Dataset Information

Machine learning in GI endoscopy: practical guidance in how to interpret a novel field.

ABSTRACT: There has been a vast increase in GI literature focused on the use of machine learning in endoscopy. The relative novelty of this field poses a challenge for reviewers and readers of GI journals. To appreciate scientific quality and novelty of machine learning studies, understanding of the technical basis and commonly used techniques is required. Clinicians often lack this technical background, while machine learning experts may be unfamiliar with clinical relevance and implications for daily practice. Therefore, there is an increasing need for a multidisciplinary, international evaluation on how to perform high-quality machine learning research in endoscopy. This review aims to provide guidance for readers and reviewers of peer-reviewed GI journals to allow critical appraisal of the most relevant quality requirements of machine learning studies. The paper provides an overview of common trends and their potential pitfalls and proposes comprehensive quality requirements in six overarching themes: terminology, data, algorithm description, experimental setup, interpretation of results and machine learning in clinical practice.

SUBMITTER: van der Sommen F

PROVIDER: S-EPMC7569393 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning in GI endoscopy: practical guidance in how to interpret a novel field.

van der Sommen Fons F de Groof Jeroen J Struyvenberg Maarten M van der Putten Joost J Boers Tim T Fockens Kiki K Schoon Erik J EJ Curvers Wouter W de With Peter P Mori Yuichi Y Byrne Michael M Bergman Jacques J G H M JJGHM

Gut 20200511 11

There has been a vast increase in GI literature focused on the use of machine learning in endoscopy. The relative novelty of this field poses a challenge for reviewers and readers of GI journals. To appreciate scientific quality and novelty of machine learning studies, understanding of the technical basis and commonly used techniques is required. Clinicians often lack this technical background, while machine learning experts may be unfamiliar with clinical relevance and implications for daily pr ...[more]

PMID: 32393540

Similar Datasets

Project description:BackgroundFollowing visible successes on a wide range of predictive tasks, machine learning techniques are attracting substantial interest from medical researchers and clinicians. We address the need for capacity development in this area by providing a conceptual introduction to machine learning alongside a practical guide to developing and evaluating predictive algorithms using freely-available open source software and public domain data.MethodsWe demonstrate the use of machine learning techniques by developing three predictive models for cancer diagnosis using descriptions of nuclei sampled from breast masses. These algorithms include regularized General Linear Model regression (GLMs), Support Vector Machines (SVMs) with a radial basis function kernel, and single-layer Artificial Neural Networks. The publicly-available dataset describing the breast mass samples (N=683) was randomly split into evaluation (n=456) and validation (n=227) samples. We trained algorithms on data from the evaluation sample before they were used to predict the diagnostic outcome in the validation dataset. We compared the predictions made on the validation datasets with the real-world diagnostic decisions to calculate the accuracy, sensitivity, and specificity of the three models. We explored the use of averaging and voting ensembles to improve predictive performance. We provide a step-by-step guide to developing algorithms using the open-source R statistical programming environment.ResultsThe trained algorithms were able to classify cell nuclei with high accuracy (.94 -.96), sensitivity (.97 -.99), and specificity (.85 -.94). Maximum accuracy (.96) and area under the curve (.97) was achieved using the SVM algorithm. Prediction performance increased marginally (accuracy =.97, sensitivity =.99, specificity =.95) when algorithms were arranged into a voting ensemble.ConclusionsWe use a straightforward example to demonstrate the theory and practice of machine learning for clinicians and medical researchers. The principals which we demonstrate here can be readily applied to other complex tasks including natural language processing and image recognition.

Project description:Dermatomyositis is a heterogeneous idiopathic inflammatory myopathy associated with various cutaneous manifestations and variable presence of myositis, interstitial lung disease, and other visceral organ involvement. An accurate diagnosis of dermatomyositis requires correlating clinical examination findings with serological and histological findings. Familiarity with pathognomonic and common cutaneous manifestations of dermatomyositis, which are highlighted here, can be especially helpful in making an accurate diagnosis. Additionally, evaluating patients for presence of myositis-specific autoantibodies can further support or refute a dermatomyositis diagnosis. When present, myositis-specific autoantibodies can also help guide workups for various dermatomyositis-associated manifestations, as each is associated with relatively distinct clinical characteristics. Evaluating patients for various systemic manifestations often relies on expert opinion recommendations; however, societal guideline statements concerning the evaluation of some manifestations have recently been described. Although malignancy-associated dermatomyositis is a well-accepted subtype, there is limited evidence to support extensive malignancy screening has a favorable benefit-risk ratio in most dermatomyositis patients. However, recent research has uncovered novel associations between dermatomyositis and malignancy, suggesting the possibility of identifying high-risk subsets of dermatomyositis patients in whom malignancy screening may have a high value. Treatment for dermatomyositis has remained largely unchanged over the past several decades. Although many dermatomyositis patients can be effectively treated with current options, either as monotherapy or with combination regimens, there is a need for more targeted and effective DM therapies, in general, and for MDA5(+) dermatomyositis-associated rapidly progressive interstitial lung disease. Fortunately, significant current and emerging research activities evaluating various novel medications for dermatomyositis provide hope for exciting future advances in patients with this intriguing immune-mediated disease.

Dataset Information

Machine learning in GI endoscopy: practical guidance in how to interpret a novel field.

Publications

Machine learning in GI endoscopy: practical guidance in how to interpret a novel field.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets