Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning
In the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques that allow machines to learn and get better at tasks such as recognition and prediction, which form the basis of clinical practice, are referr...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Galenos Publishing House
2023-01-01
|
Series: | Balkan Medical Journal |
Online Access: | http://www.balkanmedicaljournal.org/text.php?lang=en&id=2461 |
_version_ | 1797916867337125888 |
---|---|
author | Burak Koçak Renato Cuocolo Daniel Pinto dos Santos Arnaldo Stanzione Lorenzo Ugga |
author_facet | Burak Koçak Renato Cuocolo Daniel Pinto dos Santos Arnaldo Stanzione Lorenzo Ugga |
author_sort | Burak Koçak |
collection | DOAJ |
description | In the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques that allow machines to learn and get better at tasks such as recognition and prediction, which form the basis of clinical practice, are referred to as machine learning, which is a subfield of artificial intelligence. The number of artificial intelligence- and machine learnings-related publications in clinical journals has grown exponentially, driven by recent developments in computation and the accessibility of simple tools. However, clinicians are often not included in data science teams, which may limit the clinical relevance, explanability, workflow compatibility, and quality improvement of artificial intelligence solutions. Thus, this results in the language barrier between clinicians and artificial intelligence developers. Healthcare practitioners sometimes lack a basic understanding of artificial intelligence research because the approach is difficult for non-specialists to understand. Furthermore, many editors and reviewers of medical publications might not be familiar with the fundamental ideas behind these technologies, which may prevent journals from publishing high-quality artificial intelligence studies or, worse still, could allow for the publication of low-quality works. In this review, we aim to improve readers’ artificial intelligence literacy and critical thinking. As a result, we concentrated on what we consider the 10 most important qualities of artificial intelligence research: valid scientific purpose, high-quality data set, robust reference standard, robust input, no information leakage, optimal bias-variance tradeoff, proper model evaluation, proven clinical utility, transparent reporting, and open science. Before designing a study, one should have defined a sound scientific purpose. Then, it should be backed by a high-quality data set, robust input, and a solid reference standard. The artificial intelligence development pipeline should prevent information leakage. For the models, optimal bias-variance tradeoff should be achieved, and generalizability assessment must be adequately performed. The clinical value of the final models must also be established. After the study, thought should be given to transparency in publishing the process and results as well as open science for sharing data, code, and models. We hope this work may improve the artificial intelligence literacy and mindset of the readers. |
first_indexed | 2024-04-10T13:05:13Z |
format | Article |
id | doaj.art-b7e4a0b6a8d443978f54f6b0eb03087c |
institution | Directory Open Access Journal |
issn | 2146-3123 2146-3131 |
language | English |
last_indexed | 2024-04-10T13:05:13Z |
publishDate | 2023-01-01 |
publisher | Galenos Publishing House |
record_format | Article |
series | Balkan Medical Journal |
spelling | doaj.art-b7e4a0b6a8d443978f54f6b0eb03087c2023-02-15T16:13:00ZengGalenos Publishing HouseBalkan Medical Journal2146-31232146-31312023-01-0140131210.4274/balkanmedj.galenos.2022.2022-11-51Must-have Qualities of Clinical Research on Artificial Intelligence and Machine LearningBurak Koçak0https://orcid.org/0000-0002-7307-396XRenato Cuocolo1https://orcid.org/0000-0002-1452-1574Daniel Pinto dos Santos2https://orcid.org/0000-0003-4785-6394Arnaldo Stanzione3https://orcid.org/0000-0002-7905-5789Lorenzo Ugga4https://orcid.org/0000-0001-7811-4612Clinic of Radiology, University of Health Sciences Turkey, Başakşehir Çam and Sakura City Hospital, İstanbul, TurkeyDepartment of Medicine, Surgery and Dentistry University of Salerno, Baronissi, ItalyDepartment of Radiology, University Hospital of Cologne, Cologne, GermanyDepartment of Advanced Biomedical Sciences, University of Naples “Federico II”, Napoli, ItalyDepartment of Advanced Biomedical Sciences, University of Naples “Federico II”, Napoli, ItalyIn the field of computer science, known as artificial intelligence, algorithms imitate reasoning tasks that are typically performed by humans. The techniques that allow machines to learn and get better at tasks such as recognition and prediction, which form the basis of clinical practice, are referred to as machine learning, which is a subfield of artificial intelligence. The number of artificial intelligence- and machine learnings-related publications in clinical journals has grown exponentially, driven by recent developments in computation and the accessibility of simple tools. However, clinicians are often not included in data science teams, which may limit the clinical relevance, explanability, workflow compatibility, and quality improvement of artificial intelligence solutions. Thus, this results in the language barrier between clinicians and artificial intelligence developers. Healthcare practitioners sometimes lack a basic understanding of artificial intelligence research because the approach is difficult for non-specialists to understand. Furthermore, many editors and reviewers of medical publications might not be familiar with the fundamental ideas behind these technologies, which may prevent journals from publishing high-quality artificial intelligence studies or, worse still, could allow for the publication of low-quality works. In this review, we aim to improve readers’ artificial intelligence literacy and critical thinking. As a result, we concentrated on what we consider the 10 most important qualities of artificial intelligence research: valid scientific purpose, high-quality data set, robust reference standard, robust input, no information leakage, optimal bias-variance tradeoff, proper model evaluation, proven clinical utility, transparent reporting, and open science. Before designing a study, one should have defined a sound scientific purpose. Then, it should be backed by a high-quality data set, robust input, and a solid reference standard. The artificial intelligence development pipeline should prevent information leakage. For the models, optimal bias-variance tradeoff should be achieved, and generalizability assessment must be adequately performed. The clinical value of the final models must also be established. After the study, thought should be given to transparency in publishing the process and results as well as open science for sharing data, code, and models. We hope this work may improve the artificial intelligence literacy and mindset of the readers.http://www.balkanmedicaljournal.org/text.php?lang=en&id=2461 |
spellingShingle | Burak Koçak Renato Cuocolo Daniel Pinto dos Santos Arnaldo Stanzione Lorenzo Ugga Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning Balkan Medical Journal |
title | Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning |
title_full | Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning |
title_fullStr | Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning |
title_full_unstemmed | Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning |
title_short | Must-have Qualities of Clinical Research on Artificial Intelligence and Machine Learning |
title_sort | must have qualities of clinical research on artificial intelligence and machine learning |
url | http://www.balkanmedicaljournal.org/text.php?lang=en&id=2461 |
work_keys_str_mv | AT burakkocak musthavequalitiesofclinicalresearchonartificialintelligenceandmachinelearning AT renatocuocolo musthavequalitiesofclinicalresearchonartificialintelligenceandmachinelearning AT danielpintodossantos musthavequalitiesofclinicalresearchonartificialintelligenceandmachinelearning AT arnaldostanzione musthavequalitiesofclinicalresearchonartificialintelligenceandmachinelearning AT lorenzougga musthavequalitiesofclinicalresearchonartificialintelligenceandmachinelearning |