Ertugrul Safran

Dr. Ertugrul Safran

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 April 2025 in BMC Musculoskeletal Disorders
Verified
Journal Article
Open access
PDF file
ESErtugrul Safran
Ertugrul Safran
SYSefa Yildirim
Sefa Yildirim
AI models like ChatGPT have the potential to support musculoskeletal rehabilitation by providing clinical insights. However, their alignment with evidence-based guidelines needs evaluation before integration into physiotherapy practice. To evaluate the performance of ChatGPT (GPT-4 model) in generating responses to musculoskeletal rehabilitation queries by comparing its recommendations with evidence-based clinical practice guidelines (CPGs). This study was designed as a cross-sectional observational study. Twenty questions covering disease information, assessment, and rehabilitation were developed by two experienced physiotherapists specializing in musculoskeletal disorders. The questions were distributed across three anatomical regions: upper extremity (7 questions), lower extremity (9 questions), and spine (4 questions). ChatGPT’s responses were obtained and evaluated independently by two raters using a 5-point Likert scale assessing relevance, accuracy, clarity, completeness, and consistency. Weighted kappa values were calculated to assess inter-rater agreement and consistency within each category. ChatGPT’s responses received the highest average score for clarity (4.85), followed by accuracy (4.62), relevance (4.50), and completeness (4.20). Consistency received the lowest score (3.85). The highest agreement (weighted kappa = 0.90) was observed in the disease information category, whereas rehabilitation displayed relatively lower agreement (weighted kappa = 0.56). Variability in consistency and moderate weighted kappa values in relevance and clarity highlighted areas requiring improvement. This study demonstrates ChatGPT’s potential in providing guideline-aligned information in musculoskeletal rehabilitation. However, due to observed limitations in consistency, completeness, and the ability to replicate nuanced clinical reasoning, its use should remain supplementary rather than as a primary decision-making tool. While it performed better in disease information, as evidenced by higher inter-rater agreement and scores, its performance in the rehabilitation category was comparatively lower, highlighting challenges in addressing complex, nuanced therapeutic interventions. This variability in consistency and domain-specific reasoning underscores the need for further refinement to ensure reliability in complex clinical scenarios. Not applicable.

15 September 2025 in Anatolian Current Medical Journal
Verified
Journal Article
Open access
ESErtugrul Safran
Ertugrul Safran
AÇADEM ÇALI
ADEM ÇALI
Aims: Large language models (LLMs) such as ChatGPT are increasingly used in academic and clinical writing. While these tools can generate coherent and domain-specific text, concerns persist regarding the accuracy of their automatically generated references. In musculoskeletal rehabilitation—a field heavily reliant on current evidence—the reliability of citations is especially critical. Yet, systematic evaluations of citation accuracy in AI-generated scientific content are lacking. To evaluate the reference accuracy of scientific texts generated by ChatGPT (GPT-4) in response to musculoskeletal rehabilitation prompts, and to determine whether reference accuracy improves following structured post-generation verification. Methods: ChatGPT was prompted to generate four scientific paragraphs on musculoskeletal rehabilitation topics (manual therapy, ACL reconstruction, low back pain, and rotator cuff repair), each including 10 references with DOIs. A total of 40 references were analyzed using a 3-point scoring system (0=fabricated, 1=partially correct, 2=fully accurate), which was used to assess citation quality. After initial evaluation, ChatGPT was asked to verify and revise its references. Scores before and after this step were compared descriptively and with Wilcoxon signed-rank tests to assess statistical significance, and effect sizes (r) were calculated to estimate the magnitude of improvement. Results: Only 7.5% of references were fully accurate in the initial generation, while 42.5% were completely fabricated. The remaining 50% were partially correct. After verification, the proportion of fully accurate references rose to 77.5%. Wilcoxon signed-rank testing confirmed a statistically significant improvement in accuracy across all prompts (W=561.0, p

1 November 2022 in Arquivos de Neuro-Psiquiatria
Verified
Journal Article
Open access
PDF file
ESErtugrul Safran
Ertugrul Safran
AOAysel Yildiz Ozer
Aysel Yildiz Ozer
HGHulya Nilgun Gurses
Hulya Nilgun Gurses
Background Neuromuscular diseases are acquired or inherited diseases that affect the function of the muscles in our body, including respiratory muscles. Objective We aimed to discover more cost-effective and practical tools to predict respiratory function status, which causes serious problems with patients with neuromuscular disease. Methods The Vignos and Brooke Upper Extremity Functional Scales were used to evaluate functional status for patient recruitment. The handgrip strength and dexterity of patients were measured using a dynamometer and nine-hole peg test. Respiratory function parameters: forced vital capacity, forced expiratory volume in one second, and peak expiratory flow were evaluated using spirometry. Results The mean age of the 30 patients was 11.5 ± 3.79 years old. Significant relationships were found between nine-hole-peg-test scores and respiratory function parameters on both sides. Significant correlations were found between both handgrip strength and respiratory function parameters (p < 0.05). In the linear regression analysis, it was seen that the forced expiratory volume in 1 second, and peak expiratory flow values could be explained in different percentages (p < 0.05). Conclusions Handgrip strength and dexterity measurements can be used as indicators for estimating respiratory function parameters in terms of cost and accessibility, although it is known that they will not replace respiratory function tests.

21 May 2025 in BMC Musculoskeletal Disorders
Verified
Journal Article
Open access
PDF file
ESErtugrul Safran
Ertugrul Safran
YKYaren Kaya
Yaren Kaya
Suboccipital myofascial release (MR) is widely used in manual therapy for addressing cervical dysfunction. However, its specific therapeutic effects remain unclear, especially when compared to sham interventions, raising questions about the roles of contextual and placebo influences. This study aimed to evaluate the immediate effects of suboccipital MR on pain pressure threshold(PPT), cervical range of motion (ROM), and proprioception, while considering the influence of non-specific effects such as placebo and contextual factors. A single-blind, sham-controlled randomized study was conducted with 30 asymptomatic participants (15 per group). The MR group received five minutes of suboccipital myofascial release, while the sham group received light touch without therapeutic pressure.Outcomes included PPT, cervical ROM (flexion, extension, and rotation), and proprioception, measured before and immediately after the intervention. A 2 × 2 mixed ANOVA was used to analyze group × time interaction and main effects. Paired t-tests were used as supportive within-group analyses. The MR group showed within-group improvements in PPT (e.g., left-side PPT increased from 7.31 ± 2.58 to 8.67 ± 1.98 kg/cm², p = 0.028), cervical ROM (e.g., flexion improved from 57.00 ± 9.05° to 64.00 ± 9.60°, p = 0.0004), and proprioception (e.g., flexion reposition error decreased from 5.77 ± 2.24° to 3.70 ± 2.40°, p = 0.006). However, no significant group × time interactions were observed for any outcome, suggesting similar changes in both MR and sham groups. Suboccipital MR produced significant within-group improvements in PPT, cervical ROM, and proprioception. However, the absence of significant differences between the MR and sham interventions suggests that non-specific or contextual factors may account for the observed effects. Further studies are needed in symptomatic populations with longer follow-up and objective outcome measures to determine the specific efficacy of MR. This study was retrospectively registered with ClinicalTrials.gov under the identifier NCT06761391 on January 5, 2025.

