Cargando…

Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype

Predicting length of stay (LoS) and understanding its underlying factors is essential to minimizing the risk of hospital-acquired conditions, improving financial, operational, and clinical outcomes, and better managing future pandemics. The purpose of this study was to forecast patients’ LoS using a...

Descripción completa

Detalles Bibliográficos
Autores principales: Alam, Fakhare, Ananbeh, Obieda, Malik, Khalid Mahmood, Odayani, Abdulrahman Al, Hussain, Ibrahim Bin, Kaabia, Naoufel, Aidaroos, Amal Al, Saudagar, Abdul Khader Jilani
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10216944/
https://www.ncbi.nlm.nih.gov/pubmed/37238244
http://dx.doi.org/10.3390/diagnostics13101760
_version_ 1785048417485979648
author Alam, Fakhare
Ananbeh, Obieda
Malik, Khalid Mahmood
Odayani, Abdulrahman Al
Hussain, Ibrahim Bin
Kaabia, Naoufel
Aidaroos, Amal Al
Saudagar, Abdul Khader Jilani
author_facet Alam, Fakhare
Ananbeh, Obieda
Malik, Khalid Mahmood
Odayani, Abdulrahman Al
Hussain, Ibrahim Bin
Kaabia, Naoufel
Aidaroos, Amal Al
Saudagar, Abdul Khader Jilani
author_sort Alam, Fakhare
collection PubMed
description Predicting length of stay (LoS) and understanding its underlying factors is essential to minimizing the risk of hospital-acquired conditions, improving financial, operational, and clinical outcomes, and better managing future pandemics. The purpose of this study was to forecast patients’ LoS using a deep learning model and to analyze cohorts of risk factors reducing or prolonging LoS. We employed various preprocessing techniques, SMOTE-N to balance data, and a TabTransformer model to forecast LoS. Finally, the Apriori algorithm was applied to analyze cohorts of risk factors influencing hospital LoS. The TabTransformer outperformed the base machine learning models in terms of F1 score (0.92), precision (0.83), recall (0.93), and accuracy (0.73) for the discharged dataset and F1 score (0.84), precision (0.75), recall (0.98), and accuracy (0.77) for the deceased dataset. The association mining algorithm was able to identify significant risk factors/indicators belonging to laboratory, X-ray, and clinical data, such as elevated LDH and D-dimer levels, lymphocyte count, and comorbidities such as hypertension and diabetes. It also reveals what treatments have reduced the symptoms of COVID-19 patients, leading to a reduction in LoS, particularly when no vaccines or medication, such as Paxlovid, were available.
format Online
Article
Text
id pubmed-10216944
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-102169442023-05-27 Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype Alam, Fakhare Ananbeh, Obieda Malik, Khalid Mahmood Odayani, Abdulrahman Al Hussain, Ibrahim Bin Kaabia, Naoufel Aidaroos, Amal Al Saudagar, Abdul Khader Jilani Diagnostics (Basel) Article Predicting length of stay (LoS) and understanding its underlying factors is essential to minimizing the risk of hospital-acquired conditions, improving financial, operational, and clinical outcomes, and better managing future pandemics. The purpose of this study was to forecast patients’ LoS using a deep learning model and to analyze cohorts of risk factors reducing or prolonging LoS. We employed various preprocessing techniques, SMOTE-N to balance data, and a TabTransformer model to forecast LoS. Finally, the Apriori algorithm was applied to analyze cohorts of risk factors influencing hospital LoS. The TabTransformer outperformed the base machine learning models in terms of F1 score (0.92), precision (0.83), recall (0.93), and accuracy (0.73) for the discharged dataset and F1 score (0.84), precision (0.75), recall (0.98), and accuracy (0.77) for the deceased dataset. The association mining algorithm was able to identify significant risk factors/indicators belonging to laboratory, X-ray, and clinical data, such as elevated LDH and D-dimer levels, lymphocyte count, and comorbidities such as hypertension and diabetes. It also reveals what treatments have reduced the symptoms of COVID-19 patients, leading to a reduction in LoS, particularly when no vaccines or medication, such as Paxlovid, were available. MDPI 2023-05-17 /pmc/articles/PMC10216944/ /pubmed/37238244 http://dx.doi.org/10.3390/diagnostics13101760 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
Alam, Fakhare
Ananbeh, Obieda
Malik, Khalid Mahmood
Odayani, Abdulrahman Al
Hussain, Ibrahim Bin
Kaabia, Naoufel
Aidaroos, Amal Al
Saudagar, Abdul Khader Jilani
Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title_full Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title_fullStr Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title_full_unstemmed Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title_short Towards Predicting Length of Stay and Identification of Cohort Risk Factors Using Self-Attention-Based Transformers and Association Mining: COVID-19 as a Phenotype
title_sort towards predicting length of stay and identification of cohort risk factors using self-attention-based transformers and association mining: covid-19 as a phenotype
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10216944/
https://www.ncbi.nlm.nih.gov/pubmed/37238244
http://dx.doi.org/10.3390/diagnostics13101760
work_keys_str_mv AT alamfakhare towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT ananbehobieda towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT malikkhalidmahmood towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT odayaniabdulrahmanal towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT hussainibrahimbin towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT kaabianaoufel towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT aidaroosamalal towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype
AT saudagarabdulkhaderjilani towardspredictinglengthofstayandidentificationofcohortriskfactorsusingselfattentionbasedtransformersandassociationminingcovid19asaphenotype