Person: SEVEN, GÜLSEREN
9 results
Search Results
Now showing 1 - 9 of 9
Publication Open Access Differentiating Gastrointestinal Stromal Tumors from Leiomyomas Using a Neural Network Trained on Endoscopic Ultrasonography Images.(2021-10-07T00:00:00Z) Seven, GÜLSEREN; Silahtaroglu, Gokhan; Seven, Ozden Ozluk; Senturk, Hakan; SEVEN, GÜLSERENBackground: Endoscopic ultrasonography (EUS) is crucial to diagnose and evaluate gastrointestinal mesenchymal tumors (GIMTs). However, EUS-guided biopsy does not always differentiate gastrointestinal stromal tumors (GISTs) from leiomyomas. We evaluated the ability of a convolutional neural network (CNN) to differentiate GISTs from leiomyomas using EUS images. The conventional EUS features of GISTs were also compared with leiomyomas. Patients and methods: Patients who underwent EUS for evaluation of upper GIMTs between 2010 and 2020 were retrospectively reviewed, and 145 patients (73 women and 72 men; mean age 54.8 ± 13.5 years) with GISTs (n = 109) or leiomyomas (n = 36), confirmed by immunohistochemistry, were included. A total of 978 images collected from 100 patients were used to train and test the CNN system, and 384 images from 45 patients were used for validation. EUS images were also evaluated by an EUS expert for comparison with the CNN system. Results: The sensitivity, specificity, and accuracy of the CNN system for diagnosis of GIST were 92.0%, 64.3%, and 86.98% for the validation dataset, respectively. In contrast, the sensitivity, specificity, and accuracy of the EUS expert interpretations were 60.5%, 74.3%, and 63.0%, respectively. Concerning EUS features, only higher echogenicity was an independent and significant factor for differentiating GISTs from leiomyomas (p < 0.05). Conclusions: The CNN system could diagnose GIMTs with higher accuracy than an EUS expert and could be helpful in differentiating GISTs from leiomyomas. A higher echogenicity may also aid in differentiation.Publication Metadata only Early prediction of the severe course, survival, and ICU requirements in acute pancreatitis by artificial intelligence(2023-01-01) İnce A. T.; Silahtaroğlu G.; Seven G.; Koçhan K.; Yıldız K.; Şentürk H.; İNCE, ALİ TÜZÜN; SEVEN, GÜLSEREN; KOÇHAN, KORAY; ŞENTÜRK, HAKANAbstractObjectiveTo evaluate the success of artificial intelligence for early prediction of severe course, survival, and intensive care unit(ICU) requirement in patients with acute pancreatitis(AP).MethodsRetrospectively, 1334 patients were included the study. Severity is determined according to the Revised Atlanta Classification(RAC). The success of machine learning(ML) method was evaluated by 13 simple demographic, clinical, etiologic, and laboratory features obtained on ER admission. Additionally, it was evaluated whether Balthazar-computerized tomography severity index(CTSI) at 48-h contributed to success. The dataset was split into two parts, 90% for ML(of which 70% for learning and 30% for testing) and 10% for validation and 5-fold stratified sampling has been utilized. Variable Importance was used in the selection of features during training phase of machine. The Gradient Boost Algorithm trained the machine by KNIME analytics platform. SMOTE has been applied to increase the minority classes for training. The combined effects of the measured features were examined by multivariate logistic regression analysis and reciever operating curve curves of the prediction and confidence of the target variables were obtained.ResultsAccuracy values for the early estimation of Atlanta severity score, ICU requirement, and survival were found as 88.20%, 98.25%, and 92.77% respectively. When Balthazar-CTSI score is used, results were found as 91.02%, 92.25%, and 98% respectively.ConclusionsThe ML method we used successfully predicted the severe course, ICU requirement and survival, with promising accuracy values of over 88%. If 48-h Balthazar-CTSI is included in the calculation, the severity score and survival rates increase even more.Publication Metadata only Double Balloon Enteroscopy in a North American Setting: A Large Single Center 5-year Experience(2013-01-01T00:00:00Z) Seven, Gülseren; SEVEN, GÜLSERENBackground/Aims: Double balloon enteroscopy (DBE) allows both diagnosis and therapeutic maneuvers in the small bowel. Its use was pioneered in Europe and Asia but there remains a relative paucity of literature from North America. Our aim in this study was to determine diagnostic and therapeutic yield in a North American setting. Methods: A five-year retrospective