dc.date.accessioned | 2023-02-01T09:57:53Z | |
dc.date.available | 2023-02-01T09:57:53Z | |
dc.date.issued | 2023 | |
dc.identifier.isbn | 978-82-348-0142-6 | |
dc.identifier.uri | http://hdl.handle.net/10852/99519 | |
dc.description.abstract | Colorectal cancer is considered a growing health burden and a preventable disease. It is the third most common cancer and the second leading cause of cancer death worldwide. Many countries have implemented colorectal cancer screening to reduce the risk of colorectal cancer incidence and mortality. Colonoscopy is considered the gold standard of colorectal cancer screening, but it is dependent on endoscopist performance and technology used. Novel technologies such as artificial intelligence (AI) targeting improved performance and standardization is expected to play a bigger role in colonoscopy screening in the future. Clinical validation of the efficacy of AI is important in the early adoption of AI-based tools. This thesis aims to investigate the clinical performance of AI to optimize colonoscopy for colorectal cancer screening.
The thesis includes a systematic review and meta-analysis of prospective trials to determine the value of AI-based polyp and colorectal cancer detection systems, an international multicenter clinical trial comparing an AI-based device for optical diagnosis of polyps to visual inspection, and lastly a clinical implementation trial to evaluate the performance of an AI-based speedometer that monitors withdrawal speed during colonoscopy.
The studies included in this thesis show no clear proof of benefit from AI-based tools in colonoscopy screening. However, the AI-based tools may cause harm and thus increase the burden of colorectal cancer screening. This thesis does not add to the hype, but rather adds to the current understanding of where AI falls short and what is needed in order to implement AI in colorectal cancer screening with colonoscopy in the future. | en_US |
dc.language.iso | en | en_US |
dc.relation.haspart | Article I: Artificial intelligence for polyp detection during colonoscopy: a systematic review and meta-analysis. Ishita Barua, Daniela Guerrero Vinsard, Henriette C. Jodal, Magnus Løberg, Mette Kalager, Øyvind Holme, Masashi Misawa, Michael Bretthauer, Yuichi Mori. Endoscopy 2021; 53:277-284. DOI: 10.1055/a-1201-7165. The paper is not available in DUO due to publisher restrictions. The published version is available at: https://doi.org/10.1055/a-1201-7165 | |
dc.relation.haspart | Article II: Real-Time AI-Based Optical Diagnosis of Neoplastic Polyps during Colonoscopy. Ishita Barua et al. New England Journal of Medicine Evidence 2022; DOI:10.1056/EVIDoa2200003. The article is included in the thesis. Also available at: https://doi.org/10.1056/EVIDoa2200003 | |
dc.relation.haspart | Article III: Speedometer for withdrawal time monitoring during colonoscopy: A clinical implementation trial. Ishita Barua et al. Manuscript. Published in Scandinavian Journal of Gastroenterology, 2022. DOI: 10.1080/00365521.2022.2154616. The article is included in the thesis. Also available at: https://doi.org/10.1080/00365521.2022.2154616 | |
dc.relation.uri | https://doi.org/10.1055/a-1201-7165 | |
dc.relation.uri | https://doi.org/10.1056/EVIDoa2200003 | |
dc.relation.uri | https://doi.org/10.1080/00365521.2022.2154616 | |
dc.title | Clinical Validation of Artificial Intelligence for Colorectal Cancer Screening with Colonoscopy | en_US |
dc.type | Doctoral thesis | en_US |
dc.creator.author | Barua, Ishita | |
dc.type.document | Doktoravhandling | en_US |