Please use this identifier to cite or link to this item: https://ahro.austin.org.au/austinjspui/handle/1/34177
Full metadata record
DC FieldValueLanguage
dc.contributor.authorYoung, Marcus-
dc.contributor.authorHolmes, Natasha E-
dc.contributor.authorKishore, Kartik-
dc.contributor.authorAmjad, Sobia-
dc.contributor.authorGaca, Michele Jane-
dc.contributor.authorSerpa Neto, Ary-
dc.contributor.authorReade, Michael C-
dc.contributor.authorBellomo, Rinaldo-
dc.date2023-
dc.date.accessioned2023-11-10T01:46:01Z-
dc.date.available2023-11-10T01:46:01Z-
dc.date.issued2023-11-04-
dc.identifier.citationCritical Care (London, England) 2023-11-04; 27(1)en_US
dc.identifier.issn1466-609X-
dc.identifier.urihttps://ahro.austin.org.au/austinjspui/handle/1/34177-
dc.description.abstractNatural language processing (NLP) may help evaluate the characteristics, prevalence, trajectory, treatment, and outcomes of behavioural disturbance phenotypes in critically ill patients. We obtained electronic clinical notes, demographic information, outcomes, and treatment data from three medical-surgical ICUs. Using NLP, we screened for behavioural disturbance phenotypes based on words suggestive of an agitated state, a non-agitated state, or a combination of both. We studied 2931 patients. Of these, 225 (7.7%) were NLP-Dx-BD positive for the agitated phenotype, 544 (18.6%) for the non-agitated phenotype and 667 (22.7%) for the combined phenotype. Patients with these phenotypes carried multiple clinical baseline differences. On time-dependent multivariable analysis to compensate for immortal time bias and after adjustment for key outcome predictors, agitated phenotype patients were more likely to receive antipsychotic medications (odds ratio [OR] 1.84, 1.35-2.51, p < 0.001) compared to non-agitated phenotype patients but not compared to combined phenotype patients (OR 1.27, 0.86-1.89, p = 0.229). Moreover, agitated phenotype patients were more likely to die than other phenotypes patients (OR 1.57, 1.10-2.25, p = 0.012 vs non-agitated phenotype; OR 4.61, 2.14-9.90, p < 0.001 vs. combined phenotype). This association was strongest in patients receiving mechanical ventilation when compared with the combined phenotype (OR 7.03, 2.07-23.79, p = 0.002). A similar increased risk was also seen for patients with the non-agitated phenotype compared with the combined phenotype (OR 6.10, 1.80-20.64, p = 0.004). NLP-Dx-BD screening enabled identification of three behavioural disturbance phenotypes with different characteristics, prevalence, trajectory, treatment, and outcome. Such phenotype identification appears relevant to prognostication and trial design.en_US
dc.language.isoeng-
dc.subjectAgitationen_US
dc.subjectAntipsychotic drugsen_US
dc.subjectCritical illnessen_US
dc.subjectDeliriumen_US
dc.subjectIntensive careen_US
dc.subjectMortalityen_US
dc.titleNatural language processing diagnosed behavioural disturbance phenotypes in the intensive care unit: characteristics, prevalence, trajectory, treatment, and outcomes.en_US
dc.typeJournal Articleen_US
dc.identifier.journaltitleCritical Care (London, England)en_US
dc.identifier.affiliationData Analytics Research and Evaluation (DARE) Centreen_US
dc.identifier.affiliationThe University of Melbourne, Heidelberg, VIC, Australia.en_US
dc.identifier.affiliationDepartment of Infectious Diseases, Peter Doherty Institute for Infection and Immunity, University of Melbourne, Victoria, 3000, Australia.en_US
dc.identifier.affiliationSchool of Computing and Information Systems, The University of Melbourne, Parkville, Melbourne, VIC, Australia.en_US
dc.identifier.affiliationAustralian and New Zealand Intensive Care Research Centre, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia.en_US
dc.identifier.affiliationFaculty of Medicine, University of Queensland, Brisbane, QLD, Australia.en_US
dc.identifier.affiliationAustralian and New Zealand Intensive Care Research Centre, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia.;Department of Intensive Care, Austin Hospital, 145 Studley Rd, Heidelberg, Melbourne, Australia.;Department of Critical Care, School of Medicine, The University of Melbourne, Parkville, Melbourne, VIC, Australia.;Department of Intensive Care, Royal Melbourne Hospital, Melbourne, Australia.en_US
dc.identifier.affiliationJoint Health Command, Australian Defence Force, Brisbane, QLD, Australia.;Department of Intensive Care Medicine, Royal Brisbane and Women's Hospital, Brisbane, QLD, Australia.en_US
dc.identifier.doi10.1186/s13054-023-04695-0en_US
dc.type.contentTexten_US
dc.identifier.orcid0000-0002-6195-660Xen_US
dc.identifier.orcid0000-0001-8501-4054en_US
dc.identifier.orcid0000-0002-6254-6063en_US
dc.identifier.orcid0000-0002-1595-0370en_US
dc.identifier.orcid0000-0001-7350-3299en_US
dc.identifier.orcid0000-0003-1520-9387en_US
dc.identifier.orcid0000-0003-1570-0707en_US
dc.identifier.orcid0000-0002-1650-8939en_US
dc.identifier.pubmedid37925406-
dc.description.volume27-
dc.description.issue1-
dc.description.startpage425-
item.fulltextNo Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.languageiso639-1en-
item.openairetypeJournal Article-
item.grantfulltextnone-
item.cerifentitytypePublications-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
crisitem.author.deptInfectious Diseases-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
crisitem.author.deptEndocrinology-
crisitem.author.deptSurgery-
crisitem.author.deptOffice for Research-
crisitem.author.deptIntensive Care-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
crisitem.author.deptIntensive Care-
crisitem.author.deptData Analytics Research and Evaluation (DARE) Centre-
Appears in Collections:Journal articles
Show simple item record

Page view(s)

58
checked on May 27, 2024

Google ScholarTM

Check


Items in AHRO are protected by copyright, with all rights reserved, unless otherwise indicated.