Refine
Has Fulltext
- yes (3)
Is part of the Bibliography
- yes (3)
Year of publication
- 2022 (3) (remove)
Document Type
- Journal article (3)
Language
- English (3)
Keywords
- CADe (1)
- Crohn’s disease (1)
- Kono-S anastomosis (1)
- anastomotic leak (1)
- colonoscopy (1)
- deep learning (1)
- endoluminal (1)
- esophageal perforation (1)
- gastrointestinal perforation (1)
- ileocecal resection (1)
Institute
- Medizinische Klinik und Poliklinik II (3) (remove)
Background
Endoscopic vacuum therapy (EVT) is an effective treatment option for leakage of the upper gastrointestinal (UGI) tract. The aim of this study was to evaluate the clinical impact of quality improvements in EVT management on patients’ outcome.
Methods
All patients treated by EVT at our center during 2012–2021 were divided into two consecutive and equal-sized cohorts (period 1 vs. period 2). Over time several quality improvement strategies were implemented including the earlier diagnosis and EVT treatment and technical optimization of endoscopy. The primary endpoint was defined as the composite score MTL30 (mortality, transfer, length-of-stay > 30 days). Secondary endpoints included EVT efficacy, complications, in-hospital mortality, length-of-stay (LOS) and nutrition status at discharge.
Results
A total of 156 patients were analyzed. During the latter period the primary endpoint MTL30 decreased from 60.8 to 39.0% (P = .006). EVT efficacy increased from 80 to 91% (P = .049). Further, the need for additional procedures for leakage management decreased from 49.9 to 29.9% (P = .013) and reoperations became less frequent (38.0% vs.15.6%; P = .001). The duration of leakage therapy and LOS were shortened from 25 to 14 days (P = .003) and 38 days to 25 days (P = .006), respectively. Morbidity (as determined by the comprehensive complication index) decreased from 54.6 to 46.5 (P = .034). More patients could be discharged on oral nutrition (70.9% vs. 84.4%, P = .043).
Conclusions
Our experience confirms the efficacy of EVT for the successful management of UGI leakage. Our quality improvement analysis demonstrates significant changes in EVT management resulting in accelerated recovery, fewer complications and improved functional outcome.
Introduction: The rates of postoperative recurrence following ileocecal resection due to Crohn’s disease remain highly relevant. Despite this fact, while the Kono-S anastomosis technique initially demonstrated promising results, robust evidence is still lacking. This study aimed to analyze the short- and long-term outcomes of the Kono-S versus side-to-side anastomosis. Methods: A retrospective single-center study was performed including all patients who received an ileocecal resection between 1 January 2019 and 31 December 2021 at the Department of Surgery at the University Hospital of Wuerzburg. Patients who underwent conventional a side-to-side anastomosis were compared to those who received a Kono-S anastomosis. The short- and long-term outcomes were analyzed for all patients. Results: Here, 29 patients who underwent a conventional side-to-side anastomosis and 22 patients who underwent a Kono-S anastomosis were included. No differences were observed regarding short-term postoperative outcomes. The disease recurrence rate postoperatively was numerically lower following the Kono-S anastomosis (median Rutgeert score of 1.7 versus 2.5), with a relevantly increased rate of patients in remission (17.2% versus 31.8%); however, neither of these results reached statistical significance. Conclusion: The Kono-S anastomosis method is safe and feasible and potentially decreases the severity of postoperative disease remission.
Background
The efficiency of artificial intelligence as computer-aided detection (CADe) systems for colorectal polyps has been demonstrated in several randomized trials. However, CADe systems generate many distracting detections, especially during interventions such as polypectomies. Those distracting CADe detections are often induced by the introduction of snares or biopsy forceps as the systems have not been trained for such situations. In addition, there are a significant number of non-false but not relevant detections, since the polyp has already been previously detected. All these detections have the potential to disturb the examiner's work.
Objectives
Development and evaluation of a convolutional neuronal network that recognizes instruments in the endoscopic image, suppresses distracting CADe detections, and reliably detects endoscopic interventions.
Methods
A total of 580 different examination videos from 9 different centers using 4 different processor types were screened for instruments and represented the training dataset (519,856 images in total, 144,217 contained a visible instrument). The test dataset included 10 full-colonoscopy videos that were analyzed for the recognition of visible instruments and detections by a commercially available CADe system (GI Genius, Medtronic).
Results
The test dataset contained 153,623 images, 8.84% of those presented visible instruments (12 interventions, 19 instruments used). The convolutional neuronal network reached an overall accuracy in the detection of visible instruments of 98.59%. Sensitivity and specificity were 98.55% and 98.92%, respectively. A mean of 462.8 frames containing distracting CADe detections per colonoscopy were avoided using the convolutional neuronal network. This accounted for 95.6% of all distracting CADe detections.
Conclusions
Detection of endoscopic instruments in colonoscopy using artificial intelligence technology is reliable and achieves high sensitivity and specificity. Accordingly, the new convolutional neuronal network could be used to reduce distracting CADe detections during endoscopic procedures. Thus, our study demonstrates the great potential of artificial intelligence technology beyond mucosal assessment.