Techniques to integrate artificial intelligence systems with medical information in gastroenterology

Table 1 Detailed information on the studies concerning the diagnosis of polyps and neoplasms in the gastrointestinal tract published after 2018

Ref.	Training	Validation	AUC	Sensitivity	Accuracy
Chen et al[51], 2018	1476 images of neoplasms; 681 images of H. pylori	188 images of neoplasms; 96 images of H. pylori	NA	96.3%	90.1%
Urban et al[16], 2018	8641 images; 9 videos	1330 images; 9 videos	0.974	NA	96.4%
Misawa et al[15], 2018	73 videos	Cross validation	NA	90%	76.5%
Yamada et al[56], 2019	4087 images of polyps; videos	705 images with polyps; 4135 images without polyps	0.975	97.3%	NA
Klare et al[57], 2019	NA	55 colonoscopy examination videos	NA	75.3%	NA
Wang et al[17], 2019	3634 images with polyps; 1911 images without polyps	5541 images with polyps and 21572 images without polyps	0.984	94.4%	NA
Song et al[58], 2020	12480 images	545 images	0.93	82.1%	81.3%
Zachariah et al[59], 2020	8246 images	634 images	NA	96%	94%

H. pylori: Helicobacter pylori; AUC: Area under curve; NA: Not applicable.