Merve Eren Durmuş

Giriş ve Amaç: Kolonoskopi başarısı, işlem öncesi kolon temizliğinin kalitesiyle yakından ilişkilidir. Yetersiz kolon temizliği mukozal görünürlüğü azaltarak tanısal doğruluğu olumsuz etkileyebilir. Bu çalışmada, başta ileri yaş olmak üzere klinik değişkenlerin Boston Barsak Hazırlığı Skalası ile değerlendirilen kolon temizliği kalitesiyle ilişkisini araştırmayı amaçladık. Gereç ve Yöntem: Bu tek merkezli, retrospektif çalışmaya 01.01.2025–30.06.2025 tarihleri arasında kolonoskopi yapılan erişkin hastalar dahil edildi. Kolon temizliği toplam Boston Barsak Hazırlığı Skalası skoru ile değerlendirildi. Boston Barsak Hazırlığı Skalası < 6 yetersiz kolon temizliği, Boston Barsak Hazırlığı Skalası ≥ 6 yeterli kolon temizliği olarak tanımlandı. Yaş, cinsiyet, vücut kitle indeksi, diyabetes mellitus varlığı ve Amerikan Anesteziyologlar Derneği Fiziksel Durum Sınıflaması > 1 değişkenleri değerlendirildi. Gruplar karşılaştırıldı; işlem karakteristiği eğrisi, korelasyon ve ikili lojistik regresyon analizleri yapıldı. Bulgular: Çalışmaya 2350 hasta dahil edildi. Hastaların 224’ünde (%9,5) yetersiz kolon temizliği saptandı. Yetersiz kolon temizliği grubunda yaş medyanı daha yüksekti (64 yıl vs. 59 yıl; p < 0,001). Diyabetes mellitus ve Amerikan Anesteziyologlar Derneği Fiziksel Durum Sınıflaması > 1 oranları da bu grupta anlamlı olarak daha fazlaydı. Yaş ile Boston Barsak Hazırlığı Skalası skoru arasında negatif korelasyon saptandı (r = -0,210; p < 0,001). İşlem karakteristiği eğrisi analizinde yaşın yetersiz kolon temizliğini ayırt etme performansı sınırlıydı (Eğri altında kalan alan: 0,606; p < 0,001). Çok değişkenli analizde ileri yaş, diyabetes mellitus varlığı ve Amerikan Anesteziyologlar Derneği Fiziksel Durum Sınıflaması > 1 yeterli kolon temizliği olasılığında azalma ile bağımsız olarak ilişkiliydi. Sonuç: İleri yaş, diyabetes mellitus varlığı ve artmış sistemik hastalık yükü, kolonoskopi öncesi yetersiz kolon temizliği ile ilişkili bulunmuştur. Bu değişkenler, riskli hastaların işlem öncesi belirlenmesinde pratik göstergeler olarak kullanılabilir.

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

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

Background and Aims: This study aimed to evaluate the awareness, perceptions of transmission routes, treatment history, and interaction with primary healthcare services among individuals infected with hepatitis C virus. Materails and Methods: A descriptive cross-sectional study was conducted in 2023 at a tertiary center in the Western Mediterranean region of Turkey. A total of 359 anti- hepatitis C virus positive individuals aged over 18 were included. Structured face-to-face interviews were performed using a standardized questionnaire. Data were analyzed using SPSS. Results: Among the participants, 62.7% had hepatitis C virus RNA positivity, yet 42.2% of this group had never received treatment. Of the untreated patients, 83.2% reported no knowledge about hepatitis C. Misconceptions regarding transmission routes were widespread, and the involvement of family physicians in hepatitis C virus screening was limited. Although 75.7% of participants knew their family physician, only 7.8% had been tested for hepatitis by them. Conclusion: Awareness and access to treatment for hepatitis C virus in Turkey remain insufficient. Integration of primary care services into the hepatitis C virus care cascade, public awareness campaigns, and widespread implementation of reflex hepatitis C virus RNA testing are crucial for achieving national elimination goals.

Background and Aims: Fecal occult blood test is frequently used as a first-line screening method for colorectal cancer. In addition to fecal occult blood test, other screening methods include fecal immunohistochemical test, sigmoidoscopy, and colonoscopy. This study aims to evaluate the colonoscopy and histopathology results of patients who underwent colonoscopy due to a positive fecal occult blood test. Materials and Methods: This study included patients who underwent colonoscopy due to a positive fecal occult blood test at Antalya Training and Research Hospital between January 2020 and December 2024. Patients with inadequate bowel preparation, a known history of colorectal cancer, or inflammatory bowel disease were excluded. The age, gender, colonoscopy findings, and histopathological results of the included patients were recorded. Results: A total of 508 patients were included in the study, of whom 260 (51.2%) were male and 248 (48.8%) were female, with a median age of 61 years (range: 20 - 95). The median hemoglobin level was 13.5 g/dL (range: 5 - 16.3). Colonoscopy findings were normal in 196 (38.6%) patients. Other findings included polyps in 107 (21.1%), inflammatory bowel disease in 70 (13.8%), perianal disease in 59 (11.6%), colorectal cancer in 31 (6.1%), diverticula in 26 (5.1%), ulcers in 15 (3%), and angiodysplasia in 4 (0.8%) patients. A total of 223 (43.8%) patients with suspected colorectal cancer or polyps underwent biopsy. Histopathological examination revealed adenomatous polyps in 77 (34.5%) patients, inflammatory bowel disease in 59 (26.5%), adenocarcinoma in 31 (13.9%), and hyperplastic polyps in 26 (11.7%) patients, while 30 (13.5%) patients had no pathological findings. Conclusion: Nearly half of the patients who underwent colonoscopy due to a positive fecal occult blood test were found to have colonic pathology. Fecal occult blood test is a simple, cost-effective, and practical test not only for detecting colorectal cancer and precancerous lesions but also for identifying other colonic pathologies such as inflammatory bowel disease, diverticula, and perianal diseases.