Application of machine learning in rheumatic disease research

Kim, Ki-Jo; Tagkopoulos, Ilias

doi:10.3904/kjim.2018.349

Cited by 59 publications

(26 citation statements)

References 88 publications

(99 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In recent years, the use of machine-learning algorithms has gained popularity in healthcare due to their flexibility in handling large complex datasets and nonlinear relationships [ 8 , 9 ]. In addition, in the RA healthcare domain there are many opportunities for the application of machine-learning algorithms, for instance, the categorization of different arthritis subtypes or prediction of treatment response [ 10 , 11 , 12 ]. Others already successfully examined whether machine-learning algorithms could be used to predict response to MTX therapy in juvenile idiopathic arthritis (JIA) patients [ 13 ] and to antitumor necrosis factor in RA patients [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

Gosselt

Verhoeven

Bulatović-Ćalasan

et al. 2021

JPM

View full text Add to dashboard Cite

The goals of this study were to examine whether machine-learning algorithms outperform multivariable logistic regression in the prediction of insufficient response to methotrexate (MTX); secondly, to examine which features are essential for correct prediction; and finally, to investigate whether the best performing model specifically identifies insufficient responders to MTX (combination) therapy. The prediction of insufficient response (3-month Disease Activity Score 28-Erythrocyte-sedimentation rate (DAS28-ESR) > 3.2) was assessed using logistic regression, least absolute shrinkage and selection operator (LASSO), random forest, and extreme gradient boosting (XGBoost). The baseline features of 355 rheumatoid arthritis (RA) patients from the “treatment in the Rotterdam Early Arthritis CoHort” (tREACH) and the U-Act-Early trial were combined for analyses. The model performances were compared using area under the curve (AUC) of receiver operating characteristic (ROC) curves, 95% confidence intervals (95% CI), and sensitivity and specificity. Finally, the best performing model following feature selection was tested on 101 RA patients starting tocilizumab (TCZ)-monotherapy. Logistic regression (AUC = 0.77 95% CI: 0.68–0.86) performed as well as LASSO (AUC = 0.76, 95% CI: 0.67–0.85), random forest (AUC = 0.71, 95% CI: 0.61 = 0.81), and XGBoost (AUC = 0.70, 95% CI: 0.61–0.81), yet logistic regression reached the highest sensitivity (81%). The most important features were baseline DAS28 (components). For all algorithms, models with six features performed similarly to those with 16. When applied to the TCZ-monotherapy group, logistic regression’s sensitivity significantly dropped from 83% to 69% (p = 0.03). In the current dataset, logistic regression performed equally well compared to machine-learning algorithms in the prediction of insufficient response to MTX. Models could be reduced to six features, which are more conducive for clinical implementation. Interestingly, the prediction model was specific to MTX (combination) therapy response.

show abstract

Section: Introductionmentioning

confidence: 99%

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

Gosselt

Verhoeven

Bulatović-Ćalasan

et al. 2021

JPM

View full text Add to dashboard Cite

show abstract

“…Between machine learning and traditional statistical methods, there are significant differences. First, machine learning focuses on the task of "forecasting", using universal learning algorithms to find patterns in variable and volumetric data [5]. In contrast, statistical methods are mainly focused on confirming hypotheses based on inferences, which are achieved by defining and approximating probability functions for a particular model [6].…”

Section: Methodsmentioning

confidence: 99%

Usage of the machine learning to organize time series and find anomalies

2020

View full text Add to dashboard Cite

The subject of the study is the process of collecting, preparing, and searching for anomalies on data from heterogeneous sources. Economic information is naturally heterogeneous and semi-structured or unstructured. This makes pre-processing of input dynamic data an important prerequisite for the detection of significant patterns and knowledge in the subject area, so the topic of research is relevant. Pre-processing of data is several unique problems that have led to the emergence of various algorithms and heuristic methods for solving such pre-processing problems as merging and cleaning and identifying variables. In this work, an algorithm for preprocessing and searching for anomalies using LSTM is formulated, which allows you to consolidate into a single database and structure information by time series from different sources, as well as search for anomalies in an automated mode. A key modification of the preprocessing method proposed by the authors is the technology of automated data integration. The technology proposed by the authors involves the joint use of methods for building a fuzzy time series and machine lexical matching on a thesaurus network, as well as the use of a universal database built using the MIVAR concept. The preprocessing algorithm forms a single data model with the possibility of transforming the periodicity and semantics of the data set and integrating into a single information bank data that can come from various sources.

show abstract

“…For all of the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining progress. Numerous studies have shown that access to data and data quality are crucial to enable successful machine learning of medical diagnosis, providing real assistance to physicians [3,4,5,6,7]. Exceptionally high-quality annotated data can improve deep learning detection results to great extent [8,9,10].…”

Section: Researchmentioning

confidence: 99%

Fast Machine Learning Annotation in the Medical Domain: A Semi-Automated Video Annotation Tool for Gastroenterologists

Krenzer

Makowski

Hekalo

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all of the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g. visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Results: Using this framework we were able to reduce work load of domain experts on average by a factor of 20. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated pre-annotation model enhances the annotation speed further. Through a study with 10 participants we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion: In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.

show abstract

Application of machine learning in rheumatic disease research

Cited by 59 publications

References 88 publications

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

Usage of the machine learning to organize time series and find anomalies

Fast Machine Learning Annotation in the Medical Domain: A Semi-Automated Video Annotation Tool for Gastroenterologists

Contact Info

Product

Resources

About