analy-sis of all patients undergoing DBE at a single tertiary care North American hospital was performed. Results: Four-hundred fifty-seven procedures, 265 anterograde and 192 retrograde, were performed on 335 patients. The most common indications were obscure gastrointestinal bleeding, small bowel obstruction, and suspected masses and mucosal abnormalities. Total en-teroscopy was achieved in 19 of the 89 patients who had both anterograde and retrograde procedures. Overall diagnostic yield in the determination of cause of symptoms or previous imaging was 52%. The most common causes of obscure bleeding were small bowel ulcers (10%), vascular lesions (25%) and neoplasms (10%). The most common causes of small bowel obstruction were strictures, some of which underwent dilation. Other therapeutic interventions included polypectomy, retrieval of retained capsules, stent retrievals and percutaneous enteral jejunostomy tube placement. Overall complication rates were very low (0.6%) and included medication reaction (n=1), scope dysfunction (n=1) and perforation (n=1). Conclusions: DBE can be per-formed safely and with good diagnostic yield in a single referral center in North America. (Intest Res 2013;11:34-40Background/Aims: Double balloon enteroscopy (DBE) allows both diagnosis and therapeutic maneuvers in the small bowel. Its use was pioneered in Europe and Asia but there remains a relative paucity of literature from North America. Our aim in this study was to determine diagnostic and therapeutic yield in a North American setting. Methods: A five-year retrospective analy-sis of all patients undergoing DBE at a single tertiary care North American hospital was performed. Results: Four-hundred fifty-seven procedures, 265 anterograde and 192 retrograde, were performed on 335 patients. The most common indications were obscure gastrointestinal bleeding, small bowel obstruction, and suspected masses and mucosal abnormalities. Total en-teroscopy was achieved in 19 of the 89 patients who had both anterograde and retrograde procedures. Overall diagnostic yield in the determination of cause of symptoms or previous imaging was 52%. The most common causes of obscure bleeding were small bowel ulcers (10%), vascular lesions (25%) and neoplasms (10%). The most common causes of small bowel obstruction were strictures, some of which underwent dilation. Other therapeutic interventions included polypectomy, retrieval of retained capsules, stent retrievals and percutaneous enteral jejunostomy tube placement. Overall complication rates were very low (0.6%) and included medication reaction (n=1), scope dysfunction (n=1) and perforation (n=1). Conclusions: DBE can be per-formed safely and with good diagnostic yield in a single referral center in North America. (Intest Res 2013;11:34-40Background/Aims: Double balloon enteroscopy (DBE) allows both diagnosis and therapeutic maneuvers in the small bowel. Its use was pioneered in Europe and Asia but there remains a relative paucity of literature from North America. Our aim in this study was to determine diagnostic and therapeutic yield in a North American setting. Methods: A five-year retrospective analy-sis of all patients undergoing DBE at a single tertiary care North American hospital was performed. Results: Four-hundred fifty-seven procedures, 265 anterograde and 192 retrograde, were performed on 335 patients. The most common indications were obscure gastrointestinal bleeding, small bowel obstruction, and suspected masses and mucosal abnormalities. Total en-teroscopy was achieved in 19 of the 89 patients who had both anterograde and retrograde procedures. Overall diagnostic yield in the determination of cause of symptoms or previous imaging was 52%. The most common causes of obscure bleeding were small bowel ulcers (10%), vascular lesions (25%) and neoplasms (10%). The most common causes of small bowel obstruction were strictures, some of which underwent dilation. Other therapeutic interventions included polypectomy, retrieval of retained capsules, stent retrievals and percutaneous enteral jejunostomy tube placement. Overall complication rates were very low (0.6%) and included medication reaction (n=1), scope dysfunction (n=1) and perforation (n=1). Conclusions: DBE can be per-formed safely and with good diagnostic yield in a single referral center in North America. (Intest Res 2013;11:34-40Publication Metadata only EFFECT OF CHOLECYSTECTOMY ON PREVENTING RECURRENCE OF ACUTE PANCREATITIS(2022-10-11) Seven G.; Musayeva G.; İnce