Amaç: İlaç-ilaç etkileşimi (İİE), birden fazla ilacın birlikte kullanımıyla ortaya çıkan, advers ilaç reaksiyonlarından (AİR) olup, ilaçların tedavideki etkinliğinin azalması ve komplikasyonlarla ilişkilidir. Yoğun bakım ünitesi (YBÜ) hastalarında çoklu ilaç kullanımı potansiyel İİE açısından bu hastaları risk grubu haline getirmektedir. Çalışmamızda, ülkemizdeki farklı yoğun bakımlarında benzer hasta gruplarındaki potansiyel ilaç-ilaç etkileşimlerini (pİİE) belirlemek istedik. Gereç ve Yöntem: Bu çalışma Türkiye’deki YBÜ’de yatan kritik hastalarda çok merkezli nokta prevalans çalışması olarak tasarlanmıştır. Hasta orderları Lexi interact online interaction checker program (https: //www.uptodate.com/drug-interactions) ile pİİE açısından analiz edildi. Bulgular: İki yüz otuz altı hasta verisi içinden yaş

Large language models (LLMs) have demonstrated potential in clinical reasoning tasks; however, their performance in real-world intensive care unit (ICU) acid–base interpretation remains insufficiently characterized, particularly in complex and mixed disorders. Most existing evaluations rely primarily on aggregate accuracy metrics without examining structural error patterns or the clinical severity of misclassification. In high-acuity ICU settings, under-recognition of physiological complexity may carry disproportionate safety implications. In this prospective observational study, arterial blood gas (ABG) data from 50 consecutive ICU patients were interpreted independently by ICU physicians and ChatGPT using a standardized prompt. Interpretations were harmonized into six predefined diagnostic categories and compared with a final reference diagnosis established by a blinded expert panel. Agreement was assessed using Cohen’s kappa and diagnostic accuracy metrics. Additional analyses included complexity-stratified evaluation, mixed-disorder sensitivity, multi-label component-level (metabolic and respiratory) detection, false reassurance risk assessment, harm-weighted misclassification modeling, bootstrap confidence intervals, and post-hoc power analysis. Overall categorical accuracy was 82% for ICU physicians and 72% for ChatGPT. Agreement was substantial in both groups (κ = 0.73 vs. 0.63). Paired comparison did not demonstrate a statistically significant difference in overall classification ( p = 0.267), and post-hoc power analysis indicated limited ability to detect modest effect sizes (power = 0.22). However, stratified analyses revealed clinically meaningful structural differences. Sensitivity for mixed acid–base disorders was 0.96 for ICU physicians and 0.63 for ChatGPT. ChatGPT uniquely classified 16.7% of mixed cases as normal (false reassurance), whereas ICU physicians produced no false-normal classifications. Component-level analysis demonstrated lower respiratory component sensitivity for ChatGPT (0.88 vs. 1.00), contributing to under-recognition of physiological complexity. Harm-weighted misclassification modeling showed significantly higher clinical severity of errors for ChatGPT (mean difference 0.12; 95% CI 0.032–0.220; p = 0.026). While aggregate diagnostic agreement appeared broadly comparable, complexity-stratified and harm-weighted analyses demonstrated asymmetric error patterns with potential safety implications. These findings do not establish clinical equivalence and suggest that evaluation of AI diagnostic tools in critical care should extend beyond overall accuracy to incorporate safety-oriented and harm-weighted assessment frameworks.

Effect of Duration of Pre-Procedure Fasting on Clinical Outcomes in Intensive Care Patients Undergoing Percutaneous Tracheostomy - Article abstract #950128

Amaç: Gebelikle ilişkili anatomik, fizyolojik ve immünolojik değişiklikler nedeniyle gebeler koronavirüs hastalığı-2019’a (COVİD-19) bağlı morbidite ve mortalite açısından risk altındaki popülasyonlardan biridir. Yoğun bakımda takip edilen gebe ve lohusa kadınların durumları ile ilgili yeterli çalışma bulunmamaktadır. Bu çalışmanın amacı, toplumda alfa varyasyonundan delta varyasyonuna geçiş sırasında yoğun bakım ünitesinde izlenen hamile ve lohusa kadınlarda varyant durumu, aşı durumu ve mortalite arasında bir bağlantı olup olmadığını görmekti. Gereç ve Yöntem: Çalışma 1 Ağustos 2021 ile 1 Şubat 2022 tarihleri arasında gerçekleştirilen 6 aylık prospektif gözlemsel bir çalışma olarak tasarlandı. Yaş, mevcut komorbiditeler, aşılanma durumu, gravida, parite, gebelik haftası (hamileler için), varyant durumu, doğum şekli (sezaryen veya normal doğum) ve yoğun bakım ünitesindeki COVİD-19 tıbbi tedavilerinin tümü kaydedildi. Bulgular: Gözlem süresi boyunca, çalışmaya kırk hasta alındı. Hastaların yaş ortalaması 30,9±5,2 idi. Gebe hastaların medyan gebelik haftası 32 hafta 2 gündü. Hastaların 30’unda eşlik eden hastalık bulunmazken, ikisinde gestasyonel diyabet, dördünde hipotiroidi, üçünde kronik hipertansiyon ve birinde Wilson hastalığı vardı. Hastaların %37,5’inde entübasyon gerekti. Yoğun bakımda yapılan takipte on hasta hayatını kaybetti. Yoğun bakım yatış süresi burada ortalama 12,1±11,8 gün olarak tespit edildi. Alfa varyantı olan 36 hastanın 7’si (%19,4), delta varyantı olan 4 hastanın 3’ü (%75) mortaliteyle sonuçlandı ve aradaki fark istatistiksel olarak anlamlıydı (p=0,042). Sonuç: Yoğun bakım ünitesine kabul edilen gebe popülasyonda delta varyantı daha yüksek bir ölüm oranı ile ilişkilendirilmiştir. Araştırmamızda yoğun bakım ünitesine kabul edilen gebelerde aşılanma oranının oldukça düşük olduğunu tespit ettik.

