constrained settings. Ongoing training and validation are required to optimize the performance of such models.

The merging of AI and software engineering marks a defining moment: intelligent systems now move beyond simple code completion or test automation to become active partners in each phase of development. We term this “Artificial Software Engineering,” a collaborative framework where human ingenuity and machine intelligence co–author software—from early prototypes and code generation to debugging and architectural design (Menzies et al., 2019). By looking at platforms like Devin AI and GitHub Copilot, we see clear benefits—faster iterations, deeper error detection—but also face new challenges around trust, ownership, legal responsibility, and maintaining AI‐influenced code over time. Rather than treating automation as an end goal, we argue that this emerging discipline demands fresh thinking about ethics, team dynamics, and design practices. Ultimately, the most successful software.

Artificial intelligence (AI) is the one of the fast changing several fields, including such as asset management and cultural affairs. The ongoing development of AI technologies that claims lots of opportunities, offers new tools for the preservation, promotion, and restoration of individiual and global cultural assets. In Azerbaijan, a country rich with historical and cultural heritage, AI tools has the potential to play a pivotal role in ensuring the sustainability and accessibility of national treasures and colloborations. This paper discusses the general cultural and techno-psychological development perspectives of AI and examines how its advancements can influence Azerbaijan's cultural heritage landscape. Through the integration of AI-based approaches such as digitization of history, virtual reality of ancient era, and predictive analysis of civilization status, Azerbaijan can preserve its historical legacy while promoting it on global platforms.

Personalized drug selection requires balancing therapeutic efficacy, adverse events, drug interactions, and cost–objectives that are inherently conflicting. This study proposes a hybrid architecture integrating Mamdani fuzzy inference, ensemble machine learning, NSGA-II optimization, and Fuzzy DIBR II ranking for multi-objective pharmacotherapy. The Mamdani system encodes eight clinical safety rules to filter unsuitable patient-drug pairs based on renal and hepatic function. Random Forest and XGBoost models trained on 44,692 pairs achieve AUC-ROC of 0.871 and 0.907 for efficacy and adverse event prediction, respectively. NSGA-II generates nine unique Pareto-optimal prescriptions over 30 generations. Fuzzy DIBR II elicits criterion weights from physician preferences modeled as triangular fuzzy numbers (𝜎 = 0.7), yielding 𝑤₁ = 0.387 (efficacy), 𝑤₂ = 0.302 (safety), 𝑤₃ = 0.205 (interactions), 𝑤₄ = 0.105 (cost). The top-ranked prescription achieves 84.4% efficacy, 39.4% adverse events, 11.6% interaction severity, and 608.60 AZN cost. Results demonstrate clinically interpretable multi-criteria recommendations with explicit trade-off quantification.

Baxılan tədqiqat işində nevroloji əsaslı psixi pozulmaların - depressiya, təşviş pozuntusu və stressin artan dinamikası stoxastik diferensial tənliklər sistemi vasitəsilə modelləşdirilmişdir. Təklif edilmiş model psixi simptomların şiddətini və bu simptomlara təsir edən əsas bioloji göstəriciləri – dopamin, kortizol və GABA – gamma-aminobütirik turşusu kimi neyrotransmitterlərinin səviyyələrini nəzərə alır. Elmi-tədqiqat işində baxılan tənliklər sistemindəki axtarılan funksiyaların əmsalları – uyğun olaraq hormonal səviyyənin simptomlara təsir dərəcəsini, stoxastik təsirlərini və geribildirim mexanizmlərini xarakterizə edir. Çoxqatlı süni neyron şəbəkə vasitəsi ilə əmsalları təmsil edən parametrlər üçün aşağı xətalı qiymətlər proqnozlaşdırılmışdır və baxılan tənliklər sistemi Eyler – Maruyama üsulu ilə ədədi həlli tapılmışdır.