Cargando…

A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses

The study of diagnostic associations entails a large number of methodological problems regarding the application of machine learning algorithms, collinearity and wide variability being some of the most prominent ones. To overcome these, we propose and tested the usage of uniform manifold approximati...

Descripción completa

Detalles Bibliográficos
Autores principales: Sánchez-Rico, Marina, Alvarado, Jesús M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960661/
https://www.ncbi.nlm.nih.gov/pubmed/31766665
http://dx.doi.org/10.3390/bs9120122
_version_ 1783487824189718528
author Sánchez-Rico, Marina
Alvarado, Jesús M.
author_facet Sánchez-Rico, Marina
Alvarado, Jesús M.
author_sort Sánchez-Rico, Marina
collection PubMed
description The study of diagnostic associations entails a large number of methodological problems regarding the application of machine learning algorithms, collinearity and wide variability being some of the most prominent ones. To overcome these, we propose and tested the usage of uniform manifold approximation and projection (UMAP), a very recent, popular dimensionality reduction technique. We showed its effectiveness by using it on a large Spanish clinical database of patients diagnosed with depression, to whom we applied UMAP before grouping them using a hierarchical agglomerative cluster analysis. By extensively studying its behavior and results, validating them with purely unsupervised metrics, we show that they are consistent with well-known relationships, which validates the applicability of UMAP to advance the study of comorbidities.
format Online
Article
Text
id pubmed-6960661
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-69606612020-01-23 A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses Sánchez-Rico, Marina Alvarado, Jesús M. Behav Sci (Basel) Article The study of diagnostic associations entails a large number of methodological problems regarding the application of machine learning algorithms, collinearity and wide variability being some of the most prominent ones. To overcome these, we propose and tested the usage of uniform manifold approximation and projection (UMAP), a very recent, popular dimensionality reduction technique. We showed its effectiveness by using it on a large Spanish clinical database of patients diagnosed with depression, to whom we applied UMAP before grouping them using a hierarchical agglomerative cluster analysis. By extensively studying its behavior and results, validating them with purely unsupervised metrics, we show that they are consistent with well-known relationships, which validates the applicability of UMAP to advance the study of comorbidities. MDPI 2019-11-22 /pmc/articles/PMC6960661/ /pubmed/31766665 http://dx.doi.org/10.3390/bs9120122 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Sánchez-Rico, Marina
Alvarado, Jesús M.
A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title_full A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title_fullStr A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title_full_unstemmed A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title_short A Machine Learning Approach for Studying the Comorbidities of Complex Diagnoses
title_sort machine learning approach for studying the comorbidities of complex diagnoses
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6960661/
https://www.ncbi.nlm.nih.gov/pubmed/31766665
http://dx.doi.org/10.3390/bs9120122
work_keys_str_mv AT sanchezricomarina amachinelearningapproachforstudyingthecomorbiditiesofcomplexdiagnoses
AT alvaradojesusm amachinelearningapproachforstudyingthecomorbiditiesofcomplexdiagnoses
AT sanchezricomarina machinelearningapproachforstudyingthecomorbiditiesofcomplexdiagnoses
AT alvaradojesusm machinelearningapproachforstudyingthecomorbiditiesofcomplexdiagnoses