Seasonal variation of peptic ulcer disease, peptic ulcer bleeding, and acute pancreatitis

Abstract Purpose Management of peptic ulcer bleeding is clinically challenging. Accurate characterization of the bleeding during endoscopy is key for endoscopic therapy. This study aimed to assess whether a deep learning model can aid in the classification of bleeding peptic ulcer disease. Methods Endoscopic still images of patients (n = 1694) with peptic ulcer bleeding for the last 5 years were retrieved and reviewed. Overall, 2289 images were collected for deep learning model training, and 449 images were validated for the performance test. Two expert endoscopists classified the images into different classes based on their appearance. Four deep learning models, including Mobile Net V2, VGG16, Inception V4, and ResNet50, were proposed and pre-trained by ImageNet with the established convolutional neural network algorithm. A comparison of the endoscopists and trained deep learning model was performed to evaluate the model’s performance on a dataset of 449 testing images. Results The results first presented the performance comparisons of four deep learning models. The Mobile Net V2 presented the optimal performance of the proposal models. The Mobile Net V2 was chosen for further comparing the performance with the diagnostic results obtained by one senior and one novice endoscopists. The sensitivity and specificity were acceptable for the prediction of “normal” lesions in both 3-class and 4-class classifications. For the 3-class category, the sensitivity and specificity were 94.83% and 92.36%, respectively. For the 4-class category, the sensitivity and specificity were 95.40% and 92.70%, respectively. The interobserver agreement of the testing dataset of the model was moderate to substantial with the senior endoscopist. The accuracy of the determination of endoscopic therapy required and high-risk endoscopic therapy of the deep learning model was higher than that of the novice endoscopist. Conclusions In this study, the deep learning model performed better than inexperienced endoscopists. Further improvement of the model may aid in clinical decision-making during clinical practice, especially for trainee endoscopist.

Download Full-text

Risk of Peptic Ulcer Bleeding Associated with Helicobacter pylori Infection, Nonsteroidal Anti-inflammatory Drugs, and Low-dose Aspirin Therapy in Peptic Ulcer Disease: A Case-control Study

The Korean Journal of Helicobacter and Upper Gastrointestinal Research ◽

10.7704/kjhugr.2019.19.1.42 ◽

2019 ◽

Vol 19 (1) ◽

pp. 42-47 ◽

Cited By ~ 1

Author(s):

Seung In Seo ◽

Jin Gu Kang ◽

Hyoung Su Kim ◽

Woon Geon Shin ◽

Myoung Kuk Jang ◽

...

Keyword(s):

Peptic Ulcer ◽

Low Dose ◽

Case Control Study ◽

Ulcer Bleeding ◽

Peptic Ulcer Bleeding ◽

Ulcer Disease ◽

Dose Aspirin ◽

Low Dose Aspirin ◽

Inflammatory Drugs ◽

Control Study

Download Full-text

P-BN10 Seasonal Variation of Presentation of Perforated Peptic Ulcer Disease: An Overview of Patient Demographics, Management and Outcomes in Northern Ireland

British Journal of Surgery ◽

10.1093/bjs/znab430.011 ◽

2021 ◽

Vol 108 (Supplement_9) ◽

Author(s):

Bakhat Yawar ◽

Ahmed Marzouk ◽

Heba Ali ◽

Alsarah Diab ◽

Hassan Abdulrahman ◽

...

Keyword(s):

Peptic Ulcer ◽

Seasonal Variation ◽

Peptic Ulcer Disease ◽

Perforated Peptic Ulcer ◽

Peptic Ulcers ◽

Northern Irish ◽

Mortality And Morbidity ◽

Ulcer Disease ◽

Patient Demographics ◽

Acute Peritonitis

Abstract Background Perforated peptic ulcer disease is one of the most common causes of acute peritonitis. It carries significant mortality and morbidity. Several previous studies have reported a seasonal variation in presentation of patients with perforated ulcers. Here we present this study from a Northern Irish perspective on perforated peptic ulcers. Methods A retrospective cohort study was conducted on perforated peptic ulcer patients who presented to Altnagelvin Area Hospital emergency department between 2015 to 2020. Data on patient demographics, clinical presentation, investigations, management and outcomes were collected. Primary outcome was to investigate if seasonality was associated with incidence of perforated peptic ulcers. Follow-up data was also collected. Seasons were defined as per UK Met Office. Results Results: A total of 50 patients presented with perforated PUD. Male:female ratio was approximately 3:2. Peaks were noted in spring and winter. April was the most common month for presentation followed by December. Smoking was the most common risk factor followed by alcohol abuse. 14 patients (28%) were either very frail or had contained perforations and were conservatively managed. 3 deaths were noted (6%). 13 patients (26%) required ICU admission at some stage in their management. Conclusions Slight seasonal variation was noted in presentation of perforated peptic ulcers in our study with more common incidence in winter and spring months. The month of April was noted to have the peak incidence of the disease in our study.

Download Full-text

Hemostatic spray powder TC-325 in the primary endoscopic treatment of peptic ulcer-related bleeding: multicenter international registry

Endoscopy ◽

10.1055/a-1186-5360 ◽

2020 ◽

Vol 53 (01) ◽

pp. 36-43

Author(s):

Mohamed Hussein ◽

Durayd Alzoubaidi ◽

Miguel-Fraile Lopez ◽

Michael Weaver ◽

Jacobo Ortiz-Fernandez-Sordo ◽

...

Keyword(s):

Peptic Ulcer ◽

Peptic Ulcer Disease ◽

Rescue Therapy ◽

Case Series ◽

Ulcer Bleeding ◽

Peptic Ulcers ◽

Gi Bleeding ◽

Ulcer Disease ◽

Bleeding Peptic Ulcers ◽

The Uk

Abstract Background Upper gastrointestinal bleeding (UGIB) is a leading cause of morbidity and is associated with a 2 % – 17 % mortality rate in the UK and USA. Bleeding peptic ulcers account for 50 % of UGIB cases. Endoscopic intervention in a timely manner can improve outcomes. Hemostatic spray is an endoscopic hemostatic powder for GI bleeding. This multicenter registry was created to collect data prospectively on the immediate endoscopic hemostasis of GI bleeding in patients with peptic ulcer disease when hemostatic spray is applied as endoscopic monotherapy, dual therapy, or rescue therapy. Methods Data were collected prospectively (January 2016 – March 2019) from 14 centers in the UK, France, Germany, and the USA. The application of hemostatic spray was decided upon at the endoscopist’s discretion. Results 202 patients with UGIB secondary to peptic ulcers were recruited. Immediate hemostasis was achieved in 178/202 patients (88 %), 26/154 (17 %) experienced rebleeding, 21/175 (12 %) died within 7 days, and 38/175 (22 %) died within 30 days (all-cause mortality). Combination therapy of hemostatic spray with other endoscopic modalities had an associated lower 30-day mortality (16 %, P < 0.05) compared with monotherapy or rescue therapy. There were high immediate hemostasis rates across all peptic ulcer disease Forrest classifications. Conclusions This is the largest case series of outcomes of peptic ulcer bleeding treated with hemostatic spray, with high immediate hemostasis rates for bleeding peptic ulcers.

Download Full-text

Seasonal Variation in Peptic Ulcer Disease Hospitalization: A 10-year Perspective in the U.S.

The American Journal of Gastroenterology ◽

10.14309/00000434-201510001-02316 ◽

2015 ◽

Vol 110 ◽

pp. S962-S963

Author(s):

Ritesh Kanotra ◽

Moiz Ahmed ◽

Shantanu Solanki ◽

Badal Thakkar ◽

Chirag Savani ◽

...

Keyword(s):

Peptic Ulcer ◽

Seasonal Variation ◽

Peptic Ulcer Disease ◽

Ulcer Disease ◽

The U.S

Download Full-text

Surgery

Oxford Handbook of Emergency Medicine ◽

10.1093/med/9780199589562.003.0010 ◽

2012 ◽

pp. 503-532

Author(s):

Jonathan P. Wyatt ◽

Robin N. Illingworth ◽

Colin A. Graham ◽

Kerstin Hogg ◽

Michael J. Clancy ◽

...

Keyword(s):

Acute Pancreatitis ◽

Peptic Ulcer ◽

Abdominal Pain ◽

Acute Appendicitis ◽

Intestinal Obstruction ◽

Peptic Ulcer Disease ◽

Biliary Tract ◽

Large Bowel ◽

Ulcer Disease ◽

P Retention

Approach to abdominal pain 504 Causes of acute abdominal pain 506 Acute appendicitis 507 Acute pancreatitis 508 Biliary tract problems 510 Peptic ulcer disease 511 Intestinal obstruction 512 Mesenteric ischaemia/infarction 514 Large bowel emergencies 516 Anorectal problems 518 Retention of urine 520 Testicular problems 522...

Download Full-text