Yazar "Komut, S" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • [ X ]
    Öğe
    Artificial intelligence as author: Can scientific reviewers recognize GPT-4o-generated manuscripts?
    (W B SAUNDERS CO-ELSEVIER INC, 2025) Öztürk, A; Karahan, AT; Günay, S; Erdal, AS; Komut, S; Komut, E; Yiğit, Y
    Introduction: Chat Generative Pre-Trained Transformer (ChatGPT) is a natural language processing model. It can be argued that ChatGPT has recently begun to assume the role of a technological assistant capable of supporting academics in the process of scientific writing. ChatGPT may contribute to the spread of incorrect or incomplete information within academic literature, leading to conceptual confusion and potential academic misconduct. The aim of this study is to determine whether a scientific article entirely generated by an AI application such as ChatGPT can be detected by an academic journal editor or peer reviewer. Methods: This study was conducted between November 1, 2024, and December 1, 2024. GPT-4o, was utilized in this study. ChatGPT was instructed to write a scientific article focused on predicting mortality and return of spontaneous circulation (ROSC) in OHCA cases. The manuscript written by ChatGPT-4o was sent to 14 different reviewers who had previously served as reviewers or editors. The reviewers were asked to evaluate the manuscript as if they were an SCI-E journal editor or peer reviewer. The reviewers were informed that the article had been written by ChatGPT and were asked whether they had identified this during their review. Results: Among the reviewers, 42.9 % (n = 6) decided to reject the manuscript at the editorial stage, whereas another 42.9% (n = 6) opted to forward it to a peer reviewer. During the peer review stage, 42.9 % (n = 6) of the reviewers recommended rejection, while 28.6 % (n = 4) suggested major revisions. 78.6 % (n = 11) of the reviewers did not realize that the manuscript had been generated by an artificial intelligence model. Conclusion: The findings of our study highlight the necessity for journal editors and peer reviewers to be wellinformed about ChatGPT and to develop systems capable of identifying whether a manuscript has been written by a human or generated by artificial intelligence. (c) 2025 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).
  • [ X ]
    Öğe
    Comparing DeepSeek and GPT-4o in ECG interpretation: Is AI improving over time?
    (MOSBY-ELSEVIER, 2026) Günay, S; Öztürk, A; Karahan, AT; Barındık, M; Komut, S; Yiğit, Y
    Background: DeepSeek is a recently launched large language model (LLM), whereas GPT-4o is an advanced ChatGPT version whose electrocardiography (ECG) interpretation capabilities have been previously studied. However, DeepSeek's performance in this domain remains unexplored. Objectives: This study aims to evaluate DeepSeek's accuracy in ECG interpretation and compare it with GPT-4o, emergency medicine specialists, and cardiologists. A secondary aim is to assess any performance changes in GPT-4o over one year. Methods: Between February 9 and March 1, 2025, 40 ECG images (20 daily routine, 20 more challenging) from the book 150 ECG Cases were evaluated by both GPT-4o and DeepSeek, each model tested 13 times. The accuracy of their responses was compared with previously collected answers from 12 cardiologists and 12 emergency medicine specialists. GPT-4o's 2025 performance was compared to its 2024 results on identical ECGs. Results: GPT-4o outperformed DeepSeek with higher median correct answers on daily routine (14 vs. 12), more challenging (13 vs. 10), and total ECGs (27 vs. 22) with statistically significant differences (p=0.048, p<0.001, p<0.001). A moderate agreement was observed between the responses provided by GPT-4o (p<0.001, Fleiss Kappa=0.473), while a substantial agreement was observed in the responses provided by DeepSeek (p<0.001, Fleiss Kappa=0.712). No significant year-over-year improvement was observed in GPT-4o's performance. Conclusion: This first evaluation of DeepSeek in ECG interpretation reveals its performance is lower than that of GPT-4o and human experts. While GPT-4o demonstrates greater accuracy, both models fall short of expert-level performance, underscoring the need for caution and further validation before clinical integration.
  • [ X ]
    Öğe
    Comparison of Siemens Rapidlab 1200 blood gas analyzers and Beckman Coulter AU680 laboratory auto analyzers for sodium, potassium, hemoglobin and hematocrit parameters in emergency departments patients
    (TAYLOR & FRANCIS LTD, 2025) Günay, S; Öztürk, A; Pakkan, AT; Karahan, AT; Tekeli, Hİ; Özbek, E; Yılmaz, M; Komut, S; Yiğit, Y
    Blood gas analyzers (BGAs) offer rapid results and operational convenience in emergency settings, whereas laboratory auto analyzers (LAAs) remain the reference standard despite slower processing. This study compared BGA and LAA measurements of sodium (Na), potassium (K), hemoglobin (Hb), and hematocrit (Hct). A secondary aim was to evaluate their agreement across acid-base subgroups and in cases of severe acidosis. This study included >= 18 years patients from January 1 to June 30, 2024. BGA and LAA results were compared overall and across acid-base subgroups. Patients with pH <7.20 were analyzed separately as the severe acidosis group. Bland-Altman analysis showed the following mean differences and 95% limits of agreement: Na, 1.36 +/- 2.33 mmol/L (-3.21 to 5.92); K, 0.221 +/- 0.197 mmol/L (-0.166 to 0.607); Hb, 0.531 +/- 0.649 g/dL (-0.742 to 1.804); and Hct, 1.68% +/- 2.60 (-3.42 to 6.78). At clinical decision thresholds, BGA demonstrated varying diagnostic performance with sensitivities and specificities of 56.9% and 95.8% for hyponatremia, 67.5% and 98.7% for hypernatremia, 95.4% and 95.6% for hypokalemia, 48.7% and 99.8% for hyperkalemia, and 73.4% and 99.9% for transfusion decisions, respectively. In patients with severe acidosis, correlations remained strong, though agreement limits were notably wider. BGA-derived K values showed acceptable agreement with LAA and may be used interchangeably. Hb and Hct did not meet agreement criteria, while Na may be acceptable with clinical correlation. In severe acidosis, none of the parameters achieved acceptable agreement, indicating that BGA results should be interpreted with caution in this subgroup.
  • [ X ]
    Öğe
    Diagnostic accuracy and potential triage utility of the Shetty test in foot and ankle trauma: a cross-sectional study
    (Tubitak Scientific & Technological Research Council Turkey, 2025) Doğan, B; Komut, S; Komut, E; Kavak, N; Güneş, O; Karahan, AT
    Background/aim: Foot and ankle trauma represents a common reason for emergency department visits. While the majority of cases involve soft tissue injuries, radiographic imaging is frequently overutilized due to concerns about missed fractures, leading to increased costs and emergency department crowding. The Shetty test, a recently introduced clinical decision rule, may serve as a simpler alternative to established tools such as the Ottawa ankle rules. This study aimed to assess the diagnostic accuracy of the Shetty test and its potential role as a supportive tool within existing triage systems for patients presenting with foot and ankle trauma. Materials and methods: In this cross-sectional study, 229 adult patients with isolated foot or ankle trauma were evaluated in the emergency department. All participants underwent the Shetty test and standard radiographic imaging. The Shetty test was performed by trained emergency physicians prior to imaging; a positive result was defined as an inability to apply downward pressure due to pain. Diagnostic accuracy metrics-including sensitivity, specificity, positive predictive value, and negative predictive value-were calculated using radiographic findings as the reference standard. Results: Fractures were identified in 25.3% of cases. The Shetty test demonstrated a sensitivity of 77.6%, specificity of 60.8%, positive predictive value of 40.2%, and a high negative predictive value of 88.9%. Among patients with confirmed fractures, 77.6% had a positive test result. The test performed best in ruling out displaced and incomplete fractures, and results showed significant correlation with both physical findings and imaging outcomes. Conclusion: The Shetty test exhibited moderate sensitivity and specificity, alongside a high negative predictive value, supporting its use as a reliable rule-out tool for foot and ankle fractures. Its simplicity, ease of application, and diagnostic potential make it a promising triage adjunct to optimize emergency department resource use. Prospective multicenter validation is warranted before broad clinical adoption.