Multimorbidity prediction using link prediction

Abstract Multimorbidity, frequently associated with aging, can be operationally defined as the presence of two or more chronic conditions. Predicting the likelihood of a patient with multimorbidity to develop a further particular disease in the future is one of the key challenges in multimorbidity r...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Furqan Aziz, Victor Roth Cardoso, Laura Bravo-Merodio, Dominic Russ, Samantha C. Pendleton, John A. Williams, Animesh Acharjee, Georgios V. Gkoutos
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/3345541b904c4ba69daa4518344daf8f
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:3345541b904c4ba69daa4518344daf8f
record_format dspace
spelling oai:doaj.org-article:3345541b904c4ba69daa4518344daf8f2021-12-02T15:08:10ZMultimorbidity prediction using link prediction10.1038/s41598-021-95802-02045-2322https://doaj.org/article/3345541b904c4ba69daa4518344daf8f2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-95802-0https://doaj.org/toc/2045-2322Abstract Multimorbidity, frequently associated with aging, can be operationally defined as the presence of two or more chronic conditions. Predicting the likelihood of a patient with multimorbidity to develop a further particular disease in the future is one of the key challenges in multimorbidity research. In this paper we are using a network-based approach to analyze multimorbidity data and develop methods for predicting diseases that a patient is likely to develop. The multimorbidity data is represented using a temporal bipartite network whose nodes represent patients and diseases and a link between these nodes indicates that the patient has been diagnosed with the disease. Disease prediction then is reduced to a problem of predicting those missing links in the network that are likely to appear in the future. We develop a novel link prediction method for static bipartite network and validate the performance of the method on benchmark datasets. By using a probabilistic framework, we then report on the development of a method for predicting future links in the network, where links are labelled with a time-stamp. We apply the proposed method to three different multimorbidity datasets and report its performance measured by different performance metrics including AUC, Precision, Recall, and F-Score.Furqan AzizVictor Roth CardosoLaura Bravo-MerodioDominic RussSamantha C. PendletonJohn A. WilliamsAnimesh AcharjeeGeorgios V. GkoutosNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-11 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Furqan Aziz
Victor Roth Cardoso
Laura Bravo-Merodio
Dominic Russ
Samantha C. Pendleton
John A. Williams
Animesh Acharjee
Georgios V. Gkoutos
Multimorbidity prediction using link prediction
description Abstract Multimorbidity, frequently associated with aging, can be operationally defined as the presence of two or more chronic conditions. Predicting the likelihood of a patient with multimorbidity to develop a further particular disease in the future is one of the key challenges in multimorbidity research. In this paper we are using a network-based approach to analyze multimorbidity data and develop methods for predicting diseases that a patient is likely to develop. The multimorbidity data is represented using a temporal bipartite network whose nodes represent patients and diseases and a link between these nodes indicates that the patient has been diagnosed with the disease. Disease prediction then is reduced to a problem of predicting those missing links in the network that are likely to appear in the future. We develop a novel link prediction method for static bipartite network and validate the performance of the method on benchmark datasets. By using a probabilistic framework, we then report on the development of a method for predicting future links in the network, where links are labelled with a time-stamp. We apply the proposed method to three different multimorbidity datasets and report its performance measured by different performance metrics including AUC, Precision, Recall, and F-Score.
format article
author Furqan Aziz
Victor Roth Cardoso
Laura Bravo-Merodio
Dominic Russ
Samantha C. Pendleton
John A. Williams
Animesh Acharjee
Georgios V. Gkoutos
author_facet Furqan Aziz
Victor Roth Cardoso
Laura Bravo-Merodio
Dominic Russ
Samantha C. Pendleton
John A. Williams
Animesh Acharjee
Georgios V. Gkoutos
author_sort Furqan Aziz
title Multimorbidity prediction using link prediction
title_short Multimorbidity prediction using link prediction
title_full Multimorbidity prediction using link prediction
title_fullStr Multimorbidity prediction using link prediction
title_full_unstemmed Multimorbidity prediction using link prediction
title_sort multimorbidity prediction using link prediction
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/3345541b904c4ba69daa4518344daf8f
work_keys_str_mv AT furqanaziz multimorbiditypredictionusinglinkprediction
AT victorrothcardoso multimorbiditypredictionusinglinkprediction
AT laurabravomerodio multimorbiditypredictionusinglinkprediction
AT dominicruss multimorbiditypredictionusinglinkprediction
AT samanthacpendleton multimorbiditypredictionusinglinkprediction
AT johnawilliams multimorbiditypredictionusinglinkprediction
AT animeshacharjee multimorbiditypredictionusinglinkprediction
AT georgiosvgkoutos multimorbiditypredictionusinglinkprediction
_version_ 1718388242953273344