Assessing the Performance of ChatGPT on Dentistry Specialization Exam Questions: A Comparative Study with DUS Examinees DOI Open Access
Mustafa Temiz, Ceylan Güzel

Medical Records, Journal Year: 2024, Volume and Issue: 7(1), P. 162 - 166

Published: Dec. 19, 2024

Aim: This study aims to evaluate the performance of ChatGPT-4.0 model in answering questions from Turkish Dentistry Specialization Exam (DUS), comparing it with DUS examinees and exploring model’s clinical reasoning capabilities its potential educational value dental training. The objective is identify strengths limitations ChatGPT when tasked responding typically presented this critical examination for professionals. Material Method: analyzed years 2012 2017, focusing on basic medical sciences sections. ChatGPT's responses these were compared average scores examinees, who had previously taken exam. A statistical analysis was performed assess significance differences between human examinees. Results: significantly outperformed both sections across all analyzed. revealed that statistically significant, demonstrating superior accuracy years. Conclusion: ChatGPT’s demonstrates as a supplementary tool education exam preparation. However, future research should focus integrating AI into practical training, particularly assessing real-world applicability. replicating hands-on decision-making unpredictable environments must also be considered.

Language: Английский

Evaluating AI performance in nephrology triage and subspecialty referrals DOI Creative Commons

Priscilla Koirala,

Charat Thongprayoon,

Jing Miao

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Jan. 27, 2025

Language: Английский

Citations

1
Facilitators and barriers to AI adoption in nursing practice: a qualitative study of registered nurses' perspectives DOI Creative Commons
Osama Mohamed Elsayed Ramadan, Majed Mowanes Alruwaili, Abeer Nuwayfi Alruwaili

et al.

BMC Nursing, Journal Year: 2024, Volume and Issue: 23(1)

Published: Dec. 18, 2024

Integrating Artificial Intelligence (AI) in nursing practice is revolutionising healthcare by enhancing clinical decision-making and patient care. However, the adoption of AI registered nurses, especially varied settings such as Saudi Arabia, remains underexplored. Understanding facilitators barriers from perspective frontline nurses crucial for successful implementation. This study aimed to explore nurses' perspectives on Arabia propose an extended Technology Acceptance Model Nursing (TAM-AIN). A qualitative utilising focus group discussions was conducted with 48 four major facilities Al-Kharj, Arabia. Thematic analysis, guided framework, employed analyse data. Key included perceived benefits care (85%), strong organisational support (70%), comprehensive training programs (75%). Primary involved technical challenges (60%), ethical concerns regarding privacy (55%), fears job displacement (45%). These findings led development TAM-AIN, model that incorporates additional constructs alignment, readiness, threats professional autonomy. requires a holistic approach addresses technical, educational, ethical, challenges. The proposed TAM-AIN offers framework optimising integration into practice, emphasising importance nurse-centred implementation strategies. provides institutions policymakers robust tool facilitate enhance outcomes.

Language: Английский

Citations

5
Ai-driven triage in emergency departments: A review of benefits, challenges, and future directions DOI Creative Commons

Adebayo DaCosta,

Jennifer Teke,

Joseph E Origbo

et al.

International Journal of Medical Informatics, Journal Year: 2025, Volume and Issue: 197, P. 105838 - 105838

Published: Feb. 15, 2025

Language: Английский

Citations

0
The Application of AI in Clinical Nursing, Yields Several Advantageous Outcomes DOI
Habib Ahmed,

Naeema Akber,

Mohammad Saleem

et al.

Indus journal of bioscience research., Journal Year: 2025, Volume and Issue: 3(2), P. 591 - 599

Published: March 6, 2025

AI applications in nursing practice deliver transformative improvements for patient care while reducing workflow disruptions and serving healthcare workers better. This research explores how helps professionals through clinical decision systems as well observation workload optimization mental health resource delivery. Through their integration of support tools predictive analytics along with automation technologies experience better efficiency together lower administrative burdens improved safety. The use delivers individualized to nurses that enable them protect themselves from burnout stress. adoption technology faces crucial ethical obstacles include privacy risks related information systemic bias within algorithms social repercussions deployment. complete benefits depend on an equilibrium between technological progress patient-focused approaches. future success depends the education into curricula preparation AI-driven environments. demonstrates enables transformation but calls monitoring practices continuous assessment produce fair effective deployment outcomes.

Language: Английский

Citations

0
TQCPat: Tree Quantum Circuit Pattern-based Feature Engineering Model for Automated Arrhythmia Detection using PPG Signals DOI Creative Commons
Mehmet Ali Gelen, Türker Tuncer, Mehmet Bayğın

et al.

Journal of Medical Systems, Journal Year: 2025, Volume and Issue: 49(1)

Published: March 24, 2025

Abstract Background and Purpose Arrhythmia, which presents with irregular and/or fast/slow heartbeats, is associated morbidity mortality risks. Photoplethysmography (PPG) provides information on volume changes of blood flow can be used to diagnose arrhythmia. In this work, we have proposed a novel, accurate, self-organized feature engineering model for arrhythmia detection using simple, cost-effective PPG signals. Method We drawn inspiration from quantum circuits employed quantum-inspired extraction function /named the Tree Quantum Circuit Pattern (TQCPat). The system consists four main stages: (i) multilevel discrete wavelet transform (MDWT) TQCPat, (ii) selection Chi-squared (Chi2) neighborhood component analysis (NCA), (iii) classification k-nearest neighbors (kNN) support vector machine (SVM) (iv) fusion. Results Our TQCPat-based has yielded accuracy 91.30% 46,827 signals in classifying six classes ten-fold cross-validation. Conclusion results show that accurate tested large database more classes.

