{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["2"],"submitter":["Garland A"],"pubmed_abstract":["<h4>Background</h4>Prediction of future critical illness could render it practical to test interventions seeking to avoid or delay the coming event.<h4>Objective</h4>Identify adults having >33% probability of near-future critical illness.<h4>Research design</h4>Retrospective cohort study, 2013-2015.<h4>Subjects</h4>Community-dwelling residents of Manitoba, Canada, aged 40-89 years.<h4>Measures</h4>The outcome was a near-future critical illness, defined as intensive care unit admission with invasive mechanical ventilation, or non-palliative death occurring 30-180 days after 1 April each year. By dividing the data into training and test cohorts, a Classification and Regression Tree analysis was used to identify subgroups with ≥33% probability of the outcome. We considered 72 predictors including sociodemographics, chronic conditions, frailty, and health care utilization. Sensitivity analysis used logistic regression methods.<h4>Results</h4>Approximately 0.38% of each yearly cohort experienced near-future critical illness. The optimal Tree identified 2,644 mutually exclusive subgroups. Socioeconomic status was the most influential variable, followed by nursing home residency and frailty; age was sixth. In the training data, the model performed well; 41 subgroups containing 493 subjects had ≥33% members who developed the outcome. However, in the test data, those subgroups contained 429 individuals, with 20 (4.7%) experiencing the outcome, which comprised 0.98% of all subjects with the outcome. While logistic regression showed less model overfitting, it likewise failed to achieve the stated objective.<h4>Conclusions</h4>High-fidelity prediction of near-future critical illness among community-dwelling adults was not successful using population-based administrative data. Additional research is needed to ascertain whether the inclusion of additional types of data can achieve this goal."],"journal":["Frontiers in epidemiology"],"pagination":["944216"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC10910992"],"repository":["biostudies-literature"],"pubmed_title":["Administrative Data Is Insufficient to Identify Near-Future Critical Illness: A Population-Based Retrospective Cohort Study."],"pmcid":["PMC10910992"],"pubmed_authors":["Marrie RA","Wunsch H","Chateau D","Garland A","Yogendran M"],"additional_accession":[]},"is_claimable":false,"name":"Administrative Data Is Insufficient to Identify Near-Future Critical Illness: A Population-Based Retrospective Cohort Study.","description":"<h4>Background</h4>Prediction of future critical illness could render it practical to test interventions seeking to avoid or delay the coming event.<h4>Objective</h4>Identify adults having >33% probability of near-future critical illness.<h4>Research design</h4>Retrospective cohort study, 2013-2015.<h4>Subjects</h4>Community-dwelling residents of Manitoba, Canada, aged 40-89 years.<h4>Measures</h4>The outcome was a near-future critical illness, defined as intensive care unit admission with invasive mechanical ventilation, or non-palliative death occurring 30-180 days after 1 April each year. By dividing the data into training and test cohorts, a Classification and Regression Tree analysis was used to identify subgroups with ≥33% probability of the outcome. We considered 72 predictors including sociodemographics, chronic conditions, frailty, and health care utilization. Sensitivity analysis used logistic regression methods.<h4>Results</h4>Approximately 0.38% of each yearly cohort experienced near-future critical illness. The optimal Tree identified 2,644 mutually exclusive subgroups. Socioeconomic status was the most influential variable, followed by nursing home residency and frailty; age was sixth. In the training data, the model performed well; 41 subgroups containing 493 subjects had ≥33% members who developed the outcome. However, in the test data, those subgroups contained 429 individuals, with 20 (4.7%) experiencing the outcome, which comprised 0.98% of all subjects with the outcome. While logistic regression showed less model overfitting, it likewise failed to achieve the stated objective.<h4>Conclusions</h4>High-fidelity prediction of near-future critical illness among community-dwelling adults was not successful using population-based administrative data. Additional research is needed to ascertain whether the inclusion of additional types of data can achieve this goal.","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022","modification":"2025-04-04T12:34:33.096Z","creation":"2025-04-04T12:34:33.096Z"},"accession":"S-EPMC10910992","cross_references":{"pubmed":["38455278"],"doi":["10.3389/fepid.2022.944216"]}}