Endoscopic submucosal dissection (ESD) is widely used to treat early-stage esophageal squamous cell carcinoma (SCC). However, the risk of recurrence in non-curative cases remains uncertain. This study aimed to elucidate the risk of local and metastatic recurrence of esophageal SCC treated with ESD.
Methods
We retrospectively analyzed data for 222 patients who underwent ESD followed by esophagectomy and fulfilled the following criteria: (1) no metastatic lesions diagnosed before ESD and (2) pathologically diagnosed SCC with SM invasion regardless of VM status or pathologically diagnosed SCC with lymphovascular invasion. The primary outcome was the proportion of metastasis and local residual cancer determined using the pathological findings of additional esophagectomy specimens and follow-up data.
Results
For submucosal cancer with positive lymphovascular invasion, the metastasis rate was 29.5% (23/78) compared with 8.8% (5/57) in submucosal cancers with negative lymphovascular invasion. The metastasis rate for vertical margin (VM) 1 or VMX was 30.8% (16/52) compared with 20.7% (28/135) in submucosal cancer. Local residual cancer was observed in 10 (19.2%) individuals with VM1/X, with 80% of these involving the submucosal layer (n = 4) and muscularis propria or deeper (n = 4). Among cases with VM0, local residual cancer was observed in six (3.5%) individuals, of which 66.7% were mucosal cancers.
Conclusions
In conclusion, the proportions of metastasis and local residual cancer in non-curative cases were clarified. While additional treatment is necessary to reduce these risks, if a patient is managed with observation alone, strict surveillance that accounts for these risks is required.
{"title":"Risk of Metastasis and Local Residual Cancer After Non-Curative Endoscopic Submucosal Dissection for Esophageal Cancer","authors":"Ryu Ishihara, Hirofumi Kawakubo, Yoshinobu Yamamoto, Jun Nakamura, Takako Yoshii, Hiroshi Sato, Akira Nakano, Takashi Ogata, Yusuke Okuda, Kazuhiro Furukawa, Osamu Dohi, Koji Miyahara, Yoichi Hamai, Tomonori Yano, Hiroya Takeuchi","doi":"10.1111/den.15082","DOIUrl":"10.1111/den.15082","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Background</h3>\u0000 \u0000 <p>Endoscopic submucosal dissection (ESD) is widely used to treat early-stage esophageal squamous cell carcinoma (SCC). However, the risk of recurrence in non-curative cases remains uncertain. This study aimed to elucidate the risk of local and metastatic recurrence of esophageal SCC treated with ESD.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We retrospectively analyzed data for 222 patients who underwent ESD followed by esophagectomy and fulfilled the following criteria: (1) no metastatic lesions diagnosed before ESD and (2) pathologically diagnosed SCC with SM invasion regardless of VM status or pathologically diagnosed SCC with lymphovascular invasion. The primary outcome was the proportion of metastasis and local residual cancer determined using the pathological findings of additional esophagectomy specimens and follow-up data.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>For submucosal cancer with positive lymphovascular invasion, the metastasis rate was 29.5% (23/78) compared with 8.8% (5/57) in submucosal cancers with negative lymphovascular invasion. The metastasis rate for vertical margin (VM) 1 or VMX was 30.8% (16/52) compared with 20.7% (28/135) in submucosal cancer. Local residual cancer was observed in 10 (19.2%) individuals with VM1/X, with 80% of these involving the submucosal layer (<i>n</i> = 4) and muscularis propria or deeper (<i>n</i> = 4). Among cases with VM0, local residual cancer was observed in six (3.5%) individuals, of which 66.7% were mucosal cancers.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>In conclusion, the proportions of metastasis and local residual cancer in non-curative cases were clarified. While additional treatment is necessary to reduce these risks, if a patient is managed with observation alone, strict surveillance that accounts for these risks is required.</p>\u0000 </section>\u0000 </div>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 11","pages":"1207-1214"},"PeriodicalIF":4.7,"publicationDate":"2025-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144577114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Virginia Gregorio, Yasuharu Maeda, Shin-Ei Kudo, Yurie Kawabata, Takanori Kuroki, Giovanni Santacroce, Miguel Puga-Tejada, Kento Takenaka, Kaoru Takabayashi, Jun Ohara, Chiyo Maeda, Katsuro Ichimasa, Masashi Misawa, Noriyuki Ogata, Haruhiko Ogata, Kazuo Ohtsuka, Marietta Iacucci
Inflammatory bowel disease (IBD), including Crohn's disease and ulcerative colitis, presents substantial diagnostic and management challenges because of its variable clinical course and the limitations of conventional endoscopy. Although endoscopic procedures are crucial for diagnosis and surveillance, their inherent subjectivity and inter-observer variability complicate disease assessment. Recent advances in artificial intelligence (AI) offer promising solutions to these challenges by enabling automated, precise, and objective image analysis. AI technologies have demonstrated success in diagnosing IBD, distinguishing it from other gastrointestinal disorders, and facilitating early identification of neoplasia in IBD patients, improving clinical decision-making and potentially reducing the need for invasive procedures. Furthermore, AI applications for evaluating endoscopic images have enhanced the accuracy of disease severity assessments such as the Mayo Endoscopic Score and Ulcerative Colitis Endoscopic Index of Severity by overcoming issues related to observer variability. Integration of AI with advanced endoscopic technologies, including image-enhanced and magnified endoscopy, further improves lesion characterization and offers insights into mucosal healing, which is crucial for optimizing treatment. While AI's potential in IBD management is substantial, challenges remain in its clinical implementation, necessitating further validation through real-world data and regulatory approval. This review explores the evolving role of AI in transforming IBD diagnosis, surveillance, and assessment, with a focus on enhancing patient care through improved precision and efficiency.
