[Effect of an artificial intelligence-assisted recognition system on colonoscopy quality].

Zhonghua Nei Ke Za Zhi

Department of Gastroenterology, the First Affiliated Hospital of Zhejiang Chinese Medical University, Zhejiang Provincial Hospital of Chinese Medicine, Hangzhou 310006, China.

Published: November 2024

To explore the value of the artificial intelligence (AI)-assisted recognition system in the detection quality of colonoscopy. From January 2023, the data on 700 patients who underwent colonoscopy in the Digestive Endoscopy Center of the First Affiliated Hospital of Zhejiang Chinese Medical University were collected prospectively. Based on a computerized number method, patients were divided into the AI assistance group and control group. The detection rate of adenomas (ADR) and polyps, number and size of adenomas, Boston bowel preparation scale (BBPS), intubation time, withdrawal time, and cecal intubation rate were compared between groups. Normally distributed data were analyzed with the -test for independent samples. Non-normally distributed data were analyzed with the Rank sum test. Categorical data were analyzed with the Chi-square test. In total, 691 patients were included in the analysis. According to the intention to treat (ITT) analysis and per-protocol (PP) analysis, the withdrawal time of the AI group was higher than that of the control group (ITT:436 (305, 620) vs 368 (265, 510) s, =-4.24, <0.001;PP:439 (306, 618) vs 364 (262, 500) s,=-4.50, <0.001); however, there were no significant differences in the ADR (ITT:123(35.5%) vs 111(32.2%), =0.88, =0.349;PP:108(34.2%) vs 99(31.1%), =0.67, =0.414), the number of adenomas (ITT:0(0, 1) vs 0(0, 1),=-1.08, =0.282;PP:0(0, 1) vs 0(0, 1),=-0.87, =0.387), the polyp detection rate (ITT:85(24.6%) vs 85(24.6%),=0.001, =0.983;PP:79(25.0%) vs 77(24.2%),=0.05, =0.818), BBPS (ITT:6.5±0.9 vs 6.5±0.7,=-0.59, =0.555;PP:6.7±0.6 vs 6.6±0.6,=-1.83, P=0.068), and cecal intubation rate (ITT:346(100.0%) vs 343(99.4%), =0.50, =0.478) between these two groups. After excluding inadequate bowel preparation and failed cecal intubation cases, the AI-assisted system was found to significantly improve the detection rate of small adenomas (≤5 mm) (PP:27.8%(88/316)vs 21.1%(67/318), =3.94, =0.047). The application of an AI-assisted system in colonoscopy can increase the withdrawal time and improve the detection rate of small adenomas.

Download full-text PDF

Source
http://dx.doi.org/10.3760/cma.j.cn112138-20240216-00109DOI Listing

Publication Analysis

Top Keywords

data analyzed
12
recognition system
8
control group
8
withdrawal time
8
distributed data
8
[effect artificial
4
artificial intelligence-assisted
4
intelligence-assisted recognition
4
system colonoscopy
4
colonoscopy quality]
4

Similar Publications

Exploring the Role of Immersive Virtual Reality Simulation in Health Professions Education: Thematic Analysis.

JMIR Med Educ

March 2025

Division of Pulmonary, Critical Care, & Sleep Medicine, Department of Medicine, NYU Grossman School of Medicine, 550 First Avenue, 15th Floor, Medical ICU, New York, NY, 10016, United States, 1 2122635800.

Background: Although technology is rapidly advancing in immersive virtual reality (VR) simulation, there is a paucity of literature to guide its implementation into health professions education, and there are no described best practices for the development of this evolving technology.

Objective: We conducted a qualitative study using semistructured interviews with early adopters of immersive VR simulation technology to investigate use and motivations behind using this technology in educational practice, and to identify the educational needs that this technology can address.

Methods: We conducted 16 interviews with VR early adopters.

View Article and Find Full Text PDF

Background: Congenital cytomegalovirus is the leading cause of nongenetic sensorineural hearing loss. Treatment with (val)ganciclovir improves audiologic outcomes. Neutropenia is a common adverse event, but correlates that predict who will develop neutropenia have not been identified.

View Article and Find Full Text PDF

CAD manipulates tumor intrinsic DHO/UBE4B/NF-κB pathway and fuels macrophage cross-talk, promoting hepatocellular carcinoma metastasis.

Hepatology

March 2025

Department of Liver Surgery and Transplantation, Liver Cancer Institute and Zhongshan Hospital, Fudan University, Shanghai, China.

Background And Aims: Portal vein tumor thrombosis (PVTT), an indicator of clinical metastasis, significantly shortens hepatocellular carcinoma (HCC) patients' lifespan, and no effective treatment has been established. We aimed to illustrate mechanisms underlying PVTT formation and tumor metastasis, and identified potential targets for clinical intervention.

Approach And Results: Multi-omics data of 159 HCC patients (including 37 cases with PVTT) was analyzed to identify contributors to PVTT formation and tumor metastasis.

View Article and Find Full Text PDF

Objectives: This study evaluates a staged selective hybrid approach for acute type A aortic dissection. The approach involves a zone 2 aortic arch replacement with debranching of the brachiocephalic trunk and left common carotid artery to create a landing zone for thoracic endovascular aortic repair. This repair is performed either preemptively in the subacute phase to promote remodelling or electively in the chronic phase to manage aneurysm formation.

View Article and Find Full Text PDF

Introduction: Insurance type can result in disparities in access to specialist orthopaedic care. Here, we sought to quantify how insurance type affects time to surgery in patients with a distal radius fracture that needs surgical treatment.

Methods: A retrospective cohort study of patients ≥18 years with surgically managed, closed distal radius fractures was conducted.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!