Cargando…
Using machine learning to model older adult inpatient trajectories from electronic health records data
Electronic Health Records (EHR) data can provide novel insights into inpatient trajectories. Blood tests and vital signs from de-identified patients’ hospital admission episodes (AE) were represented as multivariate time-series (MVTS) to train unsupervised Hidden Markov Models (HMM) and represent ea...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9860485/ https://www.ncbi.nlm.nih.gov/pubmed/36691609 http://dx.doi.org/10.1016/j.isci.2022.105876 |
_version_ | 1784874593817722880 |
---|---|
author | Herrero-Zazo, Maria Fitzgerald, Tomas Taylor, Vince Street, Helen Chaudhry, Afzal N. Bradley, John R. Birney, Ewan Keevil, Victoria L. |
author_facet | Herrero-Zazo, Maria Fitzgerald, Tomas Taylor, Vince Street, Helen Chaudhry, Afzal N. Bradley, John R. Birney, Ewan Keevil, Victoria L. |
author_sort | Herrero-Zazo, Maria |
collection | PubMed |
description | Electronic Health Records (EHR) data can provide novel insights into inpatient trajectories. Blood tests and vital signs from de-identified patients’ hospital admission episodes (AE) were represented as multivariate time-series (MVTS) to train unsupervised Hidden Markov Models (HMM) and represent each AE day as one of 17 states. All HMM states were clinically interpreted based on their patterns of MVTS variables and relationships with clinical information. Visualization differentiated patients progressing toward stable ‘discharge-like’ states versus those remaining at risk of inpatient mortality (IM). Chi-square tests confirmed these relationships (two states associated with IM; 12 states with ≥1 diagnosis). Logistic Regression and Random Forest (RF) models trained with MVTS data rather than states had higher prediction performances of IM, but results were comparable (best RF model AUC-ROC: MVTS data = 0.85; HMM states = 0.79). ML models extracted clinically interpretable signals from hospital data. The potential of ML to develop decision-support tools for EHR systems warrants investigation. |
format | Online Article Text |
id | pubmed-9860485 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-98604852023-01-22 Using machine learning to model older adult inpatient trajectories from electronic health records data Herrero-Zazo, Maria Fitzgerald, Tomas Taylor, Vince Street, Helen Chaudhry, Afzal N. Bradley, John R. Birney, Ewan Keevil, Victoria L. iScience Article Electronic Health Records (EHR) data can provide novel insights into inpatient trajectories. Blood tests and vital signs from de-identified patients’ hospital admission episodes (AE) were represented as multivariate time-series (MVTS) to train unsupervised Hidden Markov Models (HMM) and represent each AE day as one of 17 states. All HMM states were clinically interpreted based on their patterns of MVTS variables and relationships with clinical information. Visualization differentiated patients progressing toward stable ‘discharge-like’ states versus those remaining at risk of inpatient mortality (IM). Chi-square tests confirmed these relationships (two states associated with IM; 12 states with ≥1 diagnosis). Logistic Regression and Random Forest (RF) models trained with MVTS data rather than states had higher prediction performances of IM, but results were comparable (best RF model AUC-ROC: MVTS data = 0.85; HMM states = 0.79). ML models extracted clinically interpretable signals from hospital data. The potential of ML to develop decision-support tools for EHR systems warrants investigation. Elsevier 2022-12-24 /pmc/articles/PMC9860485/ /pubmed/36691609 http://dx.doi.org/10.1016/j.isci.2022.105876 Text en © 2022 The Authors https://creativecommons.org/licenses/by/4.0/This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Herrero-Zazo, Maria Fitzgerald, Tomas Taylor, Vince Street, Helen Chaudhry, Afzal N. Bradley, John R. Birney, Ewan Keevil, Victoria L. Using machine learning to model older adult inpatient trajectories from electronic health records data |
title | Using machine learning to model older adult inpatient trajectories from electronic health records data |
title_full | Using machine learning to model older adult inpatient trajectories from electronic health records data |
title_fullStr | Using machine learning to model older adult inpatient trajectories from electronic health records data |
title_full_unstemmed | Using machine learning to model older adult inpatient trajectories from electronic health records data |
title_short | Using machine learning to model older adult inpatient trajectories from electronic health records data |
title_sort | using machine learning to model older adult inpatient trajectories from electronic health records data |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9860485/ https://www.ncbi.nlm.nih.gov/pubmed/36691609 http://dx.doi.org/10.1016/j.isci.2022.105876 |
work_keys_str_mv | AT herrerozazomaria usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT fitzgeraldtomas usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT taylorvince usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT streethelen usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT chaudhryafzaln usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT bradleyjohnr usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT birneyewan usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata AT keevilvictorial usingmachinelearningtomodelolderadultinpatienttrajectoriesfromelectronichealthrecordsdata |