{"title":"Evolving Role of Artificial Intelligence in Endoscopic Management of Inflammatory Bowel Disease: Diagnosis, Surveillance, and Assessment","authors":"Virginia Gregorio, Yasuharu Maeda, Shin-Ei Kudo, Yurie Kawabata, Takanori Kuroki, Giovanni Santacroce, Miguel Puga-Tejada, Kento Takenaka, Kaoru Takabayashi, Jun Ohara, Chiyo Maeda, Katsuro Ichimasa, Masashi Misawa, Noriyuki Ogata, Haruhiko Ogata, Kazuo Ohtsuka, Marietta Iacucci","doi":"10.1111/den.15081","DOIUrl":"10.1111/den.15081","url":null,"abstract":"<p>Inflammatory bowel disease (IBD), including Crohn's disease and ulcerative colitis, presents substantial diagnostic and management challenges because of its variable clinical course and the limitations of conventional endoscopy. Although endoscopic procedures are crucial for diagnosis and surveillance, their inherent subjectivity and inter-observer variability complicate disease assessment. Recent advances in artificial intelligence (AI) offer promising solutions to these challenges by enabling automated, precise, and objective image analysis. AI technologies have demonstrated success in diagnosing IBD, distinguishing it from other gastrointestinal disorders, and facilitating early identification of neoplasia in IBD patients, improving clinical decision-making and potentially reducing the need for invasive procedures. Furthermore, AI applications for evaluating endoscopic images have enhanced the accuracy of disease severity assessments such as the Mayo Endoscopic Score and Ulcerative Colitis Endoscopic Index of Severity by overcoming issues related to observer variability. Integration of AI with advanced endoscopic technologies, including image-enhanced and magnified endoscopy, further improves lesion characterization and offers insights into mucosal healing, which is crucial for optimizing treatment. While AI's potential in IBD management is substantial, challenges remain in its clinical implementation, necessitating further validation through real-world data and regulatory approval. This review explores the evolving role of AI in transforming IBD diagnosis, surveillance, and assessment, with a focus on enhancing patient care through improved precision and efficiency.</p>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 11","pages":"1148-1161"},"PeriodicalIF":4.7,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144562049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Colonoscopy remains a fundamental procedure in the screening, diagnosis, and therapeutic management of colorectal diseases. Despite significant improvements in reprocessing protocols, the use of reusable endoscopes continues to carry an inherent risk of cross-contamination and infection transmission [<span>1, 2</span>]. Although colonoscopy is generally regarded as a low-risk procedure for infection, studies have reported colonoscopy-associated infection rates of up to 1.6 per 1000 procedures, depending on definitions and settings [<span>1</span>]. This concern was brought to the forefront by reports of persistent contamination in endoscopes even after meticulous cleaning and strict adherence to reprocessing protocols [<span>2</span>]. These findings have prompted regulatory agencies and professional societies to reconsider reprocessing protocols and explore alternatives, including single-use components [<span>3</span>]. While single-use gastroscopes and duodenoscopes have demonstrated comparable performance to reusable counterparts in recent reports [<span>4, 5</span>], their colonoscopic counterparts have remained less explored in both clinical practice and the literature.</p><p>In this issue of <i>Digestive Endoscopy</i>, Wang et al. present a pilot randomized controlled noninferiority trial comparing a novel disposable colonoscope approved by both the FDA and Conformité Européenne (CE) to a conventional reusable model in patients undergoing routine colonoscopy [<span>6</span>]. This multicenter study enrolled 116 patients and used successful completion of colonoscopy, defined as cecal intubation with sufficient withdrawal observation, as the primary endpoint. Secondary endpoints included procedural metrics such as insertion time, polyp detection rate (PDR), adenoma detection rate (ADR), image quality, and adverse events. Notably, both groups achieved 100% success in cecal intubation. Although the disposable scope group demonstrated slightly inferior image quality, inferior operation flexibility, longer insertion times, and somewhat lower PDR and ADR, these differences were not clinically prohibitive. Importantly, most combined scores for image quality and image discernibility were rated 4 or above, and technical maneuverability scores generally ranged from 2 to 3, indicating satisfactory operability. Furthermore, the withdrawal time was comparable between the two groups. Endoscopists adapted to the disposable device after approximately 10 cases, reflecting a rapid learning curve.</p><p>The findings presented by Wang et al. have several clinical implications. First, they provide evidence that disposable colonoscopes can achieve comparable outcomes to conventional reusable scopes in terms of procedural success and diagnostic performance. This is particularly relevant in clinical environments where infection prevention is paramount, such as in immunocompromised populations, transplant units, or during outbreaks of multidrug resistant organism
