Gastroenterology Meets Machine Learning: Status Quo and Quo Vadis.

Amina Adadi,Mohammed Berrada,Safae Adadi

doi:10.1155/2019/1870975

Abstract

Machine learning has undergone a transition phase from being a pure statistical tool to being one of the main drivers of modern medicine. In gastroenterology, this technology is motivating a growing number of studies that rely on these innovative methods to deal with critical issues related to this practice. Hence, in the light of the burgeoning research on the use of machine learning in gastroenterology, a systematic review of the literature is timely. In this work, we present the results gleaned through a systematic review of prominent gastroenterology literature using machine learning techniques. Based on the analysis of 88 journal articles, we delimit the scope of application, we discuss current limitations including bias, lack of transparency, accountability, and data availability, and we put forward future avenues.

Highlights

IntroductionMachine learning (ML) has got the bulk of attention. Powered by an influx of big data and advancements in computing power and coupled with considerable enthusiasm in the mainstream media, this exciting technology is driving major industry transformations
In recent years, machine learning (ML) has got the bulk of attention
Our search strings are formed by the union of the words “Machine Learning” and a set of related terms including “Artificial Intelligence” as ML is a subfield of artificial intelligence (AI), “Data Mining” as in many works ML technique (MLT) are mentioned as data mining techniques, “Neural Network”, and “Deep Learning”; though DL is a MLT, because of its popularity it begins to be referred to as a standalone technique; we considered this key-phrase explicitly

Summary

Introduction

Machine learning (ML) has got the bulk of attention. Powered by an influx of big data and advancements in computing power and coupled with considerable enthusiasm in the mainstream media, this exciting technology is driving major industry transformations. ML encompasses a broad set of techniques inspired by human learning and reasoning systems; they share the same basic functioning, that is, to establish the extent to which the past is likely to be an accurate guide to the future. Endowed with this faculty of learning, these techniques are capable of analyzing large amounts of data, extracting (that is, learning) information from them, and driving automatic decisions. The core function of ML is to discover patterns in data that lead to actionable insights It includes a broad class of algorithms that share the capability of learning from previous experience to improve future performance. “Multivariable adaptive artificial pancreas system in type 1 diabetes,” Current Diabetes Reports, vol 17, no. 10, 2017

Methods

Results

Discussion

Conclusion