A. T.; Biberci Keskin E.; SEVEN, GÜLSEREN; İNCE, ALİ TÜZÜN; BİBERCİ KESKİN, ELMASBackground and AimsCurrent guidelines recommend cholecystectomy in patients with acute biliary pancreatitis (ABP) to prevent recurrence. Some studies suggest that a significant portion of patients with idiopathic acute pancreatitis (IAP) results from occult biliary disease and cholecystectomy, after an episode of IAP, reduces the risk of recurrent pancreatitis. However, in these studies, the work-up for potential biliary cause is not extensive and do not include endoscopic ultrasound (EUS), which can detect a biliary disease up to one-third of patients with IAP. In this study, we aimed to ascertain whether cholecystectomy can prevent pancreatitis recurrence in patients with ABP and IAP.MethodsAdult patients (over 18 years) with first episode of acute pancreatitis (AP) who admitted to inpatient clinic between January 1, 2015 and December 31, 2021 at a tertiary referral center were retrospectively reviewed. Medical records were scrutinized and relevant data extracted. In addition, a questionnaire either by mail or telephone was used. Patients with biliary and idiopathic AP were included in the analysis. Patients with chronic pancreatitis, previous pancreatic surgery, pancreatic cancer, and other etiologies were excluded. Primary outcome was recurrence rate. The diagnosis of IAP was confirmed by exclusion of all known etiological factors for AP using extensive work-up, including EUS and/or magnetic resonance cholangiopancreatography (MRCP).ResultsA total of 500 patients with first episode of AP (300 patients with ABP and 200 patients with IAP) were identified. The mean age was 58 years and 267 women, 233 men. The patients were divided into three different groups: Group 1; patients who had their first pancreatitis attack after cholecystectomy, Group 2; patients who had their gallbladder in situ during the first attack and followed by cholecystectomy and Group 3; patients who had their gallbladder in situ during the first attack but did not have cholecystectomy. The number of patients with recurrence after the first episode of AP were not statistically different in whole study group (25%, 19% and 15%, respectively, P = 0.176). In the subgroup of patients with ABP, the recurrence was higher in group 1 as compared with group 2 and 3 (39%, 19% and 14%, respectively, P = 0.018). On the other hand, in the subgroup of patients with IAP, there was no significant difference among the groups in terms of recurrence (15%, 18%, and 17%, respectively, P = 0.999). When patients with in situ gallbladder during their first attack were compared according to their cholecystectomy history (group 2 vs. group 3), no significant difference was found in neither the ABP nor the IAP subgroups (19% vs 14% and 18% vs. 17%, respectively, P > 0.05). In addition, the effect of endoscopic retrograde cholangiopancreatography (ERCP) on recurrence of pancreatitis was evaluated. In subgroup of ABP, ERCP was effective for reducing the recurrence in group 2 (P = 0.008), while it was not found statistically significant in group 1 and 3. In subgroup of IAP, it ERCP did not reduce the recurrence in any of the groups.ConclusionsIn ABP, the recurrence is high in patients who have their first pancreatitis attack after cholecystectomy. Cholecystectomy alone is not effective preventing recurrence in patients with gallbladder in situ during the first episode; however, the risk can be decreased with adding ERCP to cholecystectomy. On the other hand, cholecystectomy is not effective in reducing the recurrence in patients with IAP.Key Words: Acute biliary pancreatitis; Idiopathic acute pancreatitis; Cholecystectomy.References:1. Crockett SD, Wani S, Gardner TB, et al. American Gastroenterological Association Institute Guideline on Initial Management of Acute Pancreatitis. American Gastroenterological Association Institute Clinical Guidelines Committee. Gastroenterology. 2018 Mar;154(4):1096-1101.2. Räty S, Pulkkinen J, Nordback I, et al. Can Laparoscopic Cholecystectomy Prevent Recurrent Idiopathic Acute Pancreatitis?: A Prospective Randomized Multicenter Trial. Ann Surg. 2015 Nov;262(5):736-41.3. D S Umans, N D Hallensleben , R C Verdonk, et al. Recurrence of idiopathic acute pancreatitis after cholecystectomy: systematic review and meta-analysis. Br J Surg 2020 Feb;107(3):191-199.Publication Metadata only The natural course of non-alcoholic fatty liver disease.(2020-01-20) Seval G. C.; Kabacam G.; Yakut M.; Seven G.; Savas B.; Elhan A.; Cinar K.; Idilman R.; SEVEN, GÜLSERENPublication Open Access Correlation of Endoscopic Ultrasonography Features with the Mitotic Index in 2- to 5-cm Gastric Gastrointestinal Stromal Tumors(2021-04-01T00:00:00Z) Seven, Gulseren; Arici, Dilek Sema; Senturk, HAKAN; SEVEN, GÜLSEREN; ŞENTÜRK, HAKANBackground: Predicting the malignancy potential of gastrointestinal stromal tumor (GIST) before resection could improve patient management strategies as gastric GISTs with a low malignancy potential can be safely treated endoscopically, but surgical resection is required for those tumors with a high malignancy potential. This study aimed to evaluate endoscopic ultrasound (EUS) features of 2- to 5-cm gastric GISTs that might be used to predict their mitotic index using surgical specimens as the gold standard. Patients and methods: Forty-nine patients (30 females and 19 males; mean age 55.1 ± 12.7 years) who underwent EUS examinations, followed by surgical resections of 2- to 5-cm gastric GISTs, were retrospectively reviewed. Results: The mean tumor size was 3.44 ± 0.97 (range 2.1-5.0) cm. A univariate analysis revealed no significant differences in age, sex, and tumor location in the low mitotic index and high mitotic index groups (all p > 0.05). In terms of EUS features, there were no significant differences in the mitotic indexes with respect to the shape, surface lobulation, border regularity, echogenicity, homogeneity, growth patterns, presence of mucosal ulceration, hyperechogenic foci, anechoic spaces, and hypoechoic halos (all p > 0.05). However, the tumor size was larger in the high mitotic index group than that in the low mitotic index group (3.97 ± 1.05 vs. 3.27 ± 0.9 cm, p = 0.03). Conclusion: Conventional EUS features are not reliable for predicting the mitotic index of 2- to 5-cm gastric GISTs. Further modalities for predicting the mitotic index are needed to prevent unnecessary surgical resections in patients with a low risk of malignancy.Publication Metadata only Comparison of Endoscopic Ultrasound Guided Coil Injectıon with or without cyanoacrylate injection for gastric varices(2022-05-23) Seven G.; Musayeva G.; Seven O. O.; Herdan E.; İnce A. T.; Şentürk H.; SEVEN, GÜLSEREN; İNCE, ALİ TÜZÜN; ŞENTÜRK, HAKANPublication Metadata only Results of nucleos(t)ide analog treatment discontinuation in hepatitis b e-Antigen-negative chronic hepatitis b: Nucstop study(2024-01-01) Kiremitci S.; Kochan K.; SEVEN G.; Keskin E. B.; OKAY G.; AKKOYUNLU Y.; Koc M. M.; SÜMBÜL B.; ŞENTÜRK H.; KİREMİTÇİ, SERCAN; KOÇHAN, KORAY; SEVEN, GÜLSEREN; OKAY, GÜLAY; AKKOYUNLU, YASEMİN; SÜMBÜL, BİLGE; ŞENTÜRK, HAKANBackground/Aims: This study aims to investigate the effects of nucleos(t)ide analogs (NAs) discontinuation in eligible patients in accordance with the Asian Pacific Association for the Study of the Liver hepatitis B guideline and the factors affecting clinical and virological relapses. Materials and Methods: In this prospectively designed study, hepatitis B e antigen (HBeAg)-negative chronic hepatitis B patients who were followed up between 2012 and 2019 were evaluated and 57 patients were included. All participants enrolled the study were HBeAgnegative status at NA initiation. Results: The median age of the patients was 49 (29-72) years and 24 (42%) were females. The median treatment duration was 96 (36-276) months and patients were followed for a median duration of 27 months. Sixteen patients had a previous history of NA switch, and thirteen of these patients had a history of lamivudine resistance. Thirty-eight of 57 patients (66%) developed an elevated hepatitis B virus deoxyribonucleic acid level of 2000 IU/mL at least once, defined as virological relapse and 23 (60%) of them, experienced clinical relapse. Thirty-one of 57 patients were re-Treated during the follow-up, and hepatitis B surface antigen (HBsAg) loss occurred among 4 (7%) patients. All patients who experienced HBsAg loss had a history of lamivudine resistance (P = .002). Conclusion: Despite receiving NAs suppression therapy for a long time, HBsAg loss occurs rarely. Although it was not life-Threatening, most patients experienced relapses and treatment should be restarted. In our study, whether it is a coincidence that all patients with HBsAg loss are patients in whom NAs are used sequentially due to lamivudine resistance is an issue that needs to be further investigated.Publication Metadata only Endoscopic Ultrasound-Guided Pancreatic Duct Drainage(2024-01-01) Trieu J. A.; SEVEN G.; Baron T. H.; SEVEN, GÜLSEREN