{"title":"Disposable Colonoscopes: Unpacking the Infection-Free Endoscopy With the REAL Price Tag—What About Performance?","authors":"Yoshihiro Kishida, Shiro Oka","doi":"10.1111/den.15083","DOIUrl":"10.1111/den.15083","url":null,"abstract":"<p>Colonoscopy remains a fundamental procedure in the screening, diagnosis, and therapeutic management of colorectal diseases. Despite significant improvements in reprocessing protocols, the use of reusable endoscopes continues to carry an inherent risk of cross-contamination and infection transmission [<span>1, 2</span>]. Although colonoscopy is generally regarded as a low-risk procedure for infection, studies have reported colonoscopy-associated infection rates of up to 1.6 per 1000 procedures, depending on definitions and settings [<span>1</span>]. This concern was brought to the forefront by reports of persistent contamination in endoscopes even after meticulous cleaning and strict adherence to reprocessing protocols [<span>2</span>]. These findings have prompted regulatory agencies and professional societies to reconsider reprocessing protocols and explore alternatives, including single-use components [<span>3</span>]. While single-use gastroscopes and duodenoscopes have demonstrated comparable performance to reusable counterparts in recent reports [<span>4, 5</span>], their colonoscopic counterparts have remained less explored in both clinical practice and the literature.</p><p>In this issue of <i>Digestive Endoscopy</i>, Wang et al. present a pilot randomized controlled noninferiority trial comparing a novel disposable colonoscope approved by both the FDA and Conformité Européenne (CE) to a conventional reusable model in patients undergoing routine colonoscopy [<span>6</span>]. This multicenter study enrolled 116 patients and used successful completion of colonoscopy, defined as cecal intubation with sufficient withdrawal observation, as the primary endpoint. Secondary endpoints included procedural metrics such as insertion time, polyp detection rate (PDR), adenoma detection rate (ADR), image quality, and adverse events. Notably, both groups achieved 100% success in cecal intubation. Although the disposable scope group demonstrated slightly inferior image quality, inferior operation flexibility, longer insertion times, and somewhat lower PDR and ADR, these differences were not clinically prohibitive. Importantly, most combined scores for image quality and image discernibility were rated 4 or above, and technical maneuverability scores generally ranged from 2 to 3, indicating satisfactory operability. Furthermore, the withdrawal time was comparable between the two groups. Endoscopists adapted to the disposable device after approximately 10 cases, reflecting a rapid learning curve.</p><p>The findings presented by Wang et al. have several clinical implications. First, they provide evidence that disposable colonoscopes can achieve comparable outcomes to conventional reusable scopes in terms of procedural success and diagnostic performance. This is particularly relevant in clinical environments where infection prevention is paramount, such as in immunocompromised populations, transplant units, or during outbreaks of multidrug resistant organism","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 11","pages":"1233-1235"},"PeriodicalIF":4.7,"publicationDate":"2025-07-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15083","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144562147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computer-aided detection (CADe) is promising for improving adenoma detection rates (ADRs) but mostly in academic centers. Therefore, we evaluated the effect of CADe on ADR and related outcomes in a Japanese community hospital setting.
Methods
In this single-center, randomized controlled trial conducted between September 2022 and August 2023, patients were eligible for inclusion if they were 40 years of age or older and had undergone colonoscopy for screening, post-polypectomy surveillance, a positive fecal immunochemical test, or symptoms. Patients were randomized at a 1:1 ratio to undergo colonoscopy with or without CADe. The primary outcome was ADR. Secondary outcomes included the number of adenomas per colonoscopy (APC) and the withdrawal time.
Results
A total of 1041 patients were recruited. After exclusion, 497 and 501 patients in the control and CADe groups, respectively, were included in the analysis. ADR was 54.5% in the control group and 50.7% in the CADe group, with no significant difference between the groups (adjusted risk ratio, 0.93; 95% confidence interval [CI], 0.83–1.05). The mean number of APC was lower in the CADe group than in the control group (1.34 vs. 1.14) (adjusted rate ratio, 0.86; 95% CI, 0.77–0.96). The mean withdrawal time was longer in the CADe group than in the control group (691 vs. 751 s, p = 0.034).
Conclusions
CADe did not significantly improve ADR in a Japanese community hospital setting, possibly due to the high baseline ADR in the control group. Further research is needed to understand in which settings CADe is useful.
Trial Registration
University Hospital Medical Information Network Clinical Trials Registry: UMIN000049054
目的：计算机辅助检测（CADe）有望提高腺瘤检出率（adr），但主要是在学术中心。因此，我们在日本一家社区医院评估了CADe对不良反应和相关结局的影响。方法：在这项于2022年9月至2023年8月进行的单中心随机对照试验中，如果患者年龄在40岁或以上，并且接受过结肠镜筛查、息肉切除术后监测、粪便免疫化学试验阳性或症状，则符合纳入条件。患者按1:1的比例随机接受有或没有CADe的结肠镜检查。主要结局是ADR。次要结果包括每次结肠镜检查腺瘤的数量（APC）和停药时间。结果：共纳入1041例患者。排除后，对照组和CADe组分别有497例和501例患者被纳入分析。对照组不良反应发生率为54.5%，CADe组为50.7%，两组间差异无统计学意义(校正风险比为0.93；95%可信区间[CI]， 0.83-1.05)。CADe组APC平均数目低于对照组（1.34 vs 1.14）(校正率比，0.86；95% ci, 0.77-0.96)。CADe组平均停药时间长于对照组（691 vs 751 s, p = 0.034）。结论：CADe没有显著改善日本社区医院的ADR，可能是由于对照组的基线ADR较高。需要进一步的研究来了解CADe在哪些情况下是有用的。试验注册：大学医院医学信息网临床试验注册：UMIN000049054。
