RESUMEN
AIM: Lower gastrointestinal (GI) diagnostics have been facing relentless capacity constraints for many years, even before the COVID-19 era. Restrictions from the COVID pandemic have resulted in a significant backlog in lower GI diagnostics. Given recent developments in deep neural networks (DNNs) and the application of artificial intelligence (AI) in endoscopy, automating capsule video analysis is now within reach. Comparable to the efficiency and accuracy of AI applications in small bowel capsule endoscopy, AI in colon capsule analysis will also improve the efficiency of video reading and address the relentless demand on lower GI services. The aim of the CESCAIL study is to determine the feasibility, accuracy and productivity of AI-enabled analysis tools (AiSPEED) for polyp detection compared with the 'gold standard': a conventional care pathway with clinician analysis. METHOD: This multi-centre, diagnostic accuracy study aims to recruit 674 participants retrospectively and prospectively from centres conducting colon capsule endoscopy (CCE) as part of their standard care pathway. After the study participants have undergone CCE, the colon capsule videos will be uploaded onto two different pathways: AI-enabled video analysis and the gold standard conventional clinician analysis pathway. The reports generated from both pathways will be compared for accuracy (sensitivity and specificity). The reading time can only be compared in the prospective cohort. In addition to validating the AI tool, this study will also provide observational data concerning its use to assess the pathway execution in real-world performance. RESULTS: The study is currently recruiting participants at multiple centres within the United Kingdom and is at the stage of collecting data. CONCLUSION: This standard diagnostic accuracy study carries no additional risk to patients as it does not affect the standard care pathway, and hence patient care remains unaffected.
Asunto(s)
COVID-19 , Endoscopía Capsular , Pólipos del Colon , Humanos , Pólipos del Colon/diagnóstico , Endoscopía Capsular/métodos , Inteligencia Artificial , Estudios Prospectivos , Estudios Retrospectivos , COVID-19/diagnósticoRESUMEN
OBJECTIVES: Endoscopic resection (ER) including endoscopic submucosal dissection has been widely accepted for treatment of early gastric cancer (EGC) in Japan. Additional surgery is recommended when ER is non-curative histologically. Many elderly patients, however, do not undergo radical surgery due to comorbid disease or limited life expectancy. The aim of this study is to assess the survival outcomes of radical surgery compared with observation only in elderly patients after non-curative ER. METHODS: We reviewed existing data of all elderly patients (older than 75 years) who had undergone ER for EGC at the National Cancer Center Hospital between January 1999 and December 2005. We compared the overall and disease-free survival rates between three patients groups: curative ER, non-curative ER with additional surgery, and non-curative ER without additional surgery. RESULTS: In total, 428 patients underwent ER; 308 (72%) curative ER and 120 (28%) non-curative ER. Of the 120 non-curative ER patients, 38 patients (31.7%) underwent additional surgery and 82 patients (68.3%) were followed without surgery. There was no significant difference in American Society of Anesthesiologist score between three groups. Patients who did not undergo surgery tended to be older. Overall 5-year survival rates in the curative ER, non-curative ER with surgery, and non-curative ER without surgery were 85, 92, and 63%, respectively. There was no significant difference in overall and disease-free survival between patients in the curative ER and non-curative ER with surgery groups. On the contrary, a significant difference in overall and disease-free survival was evident between the curative ER and non-curative ER without surgery groups (hazard ratio (95% confidence interval): 1.89 (1.08-3.28), 2.30 (1.35-3.94)). CONCLUSIONS: In our elderly patient cohort, additional surgery following non-curative ER improved overall and disease-free survival compared with non-surgical observation only. Thus, surgery should be considered following non-curative ER in EGC patients >75 years of age.
Asunto(s)
Adenocarcinoma/cirugía , Gastroscopía/métodos , Recurrencia Local de Neoplasia/cirugía , Neoplasias Gástricas/cirugía , Adenocarcinoma/mortalidad , Adenocarcinoma/patología , Factores de Edad , Anciano , Anciano de 80 o más Años , Estudios de Cohortes , Intervalos de Confianza , Supervivencia sin Enfermedad , Femenino , Estudios de Seguimiento , Gastrectomía/métodos , Evaluación Geriátrica , Humanos , Japón , Estimación de Kaplan-Meier , Laparotomía/métodos , Masculino , Procedimientos Quirúrgicos Mínimamente Invasivos/métodos , Monitoreo Fisiológico/métodos , Recurrencia Local de Neoplasia/mortalidad , Recurrencia Local de Neoplasia/patología , Estadificación de Neoplasias , Modelos de Riesgos Proporcionales , Reoperación/métodos , Estudios Retrospectivos , Medición de Riesgo , Neoplasias Gástricas/mortalidad , Neoplasias Gástricas/patología , Análisis de Supervivencia , Factores de Tiempo , Resultado del TratamientoRESUMEN
Curative endoscopic resection is now a viable option for a range of neoplastic lesions of the gastrointestinal tract (GIT) with low invasive potential. Risk of lymph node metastasis is the most important prognostic factor in selecting appropriate lesions for endoscopic therapy, and assessment of invasion depth is vital in this respect. To determine appropriate treatment, detailed endoscopic diagnosis and estimation of depth using magnifying chromoendoscopy is the gold standard in Japan. En bloc resection is the most desirable endoscopic therapy as risk of local recurrence is low and accurate histological diagnosis of invasion depth is possible. Endoscopic mucosal resection is established worldwide for the ablation of early neoplasms, but en bloc removal using this technique is limited to small lesions. Evidence suggests that a piecemeal resection technique has a higher local recurrence risk, therefore necessitating repeated surveillance endoscopy and further therapy. More advanced endoscopic techniques developed in Japan allow effective en bloc removal of early GIT neoplasms, regardless of size. This review discusses assessment of GIT lesions and options for endoscopic therapy with special reference to the introduction of endoscopic submucosal dissection into Western countries.