veysel emre çelik

Dr. veysel emre çelik

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
2 October 2025 in Healthcare
Verified
Journal Article
Open access
PDF file
VAVolkan Alparslan
Volkan Alparslan
SBSibel Balci
Sibel Balci
AGAyetullah Gök
Ayetullah Gök
CACan Aksu
Can Aksu
Alpaslan Burak İNNERAlpaslan Burak İNNER
Alpaslan Burak İNNER
AKAlparslan Kuş
Alparslan Kuş
Background: Hip fractures are common in the elderly and often require ICU admission post-surgery due to high ASA scores and comorbidities. Length of hospital stay after ICU is a crucial indicator affecting patient recovery, complication rates, and healthcare costs. This study aimed to develop and validate a machine learning-based model to predict the factors associated with extended hospital stay (>7 days from surgery to discharge) in hip fracture patients requiring postoperative ICU care. The findings could help clinicians optimize ICU bed utilization and improve patient management strategies. Methods: In this retrospective single-centre cohort study conducted in a tertiary ICU in Turkey (2017–2024), 366 ICU-admitted hip fracture patients were analysed. Conventional statistical analyses were performed using SPSS 29, including Mann–Whitney U and chi-squared tests. To identify independent predictors associated with extended hospital stay, Least Absolute Shrinkage and Selection Operator (LASSO) regression was applied for variable selection, followed by multivariate binary logistic regression analysis. In addition, machine learning models (binary logistic regression, random forest (RF), extreme gradient boosting (XGBoost) and decision tree (DT)) were trained to predict the likelihood of extended hospital stay, defined as the total number of days from the date of surgery until hospital discharge, including both ICU and subsequent ward stay. Model performance was evaluated using AUROC, F1 score, accuracy, precision, recall, and Brier score. SHAP (SHapley Additive exPlanations) values were used to interpret feature contributions in the XGBoost model. Results: The XGBoost model showed the best performance, except for precision. The XGBoost model gave an AUROC of 0.80, precision of 0.67, recall of 0.92, F1 score of 0.78, accuracy of 0.71 and Brier score of 0.18. According to SHAP analysis, time from fracture to surgery, hypoalbuminaemia and ASA score were the variables that most affected the length of stay of hospitalisation. Conclusions: The developed machine learning model successfully classified hip fracture patients into short and extended hospital stay groups following postoperative intensive care. This classification model has the potential to aid in patient flow management, resource allocation, and clinical decision support. External validation will further strengthen its applicability across different settings.
1

28 October 2026 in Journal of Orthopedics Research and Rehabilitation
Verified
Journal Article
Open access
PDF file
VÇveysel emre çelik
veysel emre çelik
FÖFerhat Öktem
Ferhat Öktem
MKMümin Karahan
Mümin Karahan
BKBerkay Kırçal
Berkay Kırçal
ATAhmet Furkan Taşkın
Ahmet Furkan Taşkın
HOHüseyin Olgun
Hüseyin Olgun
Aims: To compare ChatGPT-5.2 and DeepSeek-V3.2 responses to frequently asked patient questions about hallux valgus surgery in terms of accuracy, informativeness, comprehensibility, and currency. Methods: A Google search performed with a newly created account without previous search activity was used to identify patient-oriented questions about hallux valgus surgery. Two researchers reviewed 100 questions and consolidated overlapping items into 10 representative questions. On February 1, 2026, the same questions were submitted in English to ChatGPT-5.2 and DeepSeek-V3.2. The first response from each model was recorded without editing. Ten orthopedic specialists with at least five years of professional experience independently and blindly rated each response on a 5-point Likert scale for accuracy, informativeness, comprehensibility, and currency. Paired model scores were compared using the Wilcoxon signed-rank test. Results: Both models answered all 10 questions. ChatGPT-5.2 had numerically higher mean scores for accuracy (4.7±0.3 vs 4.6±0.4; p=0.214), informativeness (4.6±0.4 vs 4.4±0.5; p=0.081), comprehensibility (4.6±0.4 vs 4.5±0.4; p=0.197), and currency (4.5±0.4 vs 4.3±0.5; p=0.064). None of the between-model differences reached statistical significance. Conclusion: ChatGPT-5.2 and DeepSeek-V3.2 both generated responses that orthopedic specialists rated highly across the four evaluated domains. Neither model demonstrated statistically significant superiority. These systems may support patient education as supplementary information tools, but their outputs should remain subject to clinical verification and should not replace individualized patient-physician communication.

Verified
Journal Article
Open access
PDF file
VÇveysel emre çelik
veysel emre çelik
Ümit GökÜmit Gök
Ümit Gök
BIBeyzanur Işık
Beyzanur Işık
ADAyşe Topçu Dursun
Ayşe Topçu Dursun
MAMehmet murat Arslan
Mehmet murat Arslan
KGKadir Emre Güngör
Kadir Emre Güngör
Background/Objectives: Intractable plantar keratosis may remain symptomatic despite conservative care, and comparative data on local excision techniques are scarce. This study retrospectively evaluated total elliptical excision and core excision, two surgical methods used in patients whose symptoms persisted despite conservative treatment. Methods: The records of 80 adult patients with histopathologically confirmed plantar keratosis who were treated surgically at a single center between April 2023 and August 2025 were reviewed. All patients had received conservative treatment before surgery. The primary outcome was symptomatic keratosis that reappeared at the operative site, was confirmed clinically, and required reoperation. Pain at the last visit, rated on a visual analog scale (VAS), served as the secondary outcome. The groups were compared with respect to patient characteristics, reoperation for recurrence, and final pain scores. Results: Reoperation for symptomatic recurrence was performed in 17 patients (21.3%): 3 of 37 (8.1%) in the total elliptical excision group and 14 of 43 (32.6%) in the core excision group (p = 0.012). Final VAS scores were 1.3 ± 0.8 and 1.5 ± 0.9, respectively, with no statistically significant difference (p = 0.41). Mean follow-up was 17.7 ± 9.6 and 18.4 ± 8.6 months (p = 0.638). Conclusions: In this retrospective cohort, symptomatic recurrence requiring reoperation occurred less often after total elliptical excision than after core excision. However, the non-randomized choice of technique, baseline differences between the groups, and differing postoperative protocols preclude firm conclusions about the independent superiority of either technique.