{"title":"Effect of Computer-Aided Detection During Colonoscopy on Adenoma Detection Rate in a Community Hospital Setting: Randomized Controlled Trial","authors":"Yohei Yabuuchi, Kazuya Hosotani, Yoshiki Morihisa, Yukie Fujio, Daisuke Oshikawa, Manami Oshita, Momoko Iketani, Kazuyuki Tsukamoto, Asuka Sone, Toshiya Nanjo, Ryoko Tatsuno, Kosuke Tanaka, Soichiro Nagao, Shinsuke Akiyama, Gensho Tanke, Masaya Wada, Shuko Morita, Satoko Inoue, Hobyung Chung, Yoshitaka Nishikawa, Tetsuro Inokuma","doi":"10.1111/den.15086","DOIUrl":"10.1111/den.15086","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>Computer-aided detection (CADe) is promising for improving adenoma detection rates (ADRs) but mostly in academic centers. Therefore, we evaluated the effect of CADe on ADR and related outcomes in a Japanese community hospital setting.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>In this single-center, randomized controlled trial conducted between September 2022 and August 2023, patients were eligible for inclusion if they were 40 years of age or older and had undergone colonoscopy for screening, post-polypectomy surveillance, a positive fecal immunochemical test, or symptoms. Patients were randomized at a 1:1 ratio to undergo colonoscopy with or without CADe. The primary outcome was ADR. Secondary outcomes included the number of adenomas per colonoscopy (APC) and the withdrawal time.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>A total of 1041 patients were recruited. After exclusion, 497 and 501 patients in the control and CADe groups, respectively, were included in the analysis. ADR was 54.5% in the control group and 50.7% in the CADe group, with no significant difference between the groups (adjusted risk ratio, 0.93; 95% confidence interval [CI], 0.83–1.05). The mean number of APC was lower in the CADe group than in the control group (1.34 vs. 1.14) (adjusted rate ratio, 0.86; 95% CI, 0.77–0.96). The mean withdrawal time was longer in the CADe group than in the control group (691 vs. 751 s, <i>p</i> = 0.034).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusions</h3>\u0000 \u0000 <p>CADe did not significantly improve ADR in a Japanese community hospital setting, possibly due to the high baseline ADR in the control group. Further research is needed to understand in which settings CADe is useful.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Trial Registration</h3>\u0000 \u0000 <p>University Hospital Medical Information Network Clinical Trials Registry: UMIN000049054</p>\u0000 </section>\u0000 </div>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 11","pages":"1215-1223"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144562048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Underwater endoscopic mucosal resection (UEMR) is effective for 10–20 mm colorectal polyps [1]. However, snaring is difficult for lesions at colonic flexures because the proximal edge is hidden by folds. We report a case of successful en bloc UEMR using a multiloop traction device (MLTD) (Boston Scientific, Tokyo, Japan).
A 72-year-old man with hypopharyngeal cancer underwent fluorodeoxyglucose (FDG) positron emission tomography, which revealed FDG accumulation in the rectosigmoid colon. Colonoscopy revealed a 20-mm protruding lesion. UEMR using SnareMasterPlus (15 mm; Olympus Medical Systems, Tokyo, Japan) was attempted. However, visualization of the oral side of the lesion was challenging, as the lesion extended across the flexure of the rectosigmoid junction (Figures 1a and 2a). Retroflex observation allowed the visualization of the oral side of the tumor; however, poor maneuverability prevented suitable snaring. Therefore, we attached MLTD to the normal mucosa 5 mm oral to the lesion using a SureClip (Micro-Tech, Nanjing, China) (Figure 1b), and subsequently hooked and anchored it to the colonic wall at the opposite side of the lesion with the second clip (Figure 1c). The traction force reduced the steep angle of the rectosigmoid junction and improved the visualization of the oral margin of the lesion in forward view (Figures 1d and 2b). We performed reliable snaring by directly observing the lesion margins (Figure 1e). The traction force optimized the visualization of the resected wound, which facilitated subsequent clipping (Figure 1f). Pathology confirmed a low-grade tubulovillous adenoma with negative resection margins.
Submucosal injection in the oral edge might also have improved lesion visibility; however, considering that unsuccessful injection carries the risk of irreversibly worsening the situation (e.g., impaired visibility due to bleeding), we first attempted this traction method, which can be undone if needed. This method has been reported in colorectal ESD [2] and duodenal UEMR cases [3], and we further confirmed its usefulness even in colorectal UEMR.
Kazuki Matsuyama performed the procedures and drafted the manuscript. Minoru Kato revised the manuscript critically. Tomoki Michida supervised manuscript preparation. All the authors have read and approved the final version of this manuscript.
Informed consent was obtained from the patient for the publication of his information and imaging data.
The authors declare no conflicts of interest.