16 September 2025 in Journal of Health Sciences and Medicine
Verified
Journal Article
Open access
ESErtugrul Safran
Ertugrul Safran
YYYusuf Yaşasın
Yusuf Yaşasın
Aims: This study aimed to compare the clinical reasoning and treatment planning performance of three advanced large language models (LLMs)-ChatGPT-4o, Gemini 2.5 Pro, and DeepSeek-V3-in orthopedic rehabilitation. Their responses to standardized clinical scenarios were evaluated to determine alignment with evidence‑based physiotherapy practices, focusing on relevance, accuracy, completeness, applicability, and safety awareness. Methods: Three fictional but clinically realistic scenarios involving rotator cuff tendinopathy, lumbar disc herniation with radiculopathy, and anterior cruciate ligament (ACL) reconstruction were developed by an experienced physiotherapist. These scenarios were independently queried on the same day by three AI models using identical prompts. A blinded expert physiotherapist evaluated each model’s detailed responses using a 5-point Likert Scale across five domains: clinical accuracy, relevance, completeness, applicability, and safety awareness. Mean scores and descriptive statistics were calculated. Results: DeepSeek-V3 was consistently rated highest (5/5) across all domains and scenarios, demonstrating comprehensive and clinically rigorous plans. ChatGPT-4o showed strong performance overall, with total scores ranging from 19 to 20 out of 25, though it exhibited lower completeness scores due to less specific milestones. Gemini 2.5 Pro scored lower overall (average total score 18/25), with particular weaknesses in applicability and clinical relevance in complex cases such as lumbar disc herniation. All models provided evidence-based treatment approaches emphasizing pain management, postural correction, gradual strengthening, and return-to-activity progression. Differences arose in emphasis on lifestyle modification, patient education depth, and integration of psychosocial factors, with Gemini uniquely addressing psychological readiness in ACL rehabilitation. Conclusion: AI-generated rehabilitation plans show substantial concordance with current physiotherapy guidelines but vary in detail and clinical practicality. DeepSeek-V3 outperformed the other models in consistency and safety considerations, while ChatGPT-4o balanced clinical accuracy with moderate completeness. Gemini 2.5 Pro’s inclusion of biopsychosocial components offers valuable insights but may require further refinement for clinical applicability. These findings highlight the potential and current limitations of AI tools in orthopedic rehabilitation, suggesting careful model selection based on clinical context and user needs.

22 July 2026 in Healthcare
Verified
Journal Article
Open access
PDF file
Ömer ŞevginÖmer Şevgin
Ömer Şevgin
BYBetül Berat Yıldız
Betül Berat Yıldız
ESErtugrul Safran
Ertugrul Safran
Background: Work-related musculoskeletal disorders (WRMSDs) are highly prevalent among construction workers. Ergonomics training and exercise are both used for their management, but the incremental benefit of adding exercise to ergonomics training in this population is unclear. Our aim was to evaluate whether adding a supervised exercise programme to ergonomics training provides additional benefit over ergonomics training alone in construction workers with WRMSDs. Methods: In this single-centre, two-arm randomized controlled trial, 52 male construction workers with musculoskeletal complaints were allocated to an ergonomics training plus exercise group (n = 26) or an ergonomics training alone group (active comparator, n = 26) for 12 weeks. The primary outcome was pain intensity (Visual Analogue Scale—VAS); secondary outcomes were musculoskeletal symptom burden (Extended Nordic Musculoskeletal Questionnaire, NMQ-E), fatigue (Fatigue Severity Scale—FSS), sleep quality (Pittsburgh Sleep Quality Index—PSQI), and occupational burnout (Maslach Burnout Inventory—MBI). The pre-specified primary contrast was the baseline-adjusted between-group difference at 12 weeks (ANCOVA), with a responder analysis as a sensitivity check. Results: Both groups improved significantly from baseline in terms of pain, fatigue, sleep quality, and musculoskeletal symptom burden (all p < 0.001) and in personal accomplishment (p < 0.001); emotional exhaustion and depersonalization were unchanged in both arms. Baseline-adjusted between-group comparisons showed no statistically significant incremental effect of added exercise on pain (adjusted difference −0.34, 95% CI −0.99 to 0.32), fatigue, sleep, symptom burden, or any burnout dimension. The exercise arm showed numerically greater improvements in pain, fatigue, and symptom burden and a higher proportion achieving ≥30% pain relief (96% vs. 77%; odds ratio 7.5), but these differences did not reach statistical significance (p = 0.099). Conclusions: Over a period of 12 weeks, ergonomics training with or without added exercise was associated with significant improvements in musculoskeletal and related outcomes; however, adding exercise to ergonomics training produced no statistically significant incremental benefit. A non-significant trend toward greater pain response with added exercise warrants confirmation in larger, longer trials.