biostudies-literatureUnknown2Garland A<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.Frontiers in epidemiology944216https://www.ebi.ac.uk/biostudies/studies/S-EPMC10910992biostudies-literatureAdministrative Data Is Insufficient to Identify Near-Future Critical Illness: A Population-Based Retrospective Cohort Study.PMC10910992Marrie RAWunsch HChateau DGarland AYogendran MfalseAdministrative Data Is Insufficient to Identify Near-Future Critical Illness: A Population-Based Retrospective Cohort Study.<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.2022-01-01T00:00:00Z20222025-04-04T12:34:33.096Z2025-04-04T12:34:33.096ZS-EPMC109109923845527810.3389/fepid.2022.944216