水下内镜粘膜切除术（UEMR）对10 ~ 20mm结直肠息肉[1]有效。然而，由于近端边缘被褶皱隐藏，在结肠屈曲处的病变很难捕获。我们报告一例使用多环牵引装置（MLTD）成功的整体UEMR（波士顿科学，东京，日本）。一位72岁的下咽癌患者接受了氟脱氧葡萄糖（FDG）正电子发射断层扫描，发现FDG在直肠乙状结肠积聚。结肠镜检查发现一个20毫米的突出病变。尝试使用SnareMasterPlus（15毫米；Olympus Medical Systems，东京，日本）的UEMR。然而，病变口腔侧的可视化是有挑战性的，因为病变延伸到直肠乙状结肠交界处的屈曲处（图1a和2a）。逆行观察可以看到肿瘤的口腔一侧；然而，较差的机动性阻碍了适当的诱捕。因此，我们使用SureClip （Micro-Tech，南京，中国）将MLTD附着在离病变5毫米的正常粘膜上（图1b），随后用第二个夹子将其钩住并锚定在病变对面的结肠壁上（图1c）。牵引力降低了直肠乙状结肠交界处的陡峭角度，改善了病变口缘的正视图可视化（图1d和2b）。我们通过直接观察病变边缘进行了可靠的诱捕（图1e）。牵引力优化了切除伤口的视觉效果，便于后续的夹闭（图1f）。病理证实为低级别管绒毛腺瘤，切除边缘阴性。口腔边缘粘膜下注射也可以改善病变的可见性；然而，考虑到不成功的注射有不可逆转地恶化情况的风险（例如，出血导致的能见度下降），我们首先尝试了这种牵引方法，如果需要，可以取消牵引方法。该方法在结直肠ESD病例[2]和十二指肠UEMR病例[3]中已有报道，我们进一步证实了该方法在结直肠UEMR中的有效性。Kazuki Matsuyama完成了程序并起草了手稿。加藤实对手稿进行了严格的修改。知树道田监督手稿的准备工作。所有作者都阅读并认可了这篇手稿的最终版本。获得患者的知情同意，公布其信息和成像数据。作者声明无利益冲突。
{"title":"Underwater Endoscopic Mucosal Resection With a Multiloop Traction Device for a Colorectal Tumor at the Flexure","authors":"Kazuki Matsuyama, Minoru Kato, Tomoki Michida","doi":"10.1111/den.15079","DOIUrl":"10.1111/den.15079","url":null,"abstract":"<p>Underwater endoscopic mucosal resection (UEMR) is effective for 10–20 mm colorectal polyps [<span>1</span>]. However, snaring is difficult for lesions at colonic flexures because the proximal edge is hidden by folds. We report a case of successful en bloc UEMR using a multiloop traction device (MLTD) (Boston Scientific, Tokyo, Japan).</p><p>A 72-year-old man with hypopharyngeal cancer underwent fluorodeoxyglucose (FDG) positron emission tomography, which revealed FDG accumulation in the rectosigmoid colon. Colonoscopy revealed a 20-mm protruding lesion. UEMR using SnareMasterPlus (15 mm; Olympus Medical Systems, Tokyo, Japan) was attempted. However, visualization of the oral side of the lesion was challenging, as the lesion extended across the flexure of the rectosigmoid junction (Figures 1a and 2a). Retroflex observation allowed the visualization of the oral side of the tumor; however, poor maneuverability prevented suitable snaring. Therefore, we attached MLTD to the normal mucosa 5 mm oral to the lesion using a SureClip (Micro-Tech, Nanjing, China) (Figure 1b), and subsequently hooked and anchored it to the colonic wall at the opposite side of the lesion with the second clip (Figure 1c). The traction force reduced the steep angle of the rectosigmoid junction and improved the visualization of the oral margin of the lesion in forward view (Figures 1d and 2b). We performed reliable snaring by directly observing the lesion margins (Figure 1e). The traction force optimized the visualization of the resected wound, which facilitated subsequent clipping (Figure 1f). Pathology confirmed a low-grade tubulovillous adenoma with negative resection margins.</p><p>Submucosal injection in the oral edge might also have improved lesion visibility; however, considering that unsuccessful injection carries the risk of irreversibly worsening the situation (e.g., impaired visibility due to bleeding), we first attempted this traction method, which can be undone if needed. This method has been reported in colorectal ESD [<span>2</span>] and duodenal UEMR cases [<span>3</span>], and we further confirmed its usefulness even in colorectal UEMR.</p><p>Kazuki Matsuyama performed the procedures and drafted the manuscript. Minoru Kato revised the manuscript critically. Tomoki Michida supervised manuscript preparation. All the authors have read and approved the final version of this manuscript.</p><p>Informed consent was obtained from the patient for the publication of his information and imaging data.</p><p>The authors declare no conflicts of interest.</p>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 10","pages":"1125-1126"},"PeriodicalIF":4.7,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15079","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144562050","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In Jung Kim, Geun Joo Choi, Hyoung-Chul Oh, Hyun Kang
Objectives
Sedation for endoscopic retrograde cholangiopancreatography (ERCP) is challenging owing to patient comorbidities and procedural complexity. Remimazolam, a novel benzodiazepine, has potential safety benefits. We aimed to systematically compare the efficacy and safety of remimazolam and propofol for ERCP sedation through a meta-analysis and trial sequential analysis (TSA).
Methods
We searched Ovid-MEDLINE, Ovid-Embase, Cochrane Central, and Google Scholar for randomized controlled trials (RCTs) that compared efficacy and safety of remimazolam and propofol in ERCP sedation. Sensitivity analysis and TSA were also performed.
Results
Five RCTs (965 participants) were included. In these trials, remimazolam significantly reduced hypoxia (risk ratio [RR], 0.522; 95% confidence interval [CI] 0.348–0.783; Grading of Recommendations, Assessment, Development, and Evaluation [GRADE], high), hypotension (RR, 0.507; 95% CI 0.396–0.649; GRADE, high), and bradycardia (RR, 0.475; 95% CI 0.308–0.732; GRADE, high). However, it increased tachycardia (RR, 3.363; 95% CI, 1.466–7.714; GRADE, moderate) and body movement (RR, 2.744; 95% CI, 1.216–6.193; GRADE, moderate). Delirium and agitation (RR, 0.586; 95% CI, 0.157–2.179; GRADE, moderate) and completion rate (RR, 1.009; 95% CI, 0.97–1.042; GRADE, moderate) were comparable. Recovery quality was higher in remimazolam group (mean difference, 1.541; 95% CI, 0.057–3.024; GRADE, low). Other outcomes, including induction and recovery times, were similar.
Conclusion
Remimazolam demonstrated superior safety profile than propofol for ERCP sedation, significantly reducing hypoxia, hypotension, and bradycardia with high certainty evidence and TSA confirmation. Despite the higher incidence of tachycardia and body movement associated with remimazolam, the completion rate and risk of delirium or agitation were similar for both sedatives.