Language: Английский

Citations

0
PIE-Med: Predicting, Interpreting and Explaining Medical Recommendations DOI
A. Romano, Gary E. Riccio, Marco Postiglione

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 6 - 12

Published: Jan. 1, 2025

Language: Английский

Citations

0
Neonatal nurses’ experiences with generative AI in clinical decision-making: a qualitative exploration in high-risk nicus DOI Creative Commons
Abeer Nuwayfi Alruwaili, Afrah Madyan Alshammari,

Ali Alhaiti

et al.

BMC Nursing, Journal Year: 2025, Volume and Issue: 24(1)

Published: April 7, 2025

Neonatal nurses in high-risk Intensive Care Units (NICUs) navigate complex, time-sensitive clinical decisions where accuracy and judgment are critical. Generative artificial intelligence (AI) has emerged as a supportive tool, yet its integration raises concerns about impact on nurses' decision-making, professional autonomy, organizational workflows. This study explored how neonatal experience integrate generative AI examining influence nursing practice, dynamics, cultural adaptation Saudi Arabian NICUs. An interpretive phenomenological approach, guided by Complexity Science, Normalization Process Theory, Tanner's Clinical Judgment Model, was employed. A purposive sample of 33 participated semi-structured interviews focus groups. Thematic analysis used to code interpret data, supported an inter-rater reliability 0.88. Simple frequency counts were included illustrate the prevalence themes but not quantitative measures. Trustworthiness ensured through reflexive journaling, peer debriefing, member checking. Five emerged: (1) Decision-Making, 93.9% reported that AI-enhanced required human validation; (2) Professional Practice Transformation, with 84.8% noting evolving role boundaries workflow changes; (3) Organizational Factors, 97.0% emphasized necessity infrastructure, training, policy integration; (4) Cultural Influences, 87.9% highlighting AI's alignment family-centered care; (5) Implementation Challenges, 90.9% identified technical barriers strategies. can support effectiveness depends structured reliable culturally sensitive implementation. These findings provide evidence-based insights for policymakers healthcare leaders ensure enhances expertise while maintaining safe, patient-centered care.

Language: Английский

Citations

0
AI-Driven Clinical Decision Support Enhancing Disease Diagnosis With Virtual Health Twin, Probabilistic Engine, Contextual Embedding DOI

K. Srinivasan,

Rahul Jadon,

Rajababu Budda

et al.

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 123 - 152

Published: April 8, 2025

Background information: Probabilistic diagnosis engines, contextual medical embedding, and virtual health twins are few illustrations of how AI developments become the rout towards precision diagnostic accuracy in real time. These address accuracy, semantic understanding, stable decision-making intricate contexts. Methods: For scaling up accommodation purposes, framework introduced SDCM for mapping symptoms to diagnoses, CME interpretation, PMDE probabilistic reasoning VHT customized patient profiles. Objectives: Develop an AI-based CDS enhancing real-time flexibility, personalized insights, understanding. Results: The realization with minimal energy consumption runtime flexibility was obtained 95%, 94.8%, latency 15 ms. Conclusion: integrated changes care patient's outcome by making it dependable, scalable, diagnostics.

Language: Английский

Citations

0
The Role of ChatGPT in osteoporosis management: a comparative analysis with clinical expertise DOI
Ömer Faruk Bucak, Çiğdem Çınar

Archives of Osteoporosis, Journal Year: 2025, Volume and Issue: 20(1)

Published: April 9, 2025

Language: Английский

Citations

0
Perceived acceptance, intention to use and actual use behavior of digital information technologies among nursing professionals in Shanghai: a cross-sectional study DOI Creative Commons
Hui Xie,

P. Zhang,

Wei Zhu

et al.

BMC Nursing, Journal Year: 2025, Volume and Issue: 24(1)

Published: April 16, 2025

Digital information technologies (DITs) can contribute to optimizing the quality and efficiency of healthcare delivery. However, profiles awareness use behavior DITs among Chinese nursing professionals remained limited. This study aimed investigate perceived acceptance, intention identify influencing factors in hospitals Shanghai. A total 1421 from 20 across Shanghai were selected as participants between August October 2021. After excluding missing values, 1395 included analyses. Using technology acceptance model, general was measured ease (PEU) usefulness (PU). Intention using two single 5-point Likert scales. Linear logistic regression models mediation analyses developed examine factors. All PU PEU items received affirmative responses (agree or strongly agree) over 50% participants. Of all participants, 1101 (78.9%) expressed DITs; 626 (44.9%) frequent users. Age, bachelor's degree, in-house training on DITs, school-based training, out-of-hospital associated with acceptance. Licensed practical nurse, deputy chief working years, significant predictors use. Vocational college diploma, tertiary level 1 2 hospitals, specialized mediated 42.6% (95%CI: 10.3% ~ 60.4%) effects DITs. suggests that although have positive strong they rarely their practice. Therefore, policies interventions should be enhance integration into professionals' daily

Language: Английский

Citations

0