Cargando…

Improving Diagnostics with Deep Forest Applied to Electronic Health Records

An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources’ limit...

Descripción completa

Detalles Bibliográficos
Autores principales: Khodadadi, Atieh, Ghanbari Bousejin, Nima, Molaei, Soheila, Kumar Chauhan, Vinod, Zhu, Tingting, Clifton, David A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10384165/
https://www.ncbi.nlm.nih.gov/pubmed/37514865
http://dx.doi.org/10.3390/s23146571
_version_ 1785081090251161600
author Khodadadi, Atieh
Ghanbari Bousejin, Nima
Molaei, Soheila
Kumar Chauhan, Vinod
Zhu, Tingting
Clifton, David A.
author_facet Khodadadi, Atieh
Ghanbari Bousejin, Nima
Molaei, Soheila
Kumar Chauhan, Vinod
Zhu, Tingting
Clifton, David A.
author_sort Khodadadi, Atieh
collection PubMed
description An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources’ limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations.
format Online
Article
Text
id pubmed-10384165
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-103841652023-07-30 Improving Diagnostics with Deep Forest Applied to Electronic Health Records Khodadadi, Atieh Ghanbari Bousejin, Nima Molaei, Soheila Kumar Chauhan, Vinod Zhu, Tingting Clifton, David A. Sensors (Basel) Article An electronic health record (EHR) is a vital high-dimensional part of medical concepts. Discovering implicit correlations in the information of this data set and the research and informative aspects can improve the treatment and management process. The challenge of concern is the data sources’ limitations in finding a stable model to relate medical concepts and use these existing connections. This paper presents Patient Forest, a novel end-to-end approach for learning patient representations from tree-structured data for readmission and mortality prediction tasks. By leveraging statistical features, the proposed model is able to provide an accurate and reliable classifier for predicting readmission and mortality. Experiments on MIMIC-III and eICU datasets demonstrate Patient Forest outperforms existing machine learning models, especially when the training data are limited. Additionally, a qualitative evaluation of Patient Forest is conducted by visualising the learnt representations in 2D space using the t-SNE, which further confirms the effectiveness of the proposed model in learning EHR representations. MDPI 2023-07-21 /pmc/articles/PMC10384165/ /pubmed/37514865 http://dx.doi.org/10.3390/s23146571 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/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 (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Khodadadi, Atieh
Ghanbari Bousejin, Nima
Molaei, Soheila
Kumar Chauhan, Vinod
Zhu, Tingting
Clifton, David A.
Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title_full Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title_fullStr Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title_full_unstemmed Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title_short Improving Diagnostics with Deep Forest Applied to Electronic Health Records
title_sort improving diagnostics with deep forest applied to electronic health records
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10384165/
https://www.ncbi.nlm.nih.gov/pubmed/37514865
http://dx.doi.org/10.3390/s23146571
work_keys_str_mv AT khodadadiatieh improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords
AT ghanbaribousejinnima improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords
AT molaeisoheila improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords
AT kumarchauhanvinod improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords
AT zhutingting improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords
AT cliftondavida improvingdiagnosticswithdeepforestappliedtoelectronichealthrecords