{"title":"Comparison of Remimazolam and Propofol for Sedation in Endoscopic Retrograde Cholangiopancreatography: A Systematic Review and Meta-Analysis With Trial Sequential Analysis","authors":"In Jung Kim, Geun Joo Choi, Hyoung-Chul Oh, Hyun Kang","doi":"10.1111/den.15078","DOIUrl":"10.1111/den.15078","url":null,"abstract":"<div>\u0000 \u0000 \u0000 <section>\u0000 \u0000 <h3> Objectives</h3>\u0000 \u0000 <p>Sedation for endoscopic retrograde cholangiopancreatography (ERCP) is challenging owing to patient comorbidities and procedural complexity. Remimazolam, a novel benzodiazepine, has potential safety benefits. We aimed to systematically compare the efficacy and safety of remimazolam and propofol for ERCP sedation through a meta-analysis and trial sequential analysis (TSA).</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Methods</h3>\u0000 \u0000 <p>We searched Ovid-MEDLINE, Ovid-Embase, Cochrane Central, and Google Scholar for randomized controlled trials (RCTs) that compared efficacy and safety of remimazolam and propofol in ERCP sedation. Sensitivity analysis and TSA were also performed.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Results</h3>\u0000 \u0000 <p>Five RCTs (965 participants) were included. In these trials, remimazolam significantly reduced hypoxia (risk ratio [RR], 0.522; 95% confidence interval [CI] 0.348–0.783; Grading of Recommendations, Assessment, Development, and Evaluation [GRADE], high), hypotension (RR, 0.507; 95% CI 0.396–0.649; GRADE, high), and bradycardia (RR, 0.475; 95% CI 0.308–0.732; GRADE, high). However, it increased tachycardia (RR, 3.363; 95% CI, 1.466–7.714; GRADE, moderate) and body movement (RR, 2.744; 95% CI, 1.216–6.193; GRADE, moderate). Delirium and agitation (RR, 0.586; 95% CI, 0.157–2.179; GRADE, moderate) and completion rate (RR, 1.009; 95% CI, 0.97–1.042; GRADE, moderate) were comparable. Recovery quality was higher in remimazolam group (mean difference, 1.541; 95% CI, 0.057–3.024; GRADE, low). Other outcomes, including induction and recovery times, were similar.</p>\u0000 </section>\u0000 \u0000 <section>\u0000 \u0000 <h3> Conclusion</h3>\u0000 \u0000 <p>Remimazolam demonstrated superior safety profile than propofol for ERCP sedation, significantly reducing hypoxia, hypotension, and bradycardia with high certainty evidence and TSA confirmation. Despite the higher incidence of tachycardia and body movement associated with remimazolam, the completion rate and risk of delirium or agitation were similar for both sedatives.</p>\u0000 </section>\u0000 </div>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 10","pages":"1054-1067"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Primary sclerosing cholangitis (PSC) is an autoimmune liver and biliary disease characterized by fibrotic narrowing of the bile ducts, leading to chronic bile stasis and eventually progressing to cirrhosis. However, to date, the etiology of PSC remains unknown.</p><p>A diagnosis of PSC is made based on the following major findings: typical bile duct images and elevated serum alkaline phosphatase level; minor findings include the presence of inflammatory bowel disease (IBD) as well as histopathological findings of the liver [<span>1, 2</span>]. Regarding the treatment, liver transplantation is the only curative treatment, and ursodeoxycholic acid and bezafibrate are used as symptomatic treatments.</p><p>It means that endoscopy is not essential for the diagnosis and treatment of PSC; however, there are situations where endoscopic findings or treatment can contribute.</p><p>However, because endoscopic intervention for patients with PSC involves a high risk, appropriate patient selection is extremely important, so it is necessary to have a deep knowledge of the findings on the contribution of endoscopes to PSC to date.</p><p>In the latest issue of <i>Digestive Endoscopy</i>, Mizuno et al. presented an in-depth and interesting review, titled “Endoscopic management of primary sclerosing cholangitis” [<span>3</span>].</p><p>In this article, we discuss the contribution of endoscopic examinations in patients with PSC in light of this review.</p><p>Typical bile duct images are a key factor in the diagnosis of PSC. For a long time, bile duct imaging has been carried out using endoscopic retrograde cholangiography (ERC); however, it is impossible to inject contrast medium into all of the bile ducts, so it is impossible to evaluate the degree of all bile ducts. In addition, in cases where many bile duct strictures exist or the strictures are severe, there remains a risk of the contrast medium not being excreted, leading to postprocedural cholangitis or pancreatitis. Further, the management of cholangitis that occurs in conjunction with PSC can be extremely challenging. In addition, the corresponding radiation exposure not only affects endoscopists but also medical staff; thus, performing ERC without actual necessity is unacceptable [<span>4, 5</span>].</p><p>Magnetic resonance cholangiopancreatography (MRCP) has been reported to have both high diagnostic sensitivity and specificity and is recommended as the first-line diagnostic method for PSC [<span>1-3</span>]; thus, it is difficult to justify performing ERC for the sole purpose of cholangiography.</p><p>The greatest contribution of ERC to the diagnosis of PSC is that it can be used to obtain tissue samples for differentiation of PSC from bile duct cancer. The findings of bile duct stenosis in PSC are sometimes very similar to those in bile duct cancer. Moreover, it is reported that patients with PSC are at risk of developing bile duct cancer, with cumulative risks of 6%, 14%, and 20% at 10, 20, and 30 y