Background/Objectives: Polypharmacy in intensive care units (ICUs) substantially increases the risk of potential drug–drug interactions (pDDIs), which may lead to adverse drug events and worsen clinical outcomes. Conventional rule-based clinical decision support systems (CDSSs), although widely used, are limited by static logic and restricted contextual reasoning. Recently, large language models (LLMs) such as ChatGPT have emerged as potential adjunctive tools capable of generating clinically interpretable outputs; however, their diagnostic reliability in safety-critical settings remains unclear. Methods: This cross-sectional study aimed to evaluate the diagnostic performance of ChatGPT-5 in detecting clinically significant pDDIs in ICU patients, using the UpToDate Drug Interaction Checker as the reference comparator. Data were collected from 101 adult ICU patients on a predefined index date. The model referred to as “ChatGPT-5” corresponds to the version available via the OpenAI API in September 2025. A standardized prompt was applied for each patient to ensure consistency. Diagnostic performance metrics, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), overall accuracy, and Cohen’s κ coefficient, were calculated. Results: ChatGPT-5 identified a higher number of pDDIs per patient compared with UpToDate (median [IQR]: 6 vs. 0 [0–2]). The mean number of pDDIs per patient was also higher for ChatGPT-5 (7.2 ± 4.1) compared with UpToDate (1.1 ± 1.8). The diagnostic performance analysis was conducted at the patient level. Of the 101 included patients, 17 without a category D or X interaction in the UpToDate reference assessment were excluded from this analysis, leaving 84 patients. Sensitivity, specificity, and overall accuracy were 69.8%, 52.4%, and 65.5%, respectively, with a positive predictive value of 81.5% and negative predictive value of 36.7%. In a conservative full-cohort scenario analysis, treating the 17 excluded patients as discordant cases reduced overall exact agreement from 65.5% (55/84) to 54.5% (55/101). Agreement between the two systems was poor (κ = 0.19), indicating considerable variability in classification. Conclusion: Although ChatGPT-5 demonstrated limited diagnostic performance and the ability to generate clinically interpretable explanations, its low specificity and limited agreement with a rule-based system highlight important safety concerns. These findings suggest that LLMs may serve as complementary tools rather than standalone solutions in ICU pharmacovigilance. Further multicenter validation studies are required before clinical integration.

Background: Intensive care medicine holds a significant place within the specialty of anesthesiology and reanimation. Medical specialization theses prepared in this field offer valuable academic outputs that reflect the changes in clinical practice and academic orientations over time. However, studies that comprehensively examine intensive care-themed anesthesiology and reanimation specialization theses in Turkey are limited. This study aims to evaluate the temporal, thematic, and structural characteristics of these theses. Material and Methods: This retrospective, cross-sectional, and bibliometric study includes anesthesiology and reanimation specialization theses with an "intensive care" theme, registered in the National Thesis Center of the Council of Higher Education (YÖKTEZ) database between 1984 and 2025. The theses were analyzed in terms of year of preparation, number of pages, advisor’s academic title, accessibility status, geographical distribution, research method, and thematic focus. The data were evaluated using descriptive statistics and appropriate comparative tests. Results: A total of 464 theses were included in the study. The majority of the theses were prepared during the 2016–2025 period, and a significant increase in the average number of thesis pages over time was observed (p < 0.001). The rate of open-access theses has markedly increased in recent years (p < 0.001). In terms of topic distribution, temporal differences were noted in the areas of sedation/delirium and organization/COVID-19. Conclusion: In Turkey, intensive care-themed specialization theses reflect an increase in academic output and evolving clinical priorities over time. This study provides a guiding framework for future thesis planning and research in the field.