This study aimed to evaluate the compliance with guidelines, clinical safety, and applicability of ChatGPT-5 responses in obstetric and gynecological emergency scenarios. With the increasing role of AI-powered large language models (LLMs) in healthcare, there is a need to examine their performance in obstetric emergencies systematically. This study was designed as a prospective, scenario-based, double-blind study. A total of 15 obstetric and gynecologic emergency scenarios were created based on the literature and current international guidelines (ACOG, RCOG, WHO). Five standard questions were posed to ChatGPT-5 for each scenario: (1) Most likely diagnosis, (2) Investigations to confirm the diagnosis, (3) Hemodynamic stability assessment, (4) Initial treatment approach, and (5) Advanced management options. The same scenarios were independently answered by two obstetricians, an emergency medicine specialist, and an anesthesiologist, and were considered the “gold standard.” Responses were scored for guideline compliance, patient safety, and critical information gaps. In addition, quality and understandability were evaluated with modified DISCERN (mDISCERN), Global Quality Score (GQS), and readability indexes [Flesch Reading Ease Score (FRES), Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook (SMOG), Coleman–Liau Index (CLI)]. A total of 75 responses were reviewed. High agreement (5/5) was observed in 5 scenarios (33.3%), moderate agreement (4/5) in 7 scenarios (46.7%), and low agreement (≤ 3/5) in 3 scenarios (20.0%). High agreement was particularly evident for well-defined guideline algorithms, such as postpartum hemorrhage, eclampsia, HELLP syndrome, shoulder dystocia, and ruptured ectopic pregnancy. Deficiencies in moderate agreement scenarios included insufficient emphasis on mortality risk, omission of scoring systems, incomplete steps in sepsis management, and inadequate specification of fertility-sparing approaches. Low agreement scenarios included severe vaginal hemorrhage, acute bleeding due to malignancy, and traumatic gynecologic emergencies. The mean mDISCERN score of the responses was 4.0 ± 0.7, and the mean GQS was 4.1 ± 0.7. Readability analyses showed that responses contained a moderate amount of technical language (FRES score = 40.5 ± 2.5; FKGL score = 11.6 ± 1.2; SMOG score = 10.9 ± 0.8; and CLI score = 10.9 ± 0.8). The mean lexical density was 0.63. ChatGPT-5 generally produced moderate to good guideline-compliant and confident responses in obstetric and gynecological emergency scenarios. However, its performance was limited in complex cases requiring a multidisciplinary approach. The findings suggest that AI-powered large language models can be a complementary tool in obstetric emergency management, but should not be used alone without expert clinician supervision. Larger, comparative, and multidisciplinary studies will provide more reliable evidence for the clinical integration of these technologies.

Large language models (LLMs) such as ChatGPT are increasingly explored for clinical decision support. However, their performance in high-stakes emergency scenarios remains underexamined. This study aimed to evaluate ChatGPT’s diagnostic and therapeutic accuracy compared to a board-certified emergency physician across diverse emergency cases. This comparative study was conducted using 15 standardized emergency scenarios sourced from validated academic platforms (Geeky Medics, Life in the Fast Lane, Emergency Medicine Cases). ChatGPT (GPT-4) and a physician independently evaluated each case based on five predefined parameters: diagnosis, investigations, initial treatment, clinical safety, and decision-making complexity. Cases were scored out of 5. Concordance was categorized as high (5/5), moderate (4/5), or low (≤ 3/5). Wilson confidence intervals (95%) were calculated for each concordance category. ChatGPT achieved high concordance (5/5) in 8 cases (53.3%, 95% CI: 27.6–77.0%), moderate concordance (4/5) in 4 cases (26.7%, CI: 10.3–55.4%), and low concordance (≤ 3/5) in 3 cases (20.0%, CI: 6.0–45.6%). Performance was strongest in structured, protocol-based conditions such as STEMI, DKA, and asthma. Lower performance was observed in complex scenarios like stroke, trauma with shock, and mixed acid-base disturbances. ChatGPT showed strong alignment with emergency physician decisions in structured scenarios but lacked reliability in complex cases. While AI may enhance decision-making and education, it cannot replace the clinical reasoning of human physicians. Its role is best framed as a supportive tool rather than a substitute.

