Review
Copyright ©The Author(s) 2022.
World J Gastroenterol. Dec 21, 2022; 28(47): 6632-6661
Published online Dec 21, 2022. doi: 10.3748/wjg.v28.i47.6632
Table 4 Studies on the accuracy of AI for polyp histology prediction
Ref.
Study type
Imaging modality
Number of patients/polyps
Sensitivity
Specificity
NPV
Accurate surveillance interval
Kominami et al[209], 2016RetrospectiveNBI41 patients, 118 polyps93%95%93%92.7%
Chen et al[210], 2018RetrospectiveNBI284 polyps96%78%90%-
Mori et al[211], 2018ProspectiveNBI325 patients, 466 polyps93%90%95%-
Renner et al[212], 2018RetrospectiveWLI, NBI100 polyps92%63%90%-
Byrne et al[213], 2019RetrospectiveNBI125 polyps98%83%97%-
Min et al[214], 2019ProspectiveLCI91 patients, 217 polyps83%70%71%-
Sánchez-Montes et al[206], 2019RetrospectiveWLI225 polyps92%89%87%-
Horiuchi et al[215], 2019ProspectiveAFI95 patients, 258 polyps80%95%93%-
Ozawa et al[216], 2020RetrospectiveWLI, NBI309 polyps97% for NBI, 90% for WLI-91% for NBI, 85% for WLI-
Jin et al[205], 2020RetrospectiveNBI300 polyps83%90%94%-
Zacharia et al[208], 2020RetrospectiveWLI, NBI524 polyps96%90%93%94%
Rodriguez-Diaz et al[217], 2021RetrospectiveNBI119 patients, 280 polyps96%84%91%94%
Van der Zander et al[218], 2021RetrospectiveWLI, BLI54 patients, 60 polyps96%93%88%-
Yoshida et al[220], 2021RetrospectiveBLI25 patients, 100 polyps91%85%92%-
Sakamoto et al[219], 2022RetrospectiveWLI, BLI604 polyps96% for WLI, 96% for BLI84% for WLI, 89% for BLI--