Merve Eren Durmuş

Merve Eren Durmuş

Auto-generated profile, based on publicly available information

Merve Eren Durmuş

Antalya Eğitim ve Araştırma Hastanesi, Gastroenteroloji Kliniği, Antalya, Türkiye

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
30 September 2025 in Turkish Journal of Gastroenterology
Verified
Journal Article
Open access
GKGokhan Koker
Gokhan Koker
GGGizem Zorlu Gorgulugil
Gizem Zorlu Gorgulugil
MCMuhammed Ali Coşkuner
Muhammed Ali Coşkuner
MDMerve Eren Durmus
Merve Eren Durmus
Background/Aims: Colorectal polyps are precursor lesions of colorectal cancer, and their histopathological types are critical for deter mining malignant potential. Predicting polyp histopathological types may support early and appropriate clinical management. Machine learning (ML) algorithms based on accessible demographic, clinical, and lifestyle data can contribute to individualized screening strategies. Materials and Methods: This retrospective cross-sectional study included 491 individuals who underwent colonoscopy for the first time between 2022 and 2025 at University of Health Sciences, Antalya Training and Research Hospital. Demographic and clinical data were recorded, and dietary habits were assessed using the Food Frequency Questionnaire. Patients were classified into 3 groups according to histopathology: adenomatous polyp, hyperplastic polyp, and no polyp. Four ML algorithms—decision tree, random forest, support vector machines (SVMs), and extreme gradient boosting—were applied. Model performance was evaluated using accuracy, sensitivity, specific ity, kappa statistic, and McNemar’s test. Variable contributions were further analyzed with SHapley Additive exPlanations. Results: Accuracy ranged from 70.9% to 76.4%, with the highest performance from SVM (76.4%) and random forest (75.7%). Extreme gradient boosting showed lower overall accuracy (70.9%) but was the only model that identified hyperplastic polyps. The no polyp groupwas consistently predicted with high accuracy (sensitivity 85.6%-95.9%). Precision for adenomatous polyps was highest with SVM (71.4%). SHapley Additive exPlanations analysis highlighted frequent bulgur consumption (>2 times/week), red meat intake, age, and body mass index as major predictors. Conclusion: Machine learning algorithms can predict colorectal polyp histopathological types using routine demographic, clinical, and dietary data, enabling more personalized and effective screening beyond age-based protocols. Cite this article as: Koker G, Gorgulugil GZ, Coskuner MA, Durmus ME. Machine learning–based prediction of histopathological classification in colorectal polyps. Turk J Gastroenterol. 2025;36(10):700-707

9 January 2023 in Gastroenterology Nursing
Verified
Journal Article
Closed access
SÖSerkan Öcal
Serkan Öcal
MDMerve Eren Durmuş
Merve Eren Durmuş
IYİbRahim Şenel Yalçın
İbRahim Şenel Yalçın
AAAhmet Şükrü Alparslan
Ahmet Şükrü Alparslan
AÇAyhan Hilmi Çekin
Ayhan Hilmi Çekin
EDEmin Durmuş
Emin Durmuş

1 December 2020 in African Health Sciences
Verified
Journal Article
Open access
PDF file
MEMerve Eren
Merve Eren
FBFeyzi Bostan
Feyzi Bostan
Background: Hypoglycemia is a common, symptom seen in individuals. Hypoglycemia in the elderly is both under-recognized and misdiagnosed due to nonspesific hypoglycemic symptoms and accompanying comorbidities in this population. In diabetic individuals, hypoglycemia is most commonly caused by administering insulin or sulphonylureas and insulin secretagogues. Other drugs, such as antibiotics or beta-blockers, have been reported to reduce blood glucose to abnormally low levels. Hypoglycemia in non-diabetic patients is considered a rare event, and the possible reasons may be reactive hypoglycemia, insulin-secreting tumours and other malignancies, hypopituitarism, hypocortisolism, alcohol abuse, inappropriate insulin self-administration, malnutrition, renal failure and sepsis. Case: An 86- year- old male was admitted to the emergency department with hypoglycemia diagnosed with non-pancreatic neuroendocrine tumour (NET) on lung secreting insulin. No surgical intervention or chemotherapy was planned due to patients age and comorbidities so best supportive care was planned. We used prednisone for symptomatic treatment of hypoglycemia and the patient has been followed up periodically. In this period he had no hypoglycemic attack. Conclusion: For patients with hypoglycemia who are unable/decline to receive any further treatment, low dose glucocorticoid is a good choice to achieve normoglycemia. It seems to be more cost effective compared to other treatment options. Furthermore hospitalisation rates may decrease due to decreased hypogylcemic attacks.

1 February 2025 in Digestive and Liver Disease
Verified
Journal Article
Closed access
SÖSerkan Öcal
Serkan Öcal
MDMerve Eren Durmuş
Merve Eren Durmuş
AAAhmet Şükrü Alparslan
Ahmet Şükrü Alparslan
FGFaruk Güleç
Faruk Güleç

17 December 2022 in Journal of Gastrointestinal and Liver Diseases
Verified
Journal Article
Open access
PDF file
MDMerve Eren Durmuş
Merve Eren Durmuş
SÖSerkan Öcal
Serkan Öcal
ADAdil Duman
Adil Duman
RÖRuhsen Öcal
Ruhsen Öcal
GKGokhan Koker
Gokhan Koker

1 January 2026 in Diagnostic and Interventional Endoscopy
Verified
Journal Article
Open access
PDF file
MDMerve Eren Durmuş
Merve Eren Durmuş
GKGokhan Koker
Gokhan Koker
FBFatma Tuğçe Bayrak
Fatma Tuğçe Bayrak
EDEmin Durmuş
Emin Durmuş
MCMuhammed Ali Coşkuner
Muhammed Ali Coşkuner
SÖSerkan Öcal
Serkan Öcal
Objective: To determine the colonoscopic yield of computed tomography (CT)-detected bowel wall thickening and assess whether its location is associated with colonoscopic findings. Materials and Methods: This retrospective study screened 4,773 colonoscopy records from November 1, 2024, to August 31, 2025. Patients were included when bowel wall thickening detected on CT performed for another reason was the sole indication for colonoscopy and the colonoscopy was performed within 6 months. CT locations were classified as rectum, left colon, right colon, or terminal ileum. Diagnostic yield was defined as any abnormal colonoscopic finding. Agreement was assessed using Cohen’s kappa. Results: Seventy-seven patients were included; the median age was 60 years (IQR, 49–72), and 40 patients (51.9%) were female. Colonoscopy identified an abnormal finding in 50 patients (64.9%). Diagnostic yield was 75.0% for rectal, 69.2% for left colonic, 42.9% for right colonic, and 64.7% for terminal ileal thickening, without significant differences among locations (p=0.269). Findings differed according to CT location (p=0.042). Terminal ileal thickening was most frequently associated with inflammatory lesions, whereas rectal and left colonic thickening were more commonly associated with polyps larger than 5 mm. CT and colonoscopy identified the same region in 36 of 50 patients with abnormal findings (72.0%; κ=0.619; p