{"title":"Contribution of Endoscopy in the Diagnosis and Treatment of Patients With Primary Sclerosing Cholangitis","authors":"Mamoru Takenaka, Masatoshi Kudo","doi":"10.1111/den.15074","DOIUrl":"10.1111/den.15074","url":null,"abstract":"<p>Primary sclerosing cholangitis (PSC) is an autoimmune liver and biliary disease characterized by fibrotic narrowing of the bile ducts, leading to chronic bile stasis and eventually progressing to cirrhosis. However, to date, the etiology of PSC remains unknown.</p><p>A diagnosis of PSC is made based on the following major findings: typical bile duct images and elevated serum alkaline phosphatase level; minor findings include the presence of inflammatory bowel disease (IBD) as well as histopathological findings of the liver [<span>1, 2</span>]. Regarding the treatment, liver transplantation is the only curative treatment, and ursodeoxycholic acid and bezafibrate are used as symptomatic treatments.</p><p>It means that endoscopy is not essential for the diagnosis and treatment of PSC; however, there are situations where endoscopic findings or treatment can contribute.</p><p>However, because endoscopic intervention for patients with PSC involves a high risk, appropriate patient selection is extremely important, so it is necessary to have a deep knowledge of the findings on the contribution of endoscopes to PSC to date.</p><p>In the latest issue of <i>Digestive Endoscopy</i>, Mizuno et al. presented an in-depth and interesting review, titled “Endoscopic management of primary sclerosing cholangitis” [<span>3</span>].</p><p>In this article, we discuss the contribution of endoscopic examinations in patients with PSC in light of this review.</p><p>Typical bile duct images are a key factor in the diagnosis of PSC. For a long time, bile duct imaging has been carried out using endoscopic retrograde cholangiography (ERC); however, it is impossible to inject contrast medium into all of the bile ducts, so it is impossible to evaluate the degree of all bile ducts. In addition, in cases where many bile duct strictures exist or the strictures are severe, there remains a risk of the contrast medium not being excreted, leading to postprocedural cholangitis or pancreatitis. Further, the management of cholangitis that occurs in conjunction with PSC can be extremely challenging. In addition, the corresponding radiation exposure not only affects endoscopists but also medical staff; thus, performing ERC without actual necessity is unacceptable [<span>4, 5</span>].</p><p>Magnetic resonance cholangiopancreatography (MRCP) has been reported to have both high diagnostic sensitivity and specificity and is recommended as the first-line diagnostic method for PSC [<span>1-3</span>]; thus, it is difficult to justify performing ERC for the sole purpose of cholangiography.</p><p>The greatest contribution of ERC to the diagnosis of PSC is that it can be used to obtain tissue samples for differentiation of PSC from bile duct cancer. The findings of bile duct stenosis in PSC are sometimes very similar to those in bile duct cancer. Moreover, it is reported that patients with PSC are at risk of developing bile duct cancer, with cumulative risks of 6%, 14%, and 20% at 10, 20, and 30 y","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 10","pages":"1089-1091"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15074","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Non-Helicobacter pylori Helicobacter Infection in the Development of Gastric Mucosa-Associated Lymphoid Tissue Lymphoma and Characteristic Endoscopic Findings","authors":"Mitsushige Sugimoto, Masaki Murata","doi":"10.1111/den.15085","DOIUrl":"10.1111/den.15085","url":null,"abstract":"","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 11","pages":"1236-1238"},"PeriodicalIF":4.7,"publicationDate":"2025-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144546405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Research and development of artificial intelligence (AI) in the field of gastrointestinal endoscopy is progressing rapidly. In Japan alone, there are more than 10 AI-assisted endoscopic medical devices that have received regulatory approval, and numerous randomized controlled trials have been published both domestically and internationally. However, the adoption of AI in clinical practice has not been smooth due to factors such as insufficient evaluation of the balance between clinical benefits and harms, unclear cost-effectiveness, the lack of reliable guidelines, and the absence of established reimbursement systems for medical fees. Considering this situation, the Japan Gastroenterological Endoscopy Society (JGES) presents its perspective on the status of AI in endoscopic practice in the form of the following position statements. This comprises nine statements developed by the JGES AI Committee in collaboration with a diverse panel of members. These statements comprehensively address issues related to the quality of endoscopic examinations, cost-effectiveness, clinical disadvantages, preparatory knowledge, medical safety, and legal responsibilities. They have been developed to be practical and useful in actual endoscopy settings.
{"title":"Artificial Intelligence in Gastrointestinal Endoscopy: The Japan Gastroenterological Endoscopy Society Position Statements","authors":"Yuichi Mori, Ryu Ishihara, Haruhiko Ogata, Hiromu Kutsumi, Yutaka Saito, Kazuki Sumiyama, Masau Sekiguchi, Hisao Tajiri, Mitsuhiro Fujishiro, Koji Matsuda, Tomonori Yano, Rika Aoki, Misaki Ishiyama, Atsushi Imagawa, Masami Omae, Yasushi Oda, Motohiko Kato, Taku Sakamoto, Maasa Sasabe, Akiko Shiotani, Shiho Suzuki, Naoto Tamai, Takuto Hikichi, Toshiaki Hirasawa, Mai Makiguchi, Masashi Misawa, Yohei Yabuuchi, Daisuke Yamaguchi, Masayoshi Yamada, Yoshinori Igarashi, Shinji Tanaka","doi":"10.1111/den.15075","DOIUrl":"10.1111/den.15075","url":null,"abstract":"<div>\u0000 \u0000 <p>Research and development of artificial intelligence (AI) in the field of gastrointestinal endoscopy is progressing rapidly. In Japan alone, there are more than 10 AI-assisted endoscopic medical devices that have received regulatory approval, and numerous randomized controlled trials have been published both domestically and internationally. However, the adoption of AI in clinical practice has not been smooth due to factors such as insufficient evaluation of the balance between clinical benefits and harms, unclear cost-effectiveness, the lack of reliable guidelines, and the absence of established reimbursement systems for medical fees. Considering this situation, the Japan Gastroenterological Endoscopy Society (JGES) presents its perspective on the status of AI in endoscopic practice in the form of the following position statements. This comprises nine statements developed by the JGES AI Committee in collaboration with a diverse panel of members. These statements comprehensively address issues related to the quality of endoscopic examinations, cost-effectiveness, clinical disadvantages, preparatory knowledge, medical safety, and legal responsibilities. They have been developed to be practical and useful in actual endoscopy settings.</p>\u0000 </div>","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 10","pages":"1116-1122"},"PeriodicalIF":4.7,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144531386","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
