Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.4
3.9
Journals
JCM
Special Issues
AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy
share announcement

AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy

A special issue of Journal of Clinical Medicine (ISSN 2077-0383). This special issue belongs to the section "Gastroenterology & Hepatopancreatobiliary Medicine".

Deadline for manuscript submissions: closed (20 June 2020) | Viewed by 18768

Special Issue Editors

Prof. Dr. Anastasios Koulaouzidis

E-Mail Website
Guest Editor
1. Department of Clinical Research, University of Southern Denmark (SDU), Odense, Denmark
2. Centre for Clinical Implementation of Capsule Endoscopy (CICA), Store Adenomer Tidlige Cancere Centre (SATC-C), Svendborg, Denmark
Interests: capsule endoscopy; gastroenterology; collagenous colitis; microscopic colitis
Special Issues, Collections and Topics in MDPI journals
Dr. Wojciech Marlicz

E-Mail Website
Guest Editor
1. Department of Gastroenterology, Pomeranian Medical University, Szczecin, Poland
2. Endoklinika sp. z o.o., Szczecin, Poland
Interests: microbiome; colonoscopy; probiotics; colorectal cancer; gastric cancer; stem cells
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

There is a new kid on the block—artificial intelligence (AI)—and it has been making noise for quite a while. Part of what we have been practicing for years now actually is nothing less than a human/software interface including several decent chunks of AI. AI essentially is any technique that enables software to mimic human intelligence (HI) using logic, neural networks/decision trees, and machine learning. However, machine learning algorithms (MLAs) and deep learning have only recently made a star entry and have been attracting the attention of gastroenterologists, hepatologists, and GI endoscopists since the appearance of automated lesion recognition software and the boost in robotic techniques in surgery. AI has also been instrumental for a while 
in big data analyses in the era of -omics technologies, targeting microbiomes, and other complex ecosystems.

Although the published PubMed evidence is still limited, compared to other fields, there is a need for a dedicated platform that will allow for papers and groups to present their work as well as rigorous reviews. Such a platform should include basic information on this expanding field, which is necessary not only for the generation(s) of clinicians in practice but also—and perhaps more importantly—for those who follow. There is also a need to call for new AI educational software, mobile applications, and virtual reality (VR) tools, which would allow for stress and physician burnout management in the work place, and the building of trust and credibility among patients for better treatment outcomes. We suggest a new G&H journal on AI or a web-based database/portal of AI, but the undersigned believe that a Special Issue on the subject is timely, necessary, and will be welcomed.

Dr. Anastasios Koulaouzidis
Dr. Wojciech Marlicz
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Journal of Clinical Medicine is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • AI
  • Gastroenteroloy
  • Endosocpy
  • Colonoscopy
  • Capsule endoscopy
  • Hepatology
  • bid data
  • Machine Learning
  • Deep learning

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Editorial

Jump to: Research, Review

4 pages, 157 KiB  
Editorial
Artificial Intelligence in Gastroenterology—Walking into the Room of Little Miracles
by Wojciech Marlicz, George Koulaouzidis and Anastasios Koulaouzidis
J. Clin. Med. 2020, 9(11), 3675; https://doi.org/10.3390/jcm9113675 - 16 Nov 2020
Cited by 5 | Viewed by 1786
Abstract
The surge of artificial intelligence (AI) in medicine stands on a lengthy, and frequently reticent, buildout [...] Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)

Research

Jump to: Editorial, Review

12 pages, 929 KiB  
Article
Development of Machine Learning Model to Predict the 5-Year Risk of Starting Biologic Agents in Patients with Inflammatory Bowel Disease (IBD): K-CDM Network Study
by Youn I Choi, Sung Jin Park, Jun-Won Chung, Kyoung Oh Kim, Jae Hee Cho, Young Jae Kim, Kang Yoon Lee, Kwang Gi Kim, Dong Kyun Park and Yoon Jae Kim
J. Clin. Med. 2020, 9(11), 3427; https://doi.org/10.3390/jcm9113427 - 26 Oct 2020
Cited by 13 | Viewed by 2377
Abstract
Background: The incidence and global burden of inflammatory bowel disease (IBD) have steadily increased in the past few decades. Improved methods to stratify risk and predict disease-related outcomes are required for IBD. Aim: The aim of this study was to develop and validate [...] Read more.
Background: The incidence and global burden of inflammatory bowel disease (IBD) have steadily increased in the past few decades. Improved methods to stratify risk and predict disease-related outcomes are required for IBD. Aim: The aim of this study was to develop and validate a machine learning (ML) model to predict the 5-year risk of starting biologic agents in IBD patients. Method: We applied an ML method to the database of the Korean common data model (K-CDM) network, a data sharing consortium of tertiary centers in Korea, to develop a model to predict the 5-year risk of starting biologic agents in IBD patients. The records analyzed were those of patients diagnosed with IBD between January 2006 and June 2017 at Gil Medical Center (GMC; n = 1299) or present in the K-CDM network (n = 3286). The ML algorithm was developed to predict 5- year risk of starting biologic agents in IBD patients using data from GMC and externally validated with the K-CDM network database. Result: The ML model for prediction of IBD-related outcomes at 5 years after diagnosis yielded an area under the curve (AUC) of 0.86 (95% CI: 0.82–0.92), in an internal validation study carried out at GMC. The model performed consistently across a range of other datasets, including that of the K-CDM network (AUC = 0.81; 95% CI: 0.80–0.85), in an external validation study. Conclusion: The ML-based prediction model can be used to identify IBD-related outcomes in patients at risk, enabling physicians to perform close follow-up based on the patient’s risk level, estimated through the ML algorithm. Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)
►▼ Show Figures

Figure 1

15 pages, 2258 KiB  
Article
Prediction of Adverse Events in Stable Non-Variceal Gastrointestinal Bleeding Using Machine Learning
by Dong-Woo Seo, Hahn Yi, Beomhee Park, Youn-Jung Kim, Dae Ho Jung, Ilsang Woo, Chang Hwan Sohn, Byuk Sung Ko, Namkug Kim and Won Young Kim
J. Clin. Med. 2020, 9(8), 2603; https://doi.org/10.3390/jcm9082603 - 11 Aug 2020
Cited by 12 | Viewed by 2203
Abstract
Clinical risk-scoring systems are important for identifying patients with upper gastrointestinal bleeding (UGIB) who are at a high risk of hemodynamic instability. We developed an algorithm that predicts adverse events in patients with initially stable non-variceal UGIB using machine learning (ML). Using prospective [...] Read more.
Clinical risk-scoring systems are important for identifying patients with upper gastrointestinal bleeding (UGIB) who are at a high risk of hemodynamic instability. We developed an algorithm that predicts adverse events in patients with initially stable non-variceal UGIB using machine learning (ML). Using prospective observational registry, 1439 out of 3363 consecutive patients were enrolled. Primary outcomes included adverse events such as mortality, hypotension, and rebleeding within 7 days. Four machine learning algorithms, namely, logistic regression with regularization (LR), random forest classifier (RF), gradient boosting classifier (GB), and voting classifier (VC), were compared with the Glasgow–Blatchford score (GBS) and Rockall scores. The RF model showed the highest accuracies and significant improvement over conventional methods for predicting mortality (area under the curve: RF 0.917 vs. GBS 0.710), but the performance of the VC model was best in hypotension (VC 0.757 vs. GBS 0.668) and rebleeding within 7 days (VC 0.733 vs. GBS 0.694). Clinically significant variables including blood urea nitrogen, albumin, hemoglobin, platelet, prothrombin time, age, and lactate were identified by the global feature importance analysis. These results suggest that ML models will be useful early predictive tools for identifying high-risk patients with initially stable non-variceal UGIB admitted at an emergency department. Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)
►▼ Show Figures

Figure 1

11 pages, 3630 KiB  
Article
Optimal Endoscopic Resection Technique for Selected Gastric GISTs. The Endoscopic Suturing System Combined with ESD—a New Alternative?
by Katarzyna M. Pawlak, Artur Raiter, Katarzyna Kozłowska-Petriczko, Joanna Szełemej, Jan Petriczko, Katarzyna Wojciechowska and Anna Wiechowska-Kozłowska
J. Clin. Med. 2020, 9(6), 1776; https://doi.org/10.3390/jcm9061776 - 08 Jun 2020
Cited by 13 | Viewed by 2861
Abstract
Background and Study Aim: In terms of therapeutic management, gastrointestinal stromal tumors (GISTs) seem to be the most difficult group of subepithelial gastrointestinal lesions (SELs). Despite various treatment option, choice of optimal management remains a dilemma in daily practice. Our aim was to [...] Read more.
Background and Study Aim: In terms of therapeutic management, gastrointestinal stromal tumors (GISTs) seem to be the most difficult group of subepithelial gastrointestinal lesions (SELs). Despite various treatment option, choice of optimal management remains a dilemma in daily practice. Our aim was to evaluate a new hybrid resection technique of gastric GISTs type III as a modality of endoscopic full-thickness resection. Methods: Three males and one female (mean age of 68) were qualified for the procedure. Endoscopic full-thickness resections consisted of the endoscopic resection combined with suturing by Apollo OverStitch System. The main inclusion criterium was a complete diagnosis of GISTs (computed tomography (CT), endoscopic ultrasound (EUS), fine-needle biopsy (FNB)) with the evaluation of the tumor features, especially, the location in the gastric wall. All of the tumors were type III with a diameter between 20–40 mm. The lesions were located in the corpus (1), antrum (1) and between gastric body and fundus (2). All procedures were performed in 2019. Results: The technical and therapeutic success rate was 100% and the mean resection time 107.5 min. Neither intra- nor postprocedural complications were observed. In all four cases, R0 resection was achieved. Histopathologic assessment confirmed GIST with <5mitose/50HPF in all of the tumors, with very low risk. Conclusion: Based on our outcomes, endoscopic resection combined with the sewing by Apollo OverStitch of gastric GISTs type III, with the diameter between 20–40 mm, seems to be an effective therapeutic option with a good safety profile, however further studies with a larger treatment group are needed. Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)
►▼ Show Figures

Figure 1

12 pages, 5480 KiB  
Article
Automated Classification of Colorectal Neoplasms in White-Light Colonoscopy Images via Deep Learning
by Young Joo Yang, Bum-Joo Cho, Myung-Je Lee, Ju Han Kim, Hyun Lim, Chang Seok Bang, Hae Min Jeong, Ji Taek Hong and Gwang Ho Baik
J. Clin. Med. 2020, 9(5), 1593; https://doi.org/10.3390/jcm9051593 - 24 May 2020
Cited by 34 | Viewed by 4419
Abstract
Background: Classification of colorectal neoplasms during colonoscopic examination is important to avoid unnecessary endoscopic biopsy or resection. This study aimed to develop and validate deep learning models that automatically classify colorectal lesions histologically on white-light colonoscopy images. Methods: White-light colonoscopy images of colorectal [...] Read more.
Background: Classification of colorectal neoplasms during colonoscopic examination is important to avoid unnecessary endoscopic biopsy or resection. This study aimed to develop and validate deep learning models that automatically classify colorectal lesions histologically on white-light colonoscopy images. Methods: White-light colonoscopy images of colorectal lesions exhibiting pathological results were collected and classified into seven categories: stages T1-4 colorectal cancer (CRC), high-grade dysplasia (HGD), tubular adenoma (TA), and non-neoplasms. The images were then re-classified into four categories including advanced CRC, early CRC/HGD, TA, and non-neoplasms. Two convolutional neural network models were trained, and the performances were evaluated in an internal test dataset and an external validation dataset. Results: In total, 3828 images were collected from 1339 patients. The mean accuracies of ResNet-152 model for the seven-category and four-category classification were 60.2% and 67.3% in the internal test dataset, and 74.7% and 79.2% in the external validation dataset, respectively, including 240 images. In the external validation, ResNet-152 outperformed two endoscopists for four-category classification, and showed a higher mean area under the curve (AUC) for detecting TA+ lesions (0.818) compared to the worst-performing endoscopist. The mean AUC for detecting HGD+ lesions reached 0.876 by Inception-ResNet-v2. Conclusions: A deep learning model presented promising performance in classifying colorectal lesions on white-light colonoscopy images; this model could help endoscopists build optimal treatment strategies. Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)
►▼ Show Figures

Figure 1

Review

Jump to: Editorial, Research

22 pages, 265 KiB  
Review
Scope of Artificial Intelligence in Screening and Diagnosis of Colorectal Cancer
by Hemant Goyal, Rupinder Mann, Zainab Gandhi, Abhilash Perisetti, Aman Ali, Khizar Aman Ali, Neil Sharma, Shreyas Saligram, Benjamin Tharian and Sumant Inamdar
J. Clin. Med. 2020, 9(10), 3313; https://doi.org/10.3390/jcm9103313 - 15 Oct 2020
Cited by 32 | Viewed by 4115
Abstract
Globally, colorectal cancer is the third most diagnosed malignancy. It causes significant mortality and morbidity, which can be reduced by early diagnosis with an effective screening test. Integrating artificial intelligence (AI) and computer-aided detection (CAD) with screening methods has shown promising colorectal cancer [...] Read more.
Globally, colorectal cancer is the third most diagnosed malignancy. It causes significant mortality and morbidity, which can be reduced by early diagnosis with an effective screening test. Integrating artificial intelligence (AI) and computer-aided detection (CAD) with screening methods has shown promising colorectal cancer screening results. AI could provide a “second look” for endoscopists to decrease the rate of missed polyps during a colonoscopy. It can also improve detection and characterization of polyps by integration with colonoscopy and various advanced endoscopic modalities such as magnifying narrow-band imaging, endocytoscopy, confocal endomicroscopy, laser-induced fluorescence spectroscopy, and magnifying chromoendoscopy. This descriptive review discusses various AI and CAD applications in colorectal cancer screening, polyp detection, and characterization. Full article
(This article belongs to the Special Issue AI in Medical Practice/Gastroenterology, Hepatology and Endoscopy)
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop