Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial
Objective Colorectal cancer (CRC) has a significant role in cancer-related mortality. Colonoscopy, combined with adenoma removal, has proven effective in reducing CRC incidence. However, suboptimal colonoscopy quality often leads to missed polyps. The impact of artificial intelligence (AI) on adenom...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMJ Publishing Group
2024-01-01
|
| Series: | BMJ Open Gastroenterology |
| Online Access: | https://bmjopengastro.bmj.com/content/11/1/e001247.full |
| _version_ | 1797338610752552960 |
|---|---|
| author | Per Hedenström Thomas de Lange Jonas Varkey Johanna Schöler Marko Alavanja Shunsuke Yamamoto |
| author_facet | Per Hedenström Thomas de Lange Jonas Varkey Johanna Schöler Marko Alavanja Shunsuke Yamamoto |
| author_sort | Per Hedenström |
| collection | DOAJ |
| description | Objective Colorectal cancer (CRC) has a significant role in cancer-related mortality. Colonoscopy, combined with adenoma removal, has proven effective in reducing CRC incidence. However, suboptimal colonoscopy quality often leads to missed polyps. The impact of artificial intelligence (AI) on adenoma and polyp detection rate (ADR, PDR) is yet to be established.Design We conducted a randomised controlled trial at Sahlgrenska University Hospital in Sweden. Patients underwent colonoscopy with or without the assistance of AI (AI-C or conventional colonoscopy (CC)). Examinations were performed with two different AI systems, that is, Fujifilm CADEye and Medtronic GI Genius. The primary outcome was ADR.Results Among 286 patients, 240 underwent analysis (average age: 66 years). The ADR was 42% for all patients, and no significant difference emerged between AI-C and CC groups (41% vs 43%). The overall PDR was 61%, with a trend towards higher PDR in the AI-C group. Subgroup analysis revealed higher detection rates for sessile serrated lesions (SSL) with AI assistance (AI-C 22%, CC 11%, p=0.004). No difference was noticed in the detection of polyps or adenomas per colonoscopy. Examinations were most often performed by experienced endoscopists, 78% (n=86 AI-C, 100 CC).Conclusion Amidst the ongoing AI integration, ADR did not improve with AI. Particularly noteworthy is the enhanced detection rates for SSL by AI assistance, especially since they pose a risk for postcolonoscopy CRC. The integration of AI into standard colonoscopy practice warrants further investigation and the development of improved software might be necessary before enforcing its mandatory implementation.Trial registration number NCT05178095. |
| first_indexed | 2024-03-08T09:32:48Z |
| format | Article |
| id | doaj.art-54c928046675456b8642101e7445243d |
| institution | Directory Open Access Journal |
| issn | 2054-4774 |
| language | English |
| last_indexed | 2024-03-08T09:32:48Z |
| publishDate | 2024-01-01 |
| publisher | BMJ Publishing Group |
| record_format | Article |
| series | BMJ Open Gastroenterology |
| spelling | doaj.art-54c928046675456b8642101e7445243d2024-01-30T17:25:08ZengBMJ Publishing GroupBMJ Open Gastroenterology2054-47742024-01-0111110.1136/bmjgast-2023-001247Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trialPer Hedenström0Thomas de Lange1Jonas Varkey2Johanna Schöler3Marko Alavanja4Shunsuke Yamamoto5Medical Department, Sahlgrenska University Hospital, Goteborg, SwedenMedical Department, Sahlgrenska University Hospital, Goteborg, SwedenDepartment of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Goteborg, SwedenMedical Department, Sahlgrenska University Hospital, Goteborg, SwedenDepartment of Molecular and Clinical Medicine, Institute of Medicine, University of Gothenburg, Goteborg, SwedenDepartment of Medicine, Sahlgrenska University Hospital, Goteborg, SwedenObjective Colorectal cancer (CRC) has a significant role in cancer-related mortality. Colonoscopy, combined with adenoma removal, has proven effective in reducing CRC incidence. However, suboptimal colonoscopy quality often leads to missed polyps. The impact of artificial intelligence (AI) on adenoma and polyp detection rate (ADR, PDR) is yet to be established.Design We conducted a randomised controlled trial at Sahlgrenska University Hospital in Sweden. Patients underwent colonoscopy with or without the assistance of AI (AI-C or conventional colonoscopy (CC)). Examinations were performed with two different AI systems, that is, Fujifilm CADEye and Medtronic GI Genius. The primary outcome was ADR.Results Among 286 patients, 240 underwent analysis (average age: 66 years). The ADR was 42% for all patients, and no significant difference emerged between AI-C and CC groups (41% vs 43%). The overall PDR was 61%, with a trend towards higher PDR in the AI-C group. Subgroup analysis revealed higher detection rates for sessile serrated lesions (SSL) with AI assistance (AI-C 22%, CC 11%, p=0.004). No difference was noticed in the detection of polyps or adenomas per colonoscopy. Examinations were most often performed by experienced endoscopists, 78% (n=86 AI-C, 100 CC).Conclusion Amidst the ongoing AI integration, ADR did not improve with AI. Particularly noteworthy is the enhanced detection rates for SSL by AI assistance, especially since they pose a risk for postcolonoscopy CRC. The integration of AI into standard colonoscopy practice warrants further investigation and the development of improved software might be necessary before enforcing its mandatory implementation.Trial registration number NCT05178095.https://bmjopengastro.bmj.com/content/11/1/e001247.full |
| spellingShingle | Per Hedenström Thomas de Lange Jonas Varkey Johanna Schöler Marko Alavanja Shunsuke Yamamoto Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial BMJ Open Gastroenterology |
| title | Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial |
| title_full | Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial |
| title_fullStr | Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial |
| title_full_unstemmed | Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial |
| title_short | Impact of AI-aided colonoscopy in clinical practice: a prospective randomised controlled trial |
| title_sort | impact of ai aided colonoscopy in clinical practice a prospective randomised controlled trial |
| url | https://bmjopengastro.bmj.com/content/11/1/e001247.full |
| work_keys_str_mv | AT perhedenstrom impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial AT thomasdelange impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial AT jonasvarkey impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial AT johannascholer impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial AT markoalavanja impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial AT shunsukeyamamoto impactofaiaidedcolonoscopyinclinicalpracticeaprospectiverandomisedcontrolledtrial |