Related Experiment Video
Updated: Jan 15, 2026

E-Patient Counseling Trial E-PACO: Computer Based Education versus Nurse Counseling for Patients to Prepare for Colonoscopy
Published on: August 1, 2019
Artificial intelligence-assisted versus conventional reading in pan-intestinal capsule endoscopy for suspected
Bruno Rosa1,2, Miguel José Mascarenhas Saraiva3,4,5, João Afonso3,5
1Gastroenterology, Hospital da Senhora da Oliveira, Guimarães, Portugal bruno.joel.rosa@gmail.com.
Objective:
Pan-intestinal capsule endoscopy (PCE) offers a safer, more effective alternative to colonoscopy for detecting potentially haemorrhagic lesions (PHL) in suspected mid-lower gastrointestinal bleeding (MLGIB), though it is limited by time-consuming review and missed lesions. We compared the diagnostic performance of artificial intelligence-assisted PCE (AI-PCE) versus conventional reading PCE (CR-PCE) and colonoscopy.
Methods:
We retrospectively analysed 100 prospectively enrolled patients undergoing PCE for suspected MLGIB using an externally validated convolutional neural network. Diagnostic performance of AI-PCE, CR-PCE and colonoscopy was evaluated against a consensus reference standard. Accuracy metrics (sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV)) were assessed overall and by lesion type and intestinal segment.
Results:
AI-PCE detected PHL in 60% of patients versus 42% with CR-PCE (p<0.01). Lesions included vascular (51% vs 33%, p<0.01), ulcers/erosions (16% vs 7%, p=0.012), protuberant (5% vs 4%, p=1.0) and active bleeding (7% vs 7%, p=1.0). AI-PCE achieved higher sensitivity than CR-PCE (95% vs 67%, p<0.0001) with comparable specificity (97% vs 97%), PPV (98% vs 98%) and superior NPV (92% vs 63%, p=0.0015). For the small bowel, AI-PCE outperformed CR-PCE in sensitivity (96% vs 59%, p<0.0001) and NPV (97% vs 76%, p=0.0010). In colon, AI-PCE also showed greater sensitivity (90% vs 68%, p=0.027) and NPV (94% vs 86%, p = 0.066). Compared with colonoscopy, AI-PCE was markedly more sensitive (90% vs 32%, p<0.0001) with higher PPV (100% vs 65%, p<0.001) and NPV (94% vs 65%, p<0.0001).
Conclusion:
AI-PCE significantly improves diagnostic accuracy over conventional reading and colonoscopy, offering superior sensitivity without compromising specificity, and may establish a new standard for PCE in MLGIB.
Insights
Artificial intelligence-assisted capsule endoscopy (AI-PCE) significantly improves detection of potentially haemorrhagic lesions in mid-lower gastrointestinal bleeding compared to conventional methods. This AI-PCE offers higher sensitivity and NPV, potentially setting a new standard for diagnosis.
Area of Science:
- Gastroenterology
- Medical Imaging
- Artificial Intelligence
Background:
- Pan-intestinal capsule endoscopy (PCE) is a safer alternative to colonoscopy for detecting potentially haemorrhagic lesions (PHL) in suspected mid-lower gastrointestinal bleeding (MLGIB).
- Current PCE methods face limitations including time-consuming review and missed lesions.
- Artificial intelligence (AI) offers potential to enhance PCE diagnostic performance.
Purpose of the Study:
- To compare the diagnostic performance of AI-assisted PCE (AI-PCE) against conventional reading PCE (CR-PCE) and colonoscopy.
- To evaluate the accuracy of AI-PCE in detecting PHL in patients with suspected MLGIB.
Main Methods:
- Retrospective analysis of 100 prospectively enrolled patients undergoing PCE for suspected MLGIB.
- Utilized an externally validated convolutional neural network for AI-PCE analysis.
- Diagnostic performance metrics (sensitivity, specificity, PPV, NPV) were assessed against a consensus reference standard.
Main Results:
- AI-PCE detected PHL in 60% of patients, significantly higher than CR-PCE (42%, p<0.01).
- AI-PCE demonstrated superior sensitivity (95% vs 67%, p<0.0001) and NPV (92% vs 63%, p=0.0015) compared to CR-PCE.
- AI-PCE significantly outperformed colonoscopy in sensitivity (90% vs 32%, p<0.0001), PPV (100% vs 65%, p<0.001), and NPV (94% vs 65%, p<0.0001).
Conclusions:
- AI-PCE significantly enhances diagnostic accuracy for PHL detection in MLGIB.
- AI-PCE offers superior sensitivity and NPV without compromising specificity compared to conventional methods.
- AI-PCE may establish a new standard for capsule endoscopy in diagnosing mid-lower gastrointestinal bleeding.
More Related Videos
09:42Murine Endoscopy for In Vivo Multimodal Imaging of Carcinogenesis and Assessment of Intestinal Wound Healing and Inflammation
Published on: August 26, 2014
15:49Flexible Colonoscopy in Mice to Evaluate the Severity of Colitis and Colorectal Tumors Using a Validated Endoscopic Scoring System
Published on: October 16, 2013
Related Concept Videos
Endoscopic Procedures III: Video Capsule Endoscopy
Imaging Studies III: Gastrointestinal Motility Studies and Virtual Colonoscopy
Radionuclide Testing
Radionuclide testing is a sophisticated medical technique for assessing gastrointestinal motility. It focuses on gastric emptying and colonic transit time. Radioactive markers track the movement of food through the digestive system, providing insights into gastrointestinal disorders.
In gastric emptying studies, a meal's liquid and...
Endoscopic Procedures V: ERCP
Patient...