Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.

<h4>Background</h4>Deep neural networks learn from former experiences on a large scale and can be used to predict future disease activity as potential clinical decision support. AdaptiveNet is a novel adaptive recurrent neural network optimized to deal with heterogeneous and missing clin...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Maria Kalweit, Ulrich A Walker, Axel Finckh, Rüdiger Müller, Gabriel Kalweit, Almut Scherer, Joschka Boedecker, Thomas Hügle
Formato:	article
Lenguaje:	EN
Publicado:	Public Library of Science (PLoS) 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/4fb44e422e2440d085807a0577cec8ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4fb44e422e2440d085807a0577cec8ba
record_format	dspace
spelling	oai:doaj.org-article:4fb44e422e2440d085807a0577cec8ba2021-12-02T20:03:49ZPersonalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.1932-620310.1371/journal.pone.0252289https://doaj.org/article/4fb44e422e2440d085807a0577cec8ba2021-01-01T00:00:00Zhttps://doi.org/10.1371/journal.pone.0252289https://doaj.org/toc/1932-6203<h4>Background</h4>Deep neural networks learn from former experiences on a large scale and can be used to predict future disease activity as potential clinical decision support. AdaptiveNet is a novel adaptive recurrent neural network optimized to deal with heterogeneous and missing clinical data.<h4>Objective</h4>We investigate AdaptiveNet for the prediction of individual disease activity in patients from a rheumatoid arthritis (RA) registry.<h4>Methods</h4>Demographic and disease characteristics from over 9500 patients and 65.000 visits from the Swiss Quality Management (SCQM) database were used to train and evaluate the network. Patient characteristics, clinical and patient reported outcomes, laboratory values and medication were used as input features. DAS28-BSR served as a target to predict active RA and future numeric individual disease activity by classification and regression.<h4>Results</h4>AdaptiveNet predicted active disease defined as DAS28-BSR >2.6 at the next visit with an overall accuracy of 75.6% (SD +- 0.7%) and a sensitivity and specificity of 84.2% (SD +- 1.6%) and 61.5% (SD +- 3.6%), respectively. Prediction performance was significantly higher in patients with a disease duration >3 years and positive rheumatoid factor. Regression allowed forecasting individual DAS28-BSR values with a mean squared error (MSE) of 0.9 (SD +- 0.05). This corresponds to a 8% deviation between estimated and real DAS28-BSR values. Compared to linear regression, random forest and support vector machines, AdaptiveNet showed an increased performance of over 7% in MSE. Medication played a minor role in the prediction of RA disease activity.<h4>Conclusion</h4>AdaptiveNet has a superior capacity to predict numeric RA disease activity compared to classical machine learning architectures. All investigated models had limitations in low specificity.Maria KalweitUlrich A WalkerAxel FinckhRüdiger MüllerGabriel KalweitAlmut SchererJoschka BoedeckerThomas HüglePublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 16, Iss 6, p e0252289 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Maria Kalweit Ulrich A Walker Axel Finckh Rüdiger Müller Gabriel Kalweit Almut Scherer Joschka Boedecker Thomas Hügle Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
description	<h4>Background</h4>Deep neural networks learn from former experiences on a large scale and can be used to predict future disease activity as potential clinical decision support. AdaptiveNet is a novel adaptive recurrent neural network optimized to deal with heterogeneous and missing clinical data.<h4>Objective</h4>We investigate AdaptiveNet for the prediction of individual disease activity in patients from a rheumatoid arthritis (RA) registry.<h4>Methods</h4>Demographic and disease characteristics from over 9500 patients and 65.000 visits from the Swiss Quality Management (SCQM) database were used to train and evaluate the network. Patient characteristics, clinical and patient reported outcomes, laboratory values and medication were used as input features. DAS28-BSR served as a target to predict active RA and future numeric individual disease activity by classification and regression.<h4>Results</h4>AdaptiveNet predicted active disease defined as DAS28-BSR >2.6 at the next visit with an overall accuracy of 75.6% (SD +- 0.7%) and a sensitivity and specificity of 84.2% (SD +- 1.6%) and 61.5% (SD +- 3.6%), respectively. Prediction performance was significantly higher in patients with a disease duration >3 years and positive rheumatoid factor. Regression allowed forecasting individual DAS28-BSR values with a mean squared error (MSE) of 0.9 (SD +- 0.05). This corresponds to a 8% deviation between estimated and real DAS28-BSR values. Compared to linear regression, random forest and support vector machines, AdaptiveNet showed an increased performance of over 7% in MSE. Medication played a minor role in the prediction of RA disease activity.<h4>Conclusion</h4>AdaptiveNet has a superior capacity to predict numeric RA disease activity compared to classical machine learning architectures. All investigated models had limitations in low specificity.
format	article
author	Maria Kalweit Ulrich A Walker Axel Finckh Rüdiger Müller Gabriel Kalweit Almut Scherer Joschka Boedecker Thomas Hügle
author_facet	Maria Kalweit Ulrich A Walker Axel Finckh Rüdiger Müller Gabriel Kalweit Almut Scherer Joschka Boedecker Thomas Hügle
author_sort	Maria Kalweit
title	Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
title_short	Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
title_full	Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
title_fullStr	Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
title_full_unstemmed	Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
title_sort	personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.
publisher	Public Library of Science (PLoS)
publishDate	2021
url	https://doaj.org/article/4fb44e422e2440d085807a0577cec8ba
work_keys_str_mv	AT mariakalweit personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT ulrichawalker personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT axelfinckh personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT rudigermuller personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT gabrielkalweit personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT almutscherer personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT joschkaboedecker personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork AT thomashugle personalizedpredictionofdiseaseactivityinpatientswithrheumatoidarthritisusinganadaptivedeepneuralnetwork
_version_	1718375658126573568

Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network.

Ejemplares similares