Status quo and future prospects of artificial neural network from the perspective of gastroenterologists

Abstract

Artificial neural networks (ANNs) are one of the primary types of artificial intelligence and have been rapidly developed and used in many fields. In recent years, there has been a sharp increase in research concerning ANNs in gastrointestinal (GI) diseases. This state-of-the-art technique exhibits excellent performance in diagnosis, prognostic prediction, and treatment. Competitions between ANNs and GI experts suggest that efficiency and accuracy might be compatible in virtue of technique advancements. However, the shortcomings of ANNs are not negligible and may induce alterations in many aspects of medical practice. In this review, we introduce basic knowledge about ANNs and summarize the current achievements of ANNs in GI diseases from the perspective of gastroenterologists. Existing limitations and future directions are also proposed to optimize ANN’s clinical potential. In consideration of barriers to interdisciplinary knowledge, sophisticated concepts are discussed using plain words and metaphors to make this review more easily understood by medical practitioners and the general public.

Use of artificial neural networks in the prognosis of musculoskeletal diseases—a scoping review

“…The advantages of ANN are mainly in the following three aspects: 1. Multi-layer network structure: ANN individual neurons cooperate with each other and form a network synergy when processing information, maintaining their independence while sharing and cascading the output results with other neurons, and making the results more reliable through the use of multiple hidden layers [ 47 , 48 ]; 2. Adaptive: According to the characteristics of the information in the input neural network, ANN can continuously establish new structures consistent with external changes through learning, extracting, and collecting information required for specific tasks from the data, and summarize the acquired knowledge, thereby improving the ability of data processing [ 49 ]; 3.…”

“…1. Multi-layer network structure: ANN individual neurons cooperate with each other and form a network synergy when processing information, maintaining their independence while sharing and cascading the output results with other neurons, and making the results more reliable through the use of multiple hidden layers [ 47 , 48 ];…”

Predicting Hepatotoxicity Associated with Low-Dose Methotrexate Using Machine Learning

“…The design of ANNs is based on the human brain’s neural network. Neurons in the different layers have their own missions to solve problems, which can be analogous to factory production lines [ 42 ]. As a type of parallel distributed system driven by mass data, ANNs are free from the requirements of logical or mathematical associations known beforehand [ 42 ].…”

Construction of a neural network diagnostic model and investigation of immune infiltration characteristics for Crohn’s disease

“…A recent study reported that Support Vector Machines and multi-layer neural network models were developed to predict a protein’s post translational modification sites, which contributed to solving a difficult problem in the field of molecular biology ( Bao et al, 2018 ). ANN have also increasingly been used in gastrointestinal disease because of its outstanding performance in diagnostic and prognostic prediction ( Cao et al, 2021 ). In the 1990s, Karakitsos et al reported the use of ANN to detect malignant gastric lesions with a discrimination performance of 97% ( Karakitsos et al, 1998 ).…”