<p>Since its inception 60 years ago [<span>1</span>], Artificial Intelligence (AI) has undergone complex evolvement. The last decade has seen its most rapid advancement, and AI is now an essential part of everyday life. The introduction of computer-aided diagnosis (CAD) to the realm of endoscopy brings a paradigm shift to medical diagnostics. Two of the most important applications of AI in endoscopy are computer-aided detection (CADe) and computer-aided diagnosis (CADx) [<span>2</span>]. Both these applications are developed by training AI models to detect vascular and mucosal patterns on mucosal lesions. However, in conditions such as achalasia, where specific lesions are not seen, this model of detection will not work. Therein lies a good reason for the study developed by Shiwaku and colleagues, which marks a different phase of CAD [<span>3</span>].</p><p>The study under discussion presents compelling evidence of CAD's potential to enhance the sensitivity and specificity of achalasia diagnosis, particularly among non-expert endoscopists. These findings highlight a transformative step in the democratization of medical expertise, where technology bridges the gap between novice and experienced clinicians. However, as with any innovation, the translation of these results into real-world clinical practice warrants careful scrutiny.</p><p>One of the most striking outcomes of this study is the dramatic improvement in sensitivity among inexperienced endoscopists, rising from 66.9% to 91.9% with CAD assistance. Even experienced practitioners benefited from CAD, with their sensitivity increasing from 79.5% to 90.8%. These findings suggest that CAD has the potential to mitigate diagnostic variability and significantly reduce the rate of missed achalasia cases. Given the availability of highly effective treatments, such as peroral endoscopic myotomy (POEM), improving early and accurate diagnosis is undoubtedly beneficial for optimizing patient outcomes.</p><p>Yet, despite these promising results, significant questions remain regarding CAD's application in real-world clinical settings. The study's limitations underscore certain critical challenges. Achalasia is a rare disease, and the artificially high prevalence of cases in this study (50% of the sample) does not reflect the reality of routine endoscopic practice. In an actual clinical setting, where achalasia cases are far less frequent, the performance of CAD may differ. The concern here is whether CAD will maintain its diagnostic power when faced with the complexities and unpredictability of daily endoscopic practice, where the pre-test probability of achalasia is much lower.</p><p>Another point of concern is the reliance on pre-selected video data, captured by a single expert. While this controlled setting ensures consistency in the dataset, it does not account for the real-life variability in endoscopic image quality, patient presentation, and operator technique. Additionally, the study does not addre
{"title":"The Promise and Challenges of CAD-Assisted Diagnosis in Achalasia","authors":"Niroshan Muwanwella, Krish Ragunath","doi":"10.1111/den.15076","DOIUrl":"10.1111/den.15076","url":null,"abstract":"<p>Since its inception 60 years ago [<span>1</span>], Artificial Intelligence (AI) has undergone complex evolvement. The last decade has seen its most rapid advancement, and AI is now an essential part of everyday life. The introduction of computer-aided diagnosis (CAD) to the realm of endoscopy brings a paradigm shift to medical diagnostics. Two of the most important applications of AI in endoscopy are computer-aided detection (CADe) and computer-aided diagnosis (CADx) [<span>2</span>]. Both these applications are developed by training AI models to detect vascular and mucosal patterns on mucosal lesions. However, in conditions such as achalasia, where specific lesions are not seen, this model of detection will not work. Therein lies a good reason for the study developed by Shiwaku and colleagues, which marks a different phase of CAD [<span>3</span>].</p><p>The study under discussion presents compelling evidence of CAD's potential to enhance the sensitivity and specificity of achalasia diagnosis, particularly among non-expert endoscopists. These findings highlight a transformative step in the democratization of medical expertise, where technology bridges the gap between novice and experienced clinicians. However, as with any innovation, the translation of these results into real-world clinical practice warrants careful scrutiny.</p><p>One of the most striking outcomes of this study is the dramatic improvement in sensitivity among inexperienced endoscopists, rising from 66.9% to 91.9% with CAD assistance. Even experienced practitioners benefited from CAD, with their sensitivity increasing from 79.5% to 90.8%. These findings suggest that CAD has the potential to mitigate diagnostic variability and significantly reduce the rate of missed achalasia cases. Given the availability of highly effective treatments, such as peroral endoscopic myotomy (POEM), improving early and accurate diagnosis is undoubtedly beneficial for optimizing patient outcomes.</p><p>Yet, despite these promising results, significant questions remain regarding CAD's application in real-world clinical settings. The study's limitations underscore certain critical challenges. Achalasia is a rare disease, and the artificially high prevalence of cases in this study (50% of the sample) does not reflect the reality of routine endoscopic practice. In an actual clinical setting, where achalasia cases are far less frequent, the performance of CAD may differ. The concern here is whether CAD will maintain its diagnostic power when faced with the complexities and unpredictability of daily endoscopic practice, where the pre-test probability of achalasia is much lower.</p><p>Another point of concern is the reliance on pre-selected video data, captured by a single expert. While this controlled setting ensures consistency in the dataset, it does not account for the real-life variability in endoscopic image quality, patient presentation, and operator technique. Additionally, the study does not addre","PeriodicalId":159,"journal":{"name":"Digestive Endoscopy","volume":"37 10","pages":"1092-1093"},"PeriodicalIF":4.7,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/den.15076","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144499689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号