Letter to the Editor
Copyright ©The Author(s) 2022. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Feb 7, 2022; 28(5): 602-604
Published online Feb 7, 2022. doi: 10.3748/wjg.v28.i5.602
Artificial intelligence model validation before its application in clinical diagnosis assistance
Gustavo Jesus Vazquez-Zapien, Monica Maribel Mata-Miranda, Francisco Garibay-Gonzalez, Miguel Sanchez-Brito
Gustavo Jesus Vazquez-Zapien, Embryology Lab, Escuela Militar de Medicina, Ciudad de Mexico 11200, CDMX, Mexico
Monica Maribel Mata-Miranda, Cell & Tissue Biology Lab, Escuela Militar de Medicina, Ciudad de Mexico 11200, CDMX, Mexico
Francisco Garibay-Gonzalez, Department of Research, Escuela Militar de Medicina, Ciudad de Mexico 11200, CDMX, Mexico
Miguel Sanchez-Brito, Instituto Tecnológico de Zacatepec, Industrial Engineering, TecNM, Zacatepec 62780, Morelos, Mexico
Miguel Sanchez-Brito, Instituto Tecnológico de Aguascalientes, Computational Sciences, TecNM, Aguascalientes 20256, Mexico
Author contributions: Vazquez-Zapien GJ and Sanchez-Brito M designed the research; all authors contributed to the writing and revision of the letter.
Supported by SEDENA Budgetary Program, No. A022-2021.
Conflict-of-interest statement: The authors declare having no competing interests.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/Licenses/by-nc/4.0/
Corresponding author: Miguel Sanchez-Brito, MD, PhD, Research Assistant Professor, Instituto Tecnológico de Zacatepec, Industrial Engineering, TecNM, Plan de Ayala, Zacatepec 62780, Morelos, Mexico. miguel.sb@zacatepec.tecnm.mx
Received: July 27, 2021
Peer-review started: July 27, 2021
First decision: October 3, 2021
Revised: October 7, 2021
Accepted: January 17, 2022
Article in press: January 17, 2022
Published online: February 7, 2022
Abstract

The process of selecting an artificial intelligence (AI) model to assist clinical diagnosis of a particular pathology and its validation tests is relevant since the values of accuracy, sensitivity and specificity may not reflect the behavior of the method in a real environment. Here, we provide helpful considerations to increase the success of using an AI model in clinical practice.

Keywords: Artificial intelligence, Diagnostic assistance, Validation tests, Leave-one-out cross-validation, K-fold validation, Hold-out validation

Core tip: The validation tests and the process to adopt a particular artificial intelligence (AI) model are relevant. The percentages of accuracy, sensitivity and specificity obtained through validation techniques are strong indicators of whether the AI model is suitable for implementation in clinical practice or whether it will be necessary to continue acquiring samples.