Ilmu Komputer & AI editorial
Open AccessOA2023
What Is Machine Learning, Artificial Neural Networks and Deep Learning?—Examples of Practical Applications in Medicine
This digest summarizes the review by Kufel et al. on machine learning, artificial neural networks, and deep learning, highlighting their definitions and practical medical applications. It outlines the IMRAD structure and key takeaways from the paper.
J. Kufel; Katarzyna Bargieł-Łączek; S. Kocot; M. Koźlik; W. Bartnikowska; Michał Janik; Łukasz Czogalik; Piotr Dudek; Mikołaj Magiera; A. Lis; I. Paszkiewicz; Z. Nawrat; Maciej M. Cebula; K. Gruszczyńska· Diagnostics· 2023· DOI 10.3390/diagnostics13152582
The core problem
The paper introduces artificial intelligence (AI) and its subfields—machine learning (ML), artificial neural networks (ANNs), and deep learning (DL)—which have gained popularity in recent years. The authors aim to clarify these concepts and provide examples of their practical applications in medicine. The introduction sets the stage by defining AI as the overarching field and positioning ML, ANNs, and DL as interconnected techniques that are increasingly used to improve disease diagnosis and treatment.
Innovation
As a review article, the methodology involves a literature review of existing research on ML, ANNs, and DL in medicine. The authors synthesize definitions and applications, providing a structured overview. Each AI technique is supported with an example of a possible medical application, illustrating how these methods are being implemented in clinical contexts. The paper likely draws from peer-reviewed studies and reports to present a balanced perspective on the current state and future potential of AI in healthcare.
Introduction
The paper introduces artificial intelligence (AI) and its subfields—machine learning (ML), artificial neural networks (ANNs), and deep learning (DL)—which have gained popularity in recent years. The authors aim to clarify these concepts and provide examples of their practical applications in medicine. The introduction sets the stage by defining AI as the overarching field and positioning ML, ANNs, and DL as interconnected techniques that are increasingly used to improve disease diagnosis and treatment.
Why it matters
The discussion emphasizes the importance of monitoring the development of AI in medicine and conducting further research to fully explore the potential of ML, ANNs, and DL. The authors highlight that while these techniques show promise, there are challenges to overcome before widespread clinical adoption, such as data quality, interpretability, and regulatory considerations. They conclude that continued research is essential to bring further applications into clinical use in the future. The paper underscores the need for interdisciplinary collaboration and robust validation to ensure safety and efficacy in patient care.
Who should read this
Pembaca Research Digest dan praktisi rumpun ini.
Opening member content…