Background: Patients in palliative care often experience prolonged hospital stays, requiring detailed documentation, complex symptom management, and multidisciplinary coordination. The emergence of AI tools, particularly GPT-based language models, offers new opportunities to support clinical workflows. Objective: To evaluate the practical utility of a GPT-based AI tool in supporting documentation, trend recognition, and clinical decision support in a real-world palliative care unit. Methods: This retrospective observational study included 25 patients admitted to a hospital-based palliative care unit during April 2025. The AI tool was used to assist with clinical documentation (daily notes and discharge summaries), drug monitoring, and recognition of clinical trends. Physicians entered patient data through a text-based interface, and the AI generated draft documentation, which was then reviewed and finalized by attending clinicians. All therapeutic suggestions were verified through specialist consultation. Results: AI assistance reduced documentation time significantly-from an average of 20.4 ± 5.6 min to 6.1 ± 1.8 min for discharge summaries. In eight patients, the AI flagged important trends, such as rising CRP levels, prompting earlier re-evaluation. The tool also provided medication suggestions in six cases, all confirmed by internal medicine specialists. Physicians reported reduced cognitive load and improved clarity in clinical records. Communication with families was enhanced using AI-generated educational summaries. Conclusion: GPT-based AI tools can improve documentation efficiency and clinical awareness in palliative care units. While not a replacement for physician judgment, they provide valuable support in managing complex, long-term patients when used under appropriate clinical supervision.

Objective: The aim of the study was to investigate the prevalence, characteristics, and consequences of workplace violence (WPV) in emergency care settings, including reporting behaviors. Methods: An online questionnaire was conducted among 660 emergency department (ED) healthcare workers (HCWs), covering types of violence, perpetrators, psychological impacts, and reporting behaviors. Results: A 97.4% of HCWs reported experiencing at least one violent incident. Verbal violence was the most prevalent (93.8%), followed by psychological pressure (59.1%) and physical violence (22.7%). Perpetrators were mainly patient companions (98.0%) and patients (60.3%). Nearly half (49.8%) had never reported violence. Consequences of the violence on HCWs included a loss of motivation (80.8%), anxiety (63.8%), and burnout (57.7%). About 85% associated violence with ED overcrowding. Conclusions: WPV in EDs remains a public health and workforce safety issue. System-level interventions are needed to enhance safety and deterrence, reduce overcrowding, improve reporting, and strengthen institutional support.

Aim: Especially in recent years, with the increase in the number of patients admitted to the emergency services the number of urological emergencies is increasing. Some of these require immediate attention. There are not enough studies on urological emergencies in our country. In this study, we aimed to investigate the demographic data of patients over the age of 18 who presented to the emergency department with non-traumatic urological emergency complaints. Materials and Methods: This study was designed based on a 6-month prospective, cross-sectional study. After obtaining the approval of the ethics committee, patients over the age of 18 with urological emergency complaints were examined between 06.11.2019 and 06.05.2020. Results: The ratio of urological emergencies to all patients was found to be 1.5%. 56.76% (n: 231) of the patients were male and 43.24% (n = 176) were female. In the study was found 44.7% of the patients to be urinary tract infection, 31.45% renal colic, 8.8% hematuria, 6.88% acute urinary retention. In our study, urology consultation was requested for 19% of urological emergency patients. Emergency intervention was applied to 21.13% of all urological emergency cases. Emergency operation was required for 1.47% of the patients. 10.81% of the patients required hospitalization. Conclusion: As a result, urological emergencies are common. Among these cases, there may be diseases that require urgent intervention or surgery. It is very important for the patients the emergency physicians who evaluate the patient first to make a careful and meticulous evaluation and to make a urology consultation if necessary.