Dataset Information

Multisite development and validation of machine learning models to predict severe outcomes and guide decision-making for emergency department patients with influenza.

ABSTRACT:

Objective

Millions of Americans are infected by influenza annually. A minority seek care in the emergency department (ED) and, of those, only a limited number experience severe disease or death. ED clinicians must distinguish those at risk for deterioration from those who can be safely discharged.

Methods

We developed random forest machine learning (ML) models to estimate needs for critical care within 24 h and inpatient care within 72 h in ED patients with influenza. Predictor data were limited to those recorded prior to ED disposition decision: demographics, ED complaint, medical problems, vital signs, supplemental oxygen use, and laboratory results. Our study population was comprised of adults diagnosed with influenza at one of five EDs in our university health system between January 1, 2017 and May 18, 2022; visits were divided into two cohorts to facilitate model development and validation. Prediction performance was assessed by the area under the receiver operating characteristic curve (AUC) and the Brier score.

Results

Among 8032 patients with laboratory-confirmed influenza, incidence of critical care needs was 6.3% and incidence of inpatient care needs was 19.6%. The most common reasons for ED visit were symptoms of respiratory tract infection, fever, and shortness of breath. Model AUCs were 0.89 (95% CI 0.86-0.93) for prediction of critical care and 0.90 (95% CI 0.88-0.93) for inpatient care needs; Brier scores were 0.026 and 0.042, respectively. Importantpredictors included shortness of breath, increasing respiratory rate, and a high number of comorbid diseases.

Conclusions

ML methods can be used to accurately predict clinical deterioration in ED patients with influenza and have potential to support ED disposition decision-making.

SUBMITTER: Hinson JS

PROVIDER: S-EPMC10945311 | biostudies-literature | 2024 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multisite development and validation of machine learning models to predict severe outcomes and guide decision-making for emergency department patients with influenza.

Hinson Jeremiah S JS Zhao Xihan X Klein Eili E Badaki-Makun Oluwakemi O Rothman Richard R Copenhaver Martin M Smith Aria A Fenstermacher Katherine K Toerper Matthew M Pekosz Andrew A Levin Scott S

Journal of the American College of Emergency Physicians open 20240318 2

<h4>Objective</h4>Millions of Americans are infected by influenza annually. A minority seek care in the emergency department (ED) and, of those, only a limited number experience severe disease or death. ED clinicians must distinguish those at risk for deterioration from those who can be safely discharged.<h4>Methods</h4>We developed random forest machine learning (ML) models to estimate needs for critical care within 24 h and inpatient care within 72 h in ED patients with influenza. Predictor da ...[more]

PMID: 38500599

Similar Datasets

Project description:ObjectivesAs shared decision making (SDM) has received increased attention as a method to improve the patient-centeredness of emergency department (ED) care, we sought to determine patients' desired level of involvement in medical decisions and their perceptions of potential barriers and facilitators to SDM in the ED.MethodsWe surveyed a cross-sectional sample of adult ED patients at three academic medical centers across the United States. The survey included 32 items regarding patient involvement in medical decisions including a modified Control Preference Scale and questions about barriers and facilitators to SDM in the ED. Items were developed and refined based on prior literature and qualitative interviews with ED patients. Research assistants administered the survey in person.ResultsOf 797 patients approached, 661 (83%) agreed to participate. Participants were 52% female, 45% white, and 30% Hispanic. The majority of respondents (85%-92%, depending on decision type) expressed a desire for some degree of involvement in decision making in the ED, while 8% to 15% preferred to leave decision making to their physician alone. Ninety-eight percent wanted to be involved with decisions when "something serious is going on." The majority of patients (94%) indicated that self-efficacy was not a barrier to SDM in the ED. However, most patients (55%) reported a tendency to defer to the physician's decision making during an ED visit, with about half reporting they would wait for a physician to ask them to be involved.ConclusionWe found that the majority of ED patients in our large, diverse sample wanted to be involved in medical decisions, especially in the case of a "serious" medical problem, and felt that they had the ability to do so. Nevertheless, many patients were unlikely to actively seek involvement and defaulted to allowing the physician to make decisions during the ED visit. After fully explaining the consequences of a decision, clinicians should make an effort to explicitly ascertain patients' desired level of involvement in decision making.

Dataset Information

Multisite development and validation of machine learning models to predict severe outcomes and guide decision-making for emergency department patients with influenza.

Objective

Methods

Results

Conclusions

Publications

Multisite development and validation of machine learning models to predict severe outcomes and guide decision-making for emergency department patients with influenza.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets