1
|
Fukuda T, Yamazaki H, Miyatani Y, Sawada T, Shibuya N, Fukuo Y, Kiyohara H, Morikubo H, Tominaga K, Kakimoto K, Imai T, Yaguchi K, Yamamoto S, Ando K, Nishimata N, Yoshihara T, Andoh A, Hibi T, Matsuoka K. Recent steroid use and the relapse risk in ulcerative colitis patients with endoscopic healing. Aliment Pharmacol Ther 2024; 60:43-51. [PMID: 38651779 DOI: 10.1111/apt.18013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Revised: 12/18/2023] [Accepted: 04/11/2024] [Indexed: 04/25/2024]
Abstract
BACKGROUND Endoscopic healing (EH) is a therapeutic target in ulcerative colitis (UC). However, even patients who have achieved EH relapse frequently. AIMS To investigate the association between recent steroid use and relapse risk in UC patients with EH. METHODS This multi-centre cohort study included 1212 UC patients with confirmed EH (Mayo endoscopic subscore ≤1). We excluded patients with current systemic steroid use or history of advanced therapy. We divided patients into a recent steroid group (last systemic steroid use within 1 year; n = 59) and a non-recent or steroid-naïve group (n = 1153). We followed the patients for 2 years to evaluate relapse, defined as induction of systemic steroids or advanced therapy. We used logistic regression to estimate the odds ratio (OR) of relapse. RESULTS Relapse occurred in 28.8% of the recent steroid group and 5.6% of the non-recent/steroid-naïve group (multi-variable-adjusted OR 5.53 [95% CI 2.85-10.7]). The risk of relapse decreased with time since the last steroid use: 28.8% for less than 1 year after steroid therapy, 22.9% for 1 year, 16.0% for 2 years and 7.9% beyond 3 years, approaching 4.0% in steroid-naïve patients. (ptrend <0.001). CONCLUSIONS Even for patients with UC who achieved EH, the risk of relapse remains high following recent steroid therapy. Physicians need to consider the duration since last steroid use to stratify the relapse risk in UC patients with EH.
Collapse
Affiliation(s)
- Tomohiro Fukuda
- Department of Gastroenterology, Yokohama Municipal Citizen's Hospital, Kanagawa, Japan
| | - Hajime Yamazaki
- Section of Clinical Epidemiology, Department of Community Medicine, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Yusuke Miyatani
- Centre for Advanced IBD Research and Treatment, Kitasato University Kitasato Institute Hospital, Tokyo, Japan
| | - Tsunaki Sawada
- Department of Endoscopy, Nagoya University Hospital, Aichi, Japan
| | - Naoki Shibuya
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Jikei University School of Medicine, Tokyo, Japan
| | - Yuka Fukuo
- Department of Gastroenterology, Juntendo University Nerima Hospital, Tokyo, Japan
| | - Hiroki Kiyohara
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Hiromu Morikubo
- Department of Gastroenterology and Hepatology, Kyorin University School of Medicine, Tokyo, Japan
| | - Keiichi Tominaga
- Department of Gastroenterology, Dokkyo Medical University, Tochigi, Japan
| | - Kazuki Kakimoto
- 2nd Department of Internal Medicine, Osaka Medical and Pharmaceutical University, Osaka, Japan
| | - Takayuki Imai
- Department of Medicine, Shiga University of Medical Science, Shiga, Japan
| | - Katsuki Yaguchi
- Inflammatory Bowel Disease Centre, Yokohama City University Medical Centre, Kanagawa, Japan
| | - Shojiro Yamamoto
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Faculty of Medicine, University of Miyazaki Hospital, Miyazaki, Japan
| | - Katsuyoshi Ando
- Gastroenterology and Endoscopy, Division of Metabolism and Biosystemic Science, Gastroenterology and Hematology/Oncology, Department of Medicine, Asahikawa Medical University, Asahikawa, Japan
| | - Nobuaki Nishimata
- Department of Gastroenterology, Sameshima Hospital, Kagoshima, Japan
| | - Takeo Yoshihara
- Department of Gastroenterology and Hepatology, Osaka University Graduate School of Medicine, Osaka, Japan
| | - Akira Andoh
- Department of Medicine, Shiga University of Medical Science, Shiga, Japan
| | - Toshifumi Hibi
- Centre for Advanced IBD Research and Treatment, Kitasato University Kitasato Institute Hospital, Tokyo, Japan
| | - Katsuyoshi Matsuoka
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Toho University Sakura Medical Center, Chiba, Japan
| |
Collapse
|
2
|
Fukuda T, Aoki Y, Kiyohara H, Yokoyama A, Nakazawa A, Yoshimatsu Y, Sugimoto S, Nanki K, Mikami Y, Fukuhara K, Mizuno S, Sujino T, Mutaguchi M, Takabayashi K, Morohoshi Y, Hosoda Y, Ogata H, Iwao Y, Naganuma M, Kanai T. Efficacy of Dose Escalation of Oral 5-Aminosalicylic Acid for Ulcerative Colitis With a Mayo Endoscopic Subscore of 1: An Open Label Randomized Controlled Trial. Inflamm Bowel Dis 2024:izae088. [PMID: 38655866 DOI: 10.1093/ibd/izae088] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/16/2023] [Indexed: 04/26/2024]
Abstract
BACKGROUND Endoscopic healing is generally defined as Mayo endoscopic subscore (MES) ≤1 in ulcerative colitis (UC). However, patients with an MES of 1 are at higher relapse risk than those with an MES of 0. This study evaluated the therapeutic efficacy of proactive dose escalation of oral 5-aminosalicylic acid (5-ASA) in UC patients with an MES of 1. METHODS An open-label, randomized controlled trial was conducted in 5 hospitals between 2018 and 2022. Ulcerative colitis patients in clinical remission under oral 5-ASA therapy and diagnosed as having an MES of 1 were enrolled. Patients receiving maintenance therapy other than 5-ASA and immunomodulator were excluded. Patients were randomly assigned in a 1:1 ratio to receive either a dose-escalated (intervention) or constant dose (control) of 5-ASA. Concomitant immunomodulator was used as the stratification factor in the randomization. The primary end point was relapse within 1 year. The subgroup analysis was stratified for the use of immunomodulators. RESULTS The full analysis set included 79 patients (39 intervention and 40 control). Immunomodulators were used in 20 (25.3%) patients. Relapse was less in the intervention group (15.4%) than the control group (37.5%; P = .026). In the subgroup with concomitant immunomodulators, relapse was also less in the intervention group (10.0%) than the control group (70.0%; P = .020). In patients without immunomodulators, the difference was not significant between 2 groups (intervention, 17.2%; control, 26.7%; P = .53). CONCLUSIONS Dose escalation of 5-ASA reduced relapse within 1 year in UC patients in clinical remission with an MES of 1.
Collapse
Affiliation(s)
- Tomohiro Fukuda
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
- Department of Gastroenterology, Yokohama Municipal Citizen's Hospital, Kanagawa, Japan
| | - Yasuhiro Aoki
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Hiroki Kiyohara
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
- Center for Advanced IBD Research and Treatment, Kitasato University Kitasato Institute Hospital, Tokyo, Japan
| | - Ayumi Yokoyama
- Department of Gastroenterology, Tokyo Saiseikai Central Hospital, Tokyo, Japan
| | - Atsushi Nakazawa
- Department of Gastroenterology, Tokyo Saiseikai Central Hospital, Tokyo, Japan
| | - Yusuke Yoshimatsu
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Shinya Sugimoto
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Kosaku Nanki
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Yohei Mikami
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Kayoko Fukuhara
- Center for Preventive Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Shinta Mizuno
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| | - Tomohisa Sujino
- Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan
| | - Makoto Mutaguchi
- Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan
| | - Kaoru Takabayashi
- Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan
| | - Yuichi Morohoshi
- Department of Gastroenterology, Yokohama Municipal Citizen's Hospital, Kanagawa, Japan
| | - Yasuo Hosoda
- Department of Gastroenterology, National Hospital Organization Saitama Hospital, Saitama, Japan
| | - Haruhiko Ogata
- Center for Diagnostic and Therapeutic Endoscopy, Keio University School of Medicine, Tokyo, Japan
| | - Yasushi Iwao
- Center for Preventive Medicine, Keio University School of Medicine, Tokyo, Japan
| | - Makoto Naganuma
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
- Division of Gastroenterology and Hepatology, The Third Department of Internal Medicine, Kansai Medical University, Osaka, Japan
| | - Takanori Kanai
- Division of Gastroenterology and Hepatology, Department of Internal Medicine, Keio University School of Medicine, 35 Shinanomachi, Shinjuku-ku, Tokyo, 160-8582, Japan
| |
Collapse
|
3
|
Shehab M, Al Akram S, Hassan A, Alrashed F, Jairath V, Bessissow T. Histological Disease Activity as Predictor of Clinical Relapse, Hospitalization, and Surgery in Inflammatory Bowel Disease: Systematic Review and Meta-Analysis. Inflamm Bowel Dis 2024; 30:563-572. [PMID: 37541185 DOI: 10.1093/ibd/izad119] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Indexed: 08/06/2023]
Abstract
BACKGROUND The clinical impact of histological remission on short- and long-term clinical outcomes in patients with inflammatory bowel disease (IBD) is not well established. We assessed risk of clinical relapse, hospitalization, and need for surgery in patients achieving histological remission in comparison with active histological disease. METHODS A systematic review was conducted using MEDLINE, Scopus, Cochrane CENTRAL, EMBASE, and conference abstracts from inception to November 2022. Our main outcome was the rate of clinical relapse in patients with IBD who reached histological remission vs patients with active histological disease. Secondary outcomes were clinical complications of IBD such as hospitalization and need for surgery. The endpoints were investigated at 2 time points, 6 to 12 months (short term) and >12 months (long term). RESULTS Short-term outcome analysis showed that the risk of clinical relapse was significantly higher in ulcerative colitis patients with active histological disease in comparison with patients at histological remission (risk ratio [RR], 2.41; 95% confidence interval [CI], 1.69-3.44; P < .01). The risk of hospitalization in ulcerative colitis patients was not significant among the 2 groups (RR, 4.22; 95% CI, 0.91-19.62; P = .07). Long-term outcome analysis demonstrated that the risk of clinical relapse (RR, 2.07; 95% CI, 1.55-2.76; P < .01), need for surgery (RR, 3.14; 95% CI, 1.53-6.45; P < .01), and hospitalization (RR, 2.52; 95% CI, 1.59-4.00; P < .01) was significantly higher in patients with active histological disease. CONCLUSIONS Histological remission in IBD represents an important therapeutic goal that is not yet routinely pursued in clinical practice. In our study, patients who achieved histological remission have more favorable outcomes than those with active histological disease in ulcerative colitis.
Collapse
Affiliation(s)
- Mohammad Shehab
- Division of Gastroenterology, Department of Internal Medicine, Mubarak Alkaber Hospital, Kuwait City, Kuwait
| | - Sahad Al Akram
- Division of Gastroenterology, Department of Internal Medicine, Mubarak Alkaber Hospital, Kuwait City, Kuwait
| | - Amro Hassan
- Division of Gastroenterology, Department of Internal Medicine, Mubarak Alkaber Hospital, Kuwait City, Kuwait
| | - Fatema Alrashed
- Department of Pharmacy Practice, Faculty of Pharmacy, Kuwait University, Kuwait City, Kuwait
| | - Vipul Jairath
- Division of Gastroenterology, Department of Medicine, Schulich School of Medicine, Western University, London, ON, Canada
- Lawson Health Research Institute, Western University, London, ON, Canada
- Department of Epidemiology and Biostatistics, Western University, London, ON, Canada
| | - Talat Bessissow
- Division of Gastroenterology and Hepatology, Department of Medicine, McGill University Health Center, Montreal, QC, Canada
| |
Collapse
|
4
|
Kim S, Park SH. Could histologic healing be a new treatment target in patients with ulcerative colitis? Korean J Intern Med 2024; 39:2-3. [PMID: 38225820 PMCID: PMC10790042 DOI: 10.3904/kjim.2023.539] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Accepted: 12/10/2023] [Indexed: 01/17/2024] Open
Affiliation(s)
- Soyoung Kim
- Department of Gastroenterology, Ulsan University Hospital, University of Ulsan College of Medicine, Ulsan,
Korea
| | - Sang Hyoung Park
- Department of Gastroenterology, Asan Medical Center, University of Ulsan College of Medicine, Seoul,
Korea
| |
Collapse
|
5
|
Yan J, Deng F, Tan Y, Zhou B, Liu D. Systemic immune-inflammation index as a potential biomarker to monitor ulcerative colitis. Curr Med Res Opin 2023; 39:1321-1328. [PMID: 37691449 DOI: 10.1080/03007995.2023.2257599] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/24/2023] [Revised: 08/17/2023] [Accepted: 09/07/2023] [Indexed: 09/12/2023]
Abstract
OBJECTIVE The treat-to-target strategy is recommended by Selecting Therapeutic Targets in Inflammatory Bowel Disease II (STRIDE-II) for treating ulcerative colitis (UC), and monitoring remission status is crucial during this management. The systemic immune-inflammation index (SII), defined as platelet * neutrophil/lymphocyte, is a complete blood count-based index reflecting the balance of immune and inflammatory status. This study aims to investigate the feasibility of SII for diagnosing UC and monitoring UC disease activity. METHODS This study retrospectively analyzed patients with UC and controls. Relationships between SII and Mayo clinical score, Mayo Endoscopic Score (MES), and Nancy Histological Index (NHI) were evaluated. RESULTS 167 patients with UC and 106 controls were included. SII significantly increased in patients with UC and was closely correlated with the Mayo clinical score, MES, and NHI. SII diagnosed UC with a cut-off value of 619.1 × 109/L (area under the curve = 0.861, p < 0.0001, sensitivity 79.64%, specificity 77.36%), evaluated clinical remission status with a cut-off value of 1068 × 109/L (area under the curve = 0.691, p < 0.05, sensitivity 55.71%, specificity 81.48%), endoscopic improvement with a cut-off value of 981.3 × 109/L (area under the curve = 0.819, p < 0.0001, sensitivity 65.22%, specificity 89.66%), and histological healing with a cut-off value of 689.3 × 109/L (area under the curve = 0.898, p < 0.0001, sensitivity 88.89%, specificity 95.83%). CONCLUSION SII is a potential biomarker for diagnosing UC and monitoring UC disease severity, especially in evaluating mucosal and histological healing during the long-term management in treat-to-target strategy. However, further research is needed to confirm its usefulness and optimize its clinical application.
Collapse
Affiliation(s)
- Jin Yan
- Department of Gastroenterology, the Second Xiangya Hospital of Central South University, Changsha, Hunan, China
- Research Center of Digestive Disease, Central South University, Changsha, Hunan, China
| | - Feihong Deng
- Department of Gastroenterology, the Second Xiangya Hospital of Central South University, Changsha, Hunan, China
- Research Center of Digestive Disease, Central South University, Changsha, Hunan, China
| | - Yuyong Tan
- Department of Gastroenterology, the Second Xiangya Hospital of Central South University, Changsha, Hunan, China
- Research Center of Digestive Disease, Central South University, Changsha, Hunan, China
| | - Bingyi Zhou
- Department of Gastroenterology, the Second Xiangya Hospital of Central South University, Changsha, Hunan, China
- Research Center of Digestive Disease, Central South University, Changsha, Hunan, China
| | - Deliang Liu
- Department of Gastroenterology, the Second Xiangya Hospital of Central South University, Changsha, Hunan, China
- Research Center of Digestive Disease, Central South University, Changsha, Hunan, China
| |
Collapse
|
6
|
George LA, Feldman HT, Alizadeh M, Abutaleb A, Zullow S, Hine A, Stashek K, Sarkar S, Sun K, Hudesman D, Axelrad J, Cross RK. Histologic Inflammation can Predict Future Clinical Relapse in Ulcerative Colitis Patients in Endoscopic Remission. CROHN'S & COLITIS 360 2023; 5:otad059. [PMID: 37886705 PMCID: PMC10599395 DOI: 10.1093/crocol/otad059] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Indexed: 10/28/2023] Open
Abstract
Background In ulcerative colitis (UC), endoscopic improvement, defined as a Mayo Endoscopic Score (MES) of 0 or 1, is a target of treatment. The aim of our study was to evaluate the risk of clinical relapse between patients with an MES of 0 or 1 and determine if histologic activity using the Robarts Histopathologic Index (RHI) was predictive of clinical relapse. Methods UC patients with an MES score of 0 or 1, no prior colectomy, and at least 1 year of outpatient follow-up after colonoscopy were included. Demographic, clinical characteristics, and clinical relapse were retrospectively collected. Biopsy specimens were read by a gastrointestinal pathologist. Primary outcome was defined as a composite of relapse requiring change in medical therapy, new steroid use, UC-related hospitalization, and/or colectomy. Results Four hundred and forty-five UC patients were identified. Ninety-five percent of patients with MES 0 were in histologic remission by the RHI whereas only 35% of patients with MES 1 were in histologic remission. Twenty-six percent of patients experienced a clinical relapse; patients with MES 1 or RHI > 3 were significantly more likely to relapse (P < .01) compared to patients with MES 0 or RHI ≤ 3. When patients were stratified into 4 groups (MES 0, RHI ≤ 3; MES 0, RHI > 3; MES 1, RHI ≤ 3; MES 1, RHI > 3) and adjusted for age and sex, RHI > 3 was predictive of relapse (P = .008). Conclusions UC patients with endoscopic improvement have a high rate of clinical relapse over time. Histologic activity is a predictor of clinical relapse.
Collapse
Affiliation(s)
- Lauren A George
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Harris T Feldman
- Department of Medicine, Department of Pediatrics, University of Massachusetts Medical School, Worcester, MA, USA
| | - Madeline Alizadeh
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
- Institute for Genome Sciences, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Ameer Abutaleb
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Samantha Zullow
- Division of Gastroenterology and Hepatology, Inflammatory Bowel Disease Center, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, USA
| | - Ashley Hine
- University of Connecticut School of Medicine, Farmington, CT, USA
| | - Kristen Stashek
- Department of Pathology, University of Maryland School of Medicine, Baltimore, MD, USA
| | - Suparna Sarkar
- Department of Pathology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY, USA
| | - Katherine Sun
- Department of Pathology, NYU Langone Health, NYU Grossman School of Medicine, New York, NY, USA
| | - David Hudesman
- Division of Gastroenterology, Department of Medicine, Inflammatory Bowel Disease Center at NYU Langone Health, NYU Grossman School of Medicine, New York, NY, USA
| | - Jordan Axelrad
- Division of Gastroenterology, Department of Medicine, Inflammatory Bowel Disease Center at NYU Langone Health, NYU Grossman School of Medicine, New York, NY, USA
| | - Raymond K Cross
- Division of Gastroenterology and Hepatology, Department of Medicine, University of Maryland School of Medicine, Baltimore, MD, USA
| |
Collapse
|
7
|
Kim JE, Choi YH, Lee YC, Seong G, Song JH, Kim TJ, Kim ER, Hong SN, Chang DK, Kim YH, Shin SY. Deep learning model for distinguishing Mayo endoscopic subscore 0 and 1 in patients with ulcerative colitis. Sci Rep 2023; 13:11351. [PMID: 37443370 PMCID: PMC10344868 DOI: 10.1038/s41598-023-38206-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Accepted: 07/05/2023] [Indexed: 07/15/2023] Open
Abstract
The aim of this study was to address the issue of differentiating between Mayo endoscopic subscore (MES) 0 and MES 1 using a deep learning model. A dataset of 492 ulcerative colitis (UC) patients who demonstrated MES improvement between January 2018 and December 2019 at Samsung Medical Center was utilized. Specifically, two representative images of the colon and rectum were selected from each patient, resulting in a total of 984 images for analysis. The deep learning model utilized in this study consisted of a convolutional neural network (CNN)-based encoder, with two auxiliary classifiers for the colon and rectum, as well as a final MES classifier that combined image features from both inputs. In the internal test, the model achieved an F1-score of 0.92, surpassing the performance of seven novice classifiers by an average margin of 0.11, and outperforming their consensus by 0.02. The area under the receiver operating characteristic curve (AUROC) was calculated to be 0.97 when considering MES 1 as positive, with an area under the precision-recall curve (AUPRC) of 0.98. In the external test using the Hyperkvasir dataset, the model achieved an F1-score of 0.89, AUROC of 0.86, and AUPRC of 0.97. The results demonstrate that the proposed CNN-based model, which integrates image features from both the colon and rectum, exhibits superior performance in accurately discriminating between MES 0 and MES 1 in patients with UC.
Collapse
Affiliation(s)
- Ji Eun Kim
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Yoon Ho Choi
- Department of Artificial Intelligence and Informatics Research, Mayo Clinic, Jacksonville, FL, USA
- Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology, Sungkyunkwan University, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Yeong Chan Lee
- Research Institute for Future Medicine, Samsung Medical Center, Seoul, South Korea
| | - Gyeol Seong
- Department of Medicine, Nowon Eulji Medical Center, Eulji University, Seoul, South Korea
| | - Joo Hye Song
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Tae Jun Kim
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Eun Ran Kim
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Sung Noh Hong
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Dong Kyung Chang
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea
| | - Young-Ho Kim
- Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea.
| | - Soo-Yong Shin
- Department of Digital Health, Samsung Advanced Institute for Health Sciences and Technology, Sungkyunkwan University, 81 Irwon-Ro, Gangnam-gu, Seoul, 06351, South Korea.
| |
Collapse
|