Clinical Prediction Models for Hospital-Induced Delirium Using Structured and Unstructured Electronic Health Record Data: Protocol for a Development and Validation Study.
big data
clinical text
data science
delirium
free text
hospital acquired
hospital induced
hospital-acquired condition
machine learning
model
models
natural language processing
predict
prediction
predictive
risk
risk factors
structured
text data
unstructured
Journal
JMIR research protocols
ISSN: 1929-0748
Titre abrégé: JMIR Res Protoc
Pays: Canada
ID NLM: 101599504
Informations de publication
Date de publication:
09 Nov 2023
09 Nov 2023
Historique:
received:
26
04
2023
accepted:
05
09
2023
revised:
01
09
2023
medline:
9
11
2023
pubmed:
9
11
2023
entrez:
9
11
2023
Statut:
epublish
Résumé
Hospital-induced delirium is one of the most common and costly iatrogenic conditions, and its incidence is predicted to increase as the population of the United States ages. An academic and clinical interdisciplinary systems approach is needed to reduce the frequency and impact of hospital-induced delirium. The long-term goal of our research is to enhance the safety of hospitalized older adults by reducing iatrogenic conditions through an effective learning health system. In this study, we will develop models for predicting hospital-induced delirium. In order to accomplish this objective, we will create a computable phenotype for our outcome (hospital-induced delirium), design an expert-based traditional logistic regression model, leverage machine learning techniques to generate a model using structured data, and use machine learning and natural language processing to produce an integrated model with components from both structured data and text data. This study will explore text-based data, such as nursing notes, to improve the predictive capability of prognostic models for hospital-induced delirium. By using supervised and unsupervised text mining in addition to structured data, we will examine multiple types of information in electronic health record data to predict medical-surgical patient risk of developing delirium. Development and validation will be compliant to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement. Work on this project will take place through March 2024. For this study, we will use data from approximately 332,230 encounters that occurred between January 2012 to May 2021. Findings from this project will be disseminated at scientific conferences and in peer-reviewed journals. Success in this study will yield a durable, high-performing research-data infrastructure that will process, extract, and analyze clinical text data in near real time. This model has the potential to be integrated into the electronic health record and provide point-of-care decision support to prevent harm and improve quality of care. DERR1-10.2196/48521.
Sections du résumé
BACKGROUND
BACKGROUND
Hospital-induced delirium is one of the most common and costly iatrogenic conditions, and its incidence is predicted to increase as the population of the United States ages. An academic and clinical interdisciplinary systems approach is needed to reduce the frequency and impact of hospital-induced delirium.
OBJECTIVE
OBJECTIVE
The long-term goal of our research is to enhance the safety of hospitalized older adults by reducing iatrogenic conditions through an effective learning health system. In this study, we will develop models for predicting hospital-induced delirium. In order to accomplish this objective, we will create a computable phenotype for our outcome (hospital-induced delirium), design an expert-based traditional logistic regression model, leverage machine learning techniques to generate a model using structured data, and use machine learning and natural language processing to produce an integrated model with components from both structured data and text data.
METHODS
METHODS
This study will explore text-based data, such as nursing notes, to improve the predictive capability of prognostic models for hospital-induced delirium. By using supervised and unsupervised text mining in addition to structured data, we will examine multiple types of information in electronic health record data to predict medical-surgical patient risk of developing delirium. Development and validation will be compliant to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement.
RESULTS
RESULTS
Work on this project will take place through March 2024. For this study, we will use data from approximately 332,230 encounters that occurred between January 2012 to May 2021. Findings from this project will be disseminated at scientific conferences and in peer-reviewed journals.
CONCLUSIONS
CONCLUSIONS
Success in this study will yield a durable, high-performing research-data infrastructure that will process, extract, and analyze clinical text data in near real time. This model has the potential to be integrated into the electronic health record and provide point-of-care decision support to prevent harm and improve quality of care.
INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)
UNASSIGNED
DERR1-10.2196/48521.
Identifiants
pubmed: 37943599
pii: v12i1e48521
doi: 10.2196/48521
pmc: PMC10667972
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e48521Subventions
Organisme : NIA NIH HHS
ID : R33 AG062884
Pays : United States
Informations de copyright
©Sarah E Ser, Kristen Shear, Urszula A Snigurska, Mattia Prosperi, Yonghui Wu, Tanja Magoc, Ragnhildur I Bjarnadottir, Robert J Lucero. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 09.11.2023.
Références
Nat Rev Neurol. 2009 Apr;5(4):210-20
pubmed: 19347026
J Am Med Inform Assoc. 2021 Mar 1;28(3):664-665
pubmed: 33325514
JAMA Cardiol. 2016 Dec 1;1(9):976-977
pubmed: 27732706
J Am Geriatr Soc. 2011 Nov;59 Suppl 2:S241-3
pubmed: 22091567
Biostatistics. 2006 Jul;7(3):355-73
pubmed: 16344280
Clin Interv Aging. 2011;6:77-82
pubmed: 21472095
BMC Bioinformatics. 2007 Jan 25;8:25
pubmed: 17254353
Pharmacoepidemiol Drug Saf. 2017 Aug;26(8):945-953
pubmed: 28485014
J Am Med Inform Assoc. 2011 Mar-Apr;18(2):181-6
pubmed: 21233086
J Am Med Inform Assoc. 2021 Mar 1;28(3):666-667
pubmed: 33325532
J Am Med Inform Assoc. 2013 Sep-Oct;20(5):906-14
pubmed: 23242765
Age Ageing. 2013 May;42(3):284-91
pubmed: 23537588
JMIR Form Res. 2022 Jun 24;6(6):e33834
pubmed: 35749214
BMJ. 2021 Oct 20;375:n2281
pubmed: 34670780
Br J Surg. 2015 Feb;102(3):148-58
pubmed: 25627261
Can J Anaesth. 2010 Oct;57(10):898-902
pubmed: 20645040
J Appl Gerontol. 2022 May;41(5):1485-1490
pubmed: 35176883
Adv Exp Med Biol. 2016;939:139-166
pubmed: 27807747
J Am Med Inform Assoc. 2013 Jan 1;20(1):117-21
pubmed: 22955496
Int J Med Inform. 2020 Nov;143:104272
pubmed: 32980667
JMIR Med Inform. 2020 Jan 24;8(1):e16042
pubmed: 32012059
Methods. 2015 Mar;74:47-53
pubmed: 25448298
Yearb Med Inform. 2008;:128-44
pubmed: 18660887
BMC Med Inform Decis Mak. 2018 Dec 29;18(1):139
pubmed: 30594159
BMC Bioinformatics. 2008 Jul 11;9:307
pubmed: 18620558
J Am Med Inform Assoc. 2020 Jul 1;27(9):1383-1392
pubmed: 32968811
PLoS One. 2023 Aug 17;18(8):e0285527
pubmed: 37590196
Intern Med J. 2019 Mar;49(3):338-344
pubmed: 30091294
J Am Med Inform Assoc. 2017 Jan;24(1):198-208
pubmed: 27189013
Oman Med J. 2008 Jul;23(3):150-7
pubmed: 22359704
Stud Health Technol Inform. 2013;192:1145
pubmed: 23920919
Drug Saf. 2014 Oct;37(10):777-90
pubmed: 25151493
AMIA Annu Symp Proc. 2007 Oct 11;:543-7
pubmed: 18693895
Int J Med Inform. 2019 Feb;122:63-69
pubmed: 30623785
Lancet. 2014 Mar 8;383(9920):911-22
pubmed: 23992774