Güncel Gönderiler

• Yükleniyor...

  Öğe Türü: Öğe ,

  Dietitians' Views on Artificial Intelligence: An In-Depth Study

  (İstanbul Gelişim Üniversitesi Yayınları / Istanbul Gelisim University Press, 2026) Güner, Elif; Yuca, Kübra; Öztürk, Emel; Balcıoğlu, Berfin; Küçükçakan, Zeynep İrem

  Daha fazla

  Aim: Today, the use of artificial intelligence technologies is becoming increasingly common in many areas from health services to nutrition planning. The aim of this study is to explore dietitians' perceptions, experiences, and professional perspectives on the role of artificial intelligence in the field of nutrition. Method: In this qualitative study, online in-depth interviews were conducted with 29 dietitians working in different sectors between March 27 and April 28, 2025. In the interviews lasting 15-20 minutes, a semistructured topic guide consisting of 10 questions was used. Transcripts were analyzed using the thematic analysis method. Results: Dietitians' statements were evaluated under the themes of (1) professional transformation and the role of artificial intelligence, (2) ethics, trust and professional responsibility, (3) professional competence, education and adaptation, (4) Scientific validity, reliability and personalization. Dietitians evaluated artificial intelligence as a helpful tool that saves time and facilitates routine tasks, but emphasized that human interaction, empathetic communication, and ethical responsibility cannot be replaced by technology. Although it is thought that artificial intelligence will lead to a radical change in the field of nutrition, there are concerns about issues such as patient privacy, ethical values, and lack of scientific evidence. Conclusion: To our knowledge, this is the first study in Türkiye to explore dietitians’ perspectives on artificial intelligence in nutrition. This study shows that artificial intelligence presents both risks and opportunities in the dietitian profession, and draws attention to the fact that professionals should be equipped in terms of knowledge, ethics and digital competence in this transformation process.

  Daha fazla
• Yükleniyor...

  Öğe Türü: Öğe ,

  Clinical Decision Support via ChatGPT: An Evidence-Based Perspective in Pediatric Occupational Therapy

  (İstanbul Gelişim Üniversitesi Yayınları / Istanbul Gelisim University Press, 2026) Sırma, Gamze Çağla; Eraslan, İbrahim; Bahadır, Zeynep

  Daha fazla

  Aim: This study aims to evaluate the accuracy of ChatGPT’s responses to clinical questions related to Cerebral Palsy (CP) and Autism Spectrum Disorder (ASD) in the field of occupational therapy, as well as the reliability of the references it provides. Method: Ten clinical questions were formulated, and answers were prepared based on clinical guidelines and reviewed by two expert clinicians. The same questions were presented to ChatGPT, and its responses and references were rated by two independent evaluators using a four-point Likert scale. Weighted Kappa Coefficients were calculated to assess inter-rater agreement. Results: ChatGPT’s responses demonstrated high accuracy, with strong inter-rater agreement (Weighted Kappa: 0.72–0.75). However, significant deficiencies were identified in reference reliability, with moderate to high inter-rater agreement (Weighted Kappa: 0.75–0.78). Additionally, fictitious reference rates ranged from 40% to 100% for CP-related questions and from 25% to 100% for ASD-related questions. Conclusion: While ChatGPT shows potential as a clinical decision support tool in occupational therapy, the limitations in reference accuracy restrict its reliability in healthcare applications. Future studies should focus on improving artificial intelligence models’ reference accuracy to enhance their applicability in healthcare settings.

  Daha fazla
• Yükleniyor...

  Öğe Türü: Öğe ,

  Can Artificial Intelligence Reliably Detect Risky Eating Narratives? A Comparative Analysis of YouTube Extreme Diet Videos

  (İstanbul Gelişim Üniversitesi Yayınları / Istanbul Gelisim University Press, 2026) Başören, İrem; Aksoy, Hilal; Korkmaz, Abdullah Furkan; Çelik, Zehra Margot

  Daha fazla

  Aim: This descriptive study was conducted to identify characteristics that are related to binge eating in YouTube videos that have been shared with the keywords “extreme diet” and “diet challenge” and to compare classifications made by expert dietitians with those generated by an artificial intelligence model. Method: A total of 49 YouTube videos that met the inclusion criteria were analyzed. The video characteristics were evaluated in relation to the view count, number of likes and comments, video duration, and time elapsed since upload. The quality of information provided in the video was assessed using the Modified DISCERN instrument, JAMA Benchmark Criteria, and Global Quality Score (GQS). A studyspecific Binge Eating–Related Scoring System (BERS), consisting of 15 dichotomous items and based on video transcripts, was independently applied by both expert dietitians and the Gemini 3 Pro artificial intelligence model. In addition, 89,240 user comments were analyzed using R-based sentiment and emotion analysis techniques. Google Trends data for 2021–2026 were also evaluated. Statistical analyses were performed using SPSS 22.0. Results: The median number of views was 2,043,167 (IQR: 1,043,285–5,550,269). AI-based BERS scores showed significant positive correlations with the number of views (r=0.471), likes (r=0.453), comments (r=0.423), and video length (r=0.543) (p<0.05). A moderate positive correlation was found between expertrated and AI-generated BERS scores (r=0.577, p<0.001). Higher binge eating–related scores were negatively correlated with educational quality scores (GQS). Sentiment analysis revealed that 41.3% of comments were positive, and the most frequently identified emotions were trust and joy. Google Trends indicated a peak in “extreme diet” searches in 2026. Conclusion: Highly engaging YouTube content often not only normalizes extreme eating behaviors but is also received positively by viewers. AI proved to be moderately reliable for identifying binge eating-related features, thus suggesting its potential as a scalable screening tool for monitoring harmful health trends. Interdisciplinary collaboration is required to ensure that AI-powered content analysis aligns with public health priorities.

  Daha fazla
• Yükleniyor...

  Öğe Türü: Öğe ,

  Predicting Mortality and the Need for Early Intubation in Intensive Care Patients Using Machine Learning: A Pilot Study

  (İstanbul Gelişim Üniversitesi Yayınları / Istanbul Gelisim University Press, 2026) Kılbasanlı, Seval; Çolak, Andaç Batur; Bozkurt Polat, Şerife Buket; Yüksel Turhan, Zeynep; Kaçmaz, Mustafa; Bulut, Seyyid Mehmet

  Daha fazla

  Aim: This pilot study aimed to assess the feasibility and preliminary performance of machine learning models for predicting ICU mortality and the need for intubation within 48 hours using routinely collected admission data. Method: Ten adult intensive care patients were included in this single-center, retrospective observational pilot study. For ANN development, 13 prespecified clinical and laboratory features per patient were restructured in long format, yielding 130 feature-level records. These records represented feature entries derived from 10 patients rather than independent patient-level observations. Demographic characteristics, primary diagnosis, APACHE II and SOFA scores, arterial blood gas parameters, oxygenation indicators (FiO₂, PaO₂/FiO₂), and routine metabolic–biochemical variables were analyzed. ML-based classification models predicted ICU mortality and the need for intubation within the first 48 hours. Results: In the exploratory feature-level internal assessment, both the ICU mortality and early-intubation classifications yielded an AUC of 1.00, sensitivity of 100%, specificity of 100%, and an F1-score of 1.00. These estimates were derived from records originating from 10 patients and should be interpreted cautiously. Conclusion: This pilot study demonstrates the feasibility of applying machine learning methods to routinely collected ICU admission data. The findings are preliminary and hypothesis-generating and should not be interpreted as established clinical predictive performance. Validation in larger, independent, prospective, and multicenter cohorts is required.

  Daha fazla
• Yükleniyor...

  Öğe Türü: Öğe ,

  Boric Acid-Induced Apoptosis in Breast Cancer Subtypes: Comparative Gene Expression and Machine Learning Study

  (İstanbul Gelişim Üniversitesi Yayınları / Istanbul Gelisim University Press, 2026) Bozkurt Polat, Şerife Buket; Çolak, Andaç Batur; Bulut, Seyyid Mehmet

  Daha fazla

  Aim: Breast cancer is a diverse illness that arises from the interplay of outside factors and genetic predisposition. Recently, artificial intelligence approaches have enabled the systematic analysis of potential anticancer agents such as boric acid by modeling the functions of apoptotic regulators. This study proposes an artificial intelligence-based analytical approach to evaluate how boric acid (B) affects cell survival and cell death through apoptosis pathway modulation. Method: Viability of cells was determined by applying boric acid at various concentrations of 0.1, 1, 10, 50, 100, and 1000 ng/mL to cells at 24 h and 72 h using the cell viability test. Lastly, total RNA was isolated at 24 and 72 hours, and messenger RNA (mRNA) expression levels of specific genes were established by quantitative PCR (qPCR). An analysis was carried out using artificial intelligence based upon the Extreme Gradient Boosting (XGBoost) solution, a technique that enables the development of a pair of predictive models for cell viability and relative mRNA expression.Results: After 24- and 72-hour treatments, boric acid reduced cell viability in MCF-7 and MDA-MB-231 cells in a rate- and time-sensitive manner in relation to the unaffected category. The triple-negative breast cancer phenotype was shown to be more susceptible to apoptosis at both time periods, as evidenced by the increased lethal consequences of boric acid in MDA-MB-231 cells compared to MCF-7 cells. However, boric acid was found to induce both intrinsic and extrinsic apoptosis in both breast cancer cell lines. Specifically for internal apoptosis signaling, ENDOG, BAX, Caspase-9, and Caspase-3 mRNA expression increased, while BCL-2 mRNA expression decreased, and the BAX/BCL-2 ratio was determined to shift towards apoptosis. Furthermore, apoptotic effects were detected in MCF-7 cells at 24 and 72 hours into the experiment, with this effect being particularly higher in MDA-MB-231 cells at 24 hours. The results obtained showed that boric acid induced the extrinsic apoptosis pathway by increasing mRNA FAS, FASLG, and CASP8 mRNA expression levels at 72 hours in MCF-7 cells and at 24 hours in MDA-MB-231 cells. However, boric acid increased MYC expression in MDA-MB-231 cells at 24 hours, while this effect was observed in MCF-7 cells at 72 hours of the experiment. The optimized XGBoost models were insufficient and showed highly non-homogeneous Margin of Deviation (MoD) values, with cell viability in the range of ±100% and mRNA expression spanning -4000% to +2000%.Conclusions: The results obtained indicate that boric acid regulates cellular survival and death in breast cancer subtypes through MYC-dependent mechanisms and that this effect exhibits a more pronounced antitumor effect in MDA-MB-231 cells. So, it is concluded that boric acid may be a promising therapeutic agent for breast cancer if supported by additional research. Moreover, the inability of the current AI models also accentuates the complexity and non-linearity of the cellular response and suggests that the quantitative biological outcome can be better predicted with a broader multi-feature set.

  Daha fazla