Objective: Early identification of emergency department (ED) patients who need hospitalization is essential for quality of care and patient safety. We aimed to compare machine learning (ML) models... Show moreObjective: Early identification of emergency department (ED) patients who need hospitalization is essential for quality of care and patient safety. We aimed to compare machine learning (ML) models predicting the hospitalization of ED patients and conventional regression techniques at three points in time after ED registration.Methods: We analyzed consecutive ED patients of three hospitals using the Netherlands Emergency Department Evaluation Database (NEED). We developed prediction models for hospitalization using an increasing number of data available at triage, similar to 30 min (including vital signs) and similar to 2 h (including laboratory tests) after ED registration, using ML (random forest, gradient boosted decision trees, deep neural networks) and multivariable logistic regression analysis (including spline transformations for continuous predictors). Demographics, urgency, presenting complaints, disease severity and proxies for comorbidity, and complexity were used as covariates. We compared the performance using the area under the ROC curve in independent validation sets from each hospital.Results: We included 172,104 ED patients of whom 66,782 (39 %) were hospitalized. The AUC of the multi-variable logistic regression model was 0.82 (0.78-0.86) at triage, 0.84 (0.81-0.86) at similar to 30 min and 0.83 (0.75-0.92) after similar to 2 h. The best performing ML model over time was the gradient boosted decision trees model with an AUC of 0.84 (0.77-0.88) at triage, 0.86 (0.82-0.89) at similar to 30 min and 0.86 (0.74-0.93) after similar to 2 h.Conclusions: Our study showed that machine learning models had an excellent but similar predictive performance as the logistic regression model for predicting hospital admission. In comparison to the 30-min model, the 2-h model did not show a performance improvement. After further validation, these prediction models could support management decisions by real-time feedback to medical personal. Show less
Older emergency department (ED) patients are at high risk of adverse health outcomes, such as mortality or functional decline. Early identification of those patients who are at highest risk gives... Show moreOlder emergency department (ED) patients are at high risk of adverse health outcomes, such as mortality or functional decline. Early identification of those patients who are at highest risk gives an opportunity to target interventions and guide treatment decisions for those who need it most.This thesis describes the clinical value of using geriatric screening in the ED. Geriatric screening identifies older patients at high risk of both short- and long-term poor outcomes and provides valuable information for care providers treating acutely hospitalized older patients. The results from screening could aid in individualized treatment decisions to acquire more personalized care, and therefore gives an opportunity to optimize outcomes for older patients.Implementation of screening programs in the fast-paced environment of everyday ED practice remains scarce. The results of this thesis show that the implementation of a geriatric screening program in routine ED practice is feasible and the use of screening is accepted by both the users (triage nurses) and the older patients.Using geriatric screening in routine care is therefore useful and feasible. More research will be needed to investigate implementation in different hospitals to generate guidance on how geriatric screening tools can be successfully implemented on a wide scale. Show less
Blomaard, L.C.; Olthof, M.; Meuleman, Y.; Groot, B. de; Gussekloo, J.; Mooijaart, S.P. 2021
BackgroundThe patient perspective on the use of screening for high risks of adverse health outcomes in Emergency Department (ED) care is underexposed, although it is an important perspective... Show moreBackgroundThe patient perspective on the use of screening for high risks of adverse health outcomes in Emergency Department (ED) care is underexposed, although it is an important perspective influencing implementation in routine care. This study explores the experiences with, and attitudes towards geriatric screening in routine ED care among older people who visited the ED.MethodsThis was a qualitative study using individual face-to-face semi-structured interviews. Interviews were conducted in older patients (>= 70years) who completed the 'Acutely Presenting Older Patient' screener while visiting the ED of a Dutch academic hospital. Purposive convenience sampling was used to select a heterogeneous sample of participants regarding age, disease severity and the result from screening. Transcripts were analyzed inductively using thematic analysis.ResultsAfter 13 interviews (7 women, median age 82years), data saturation was reached. The participants had noticed little of the screening administration during triage and screening was considered as a normal part of ED care. Most participants believed that geriatric screening contributes to assessing older patients holistically, recognizing geriatric problems early and comforting patients with communication and attention. None of the participants had a negative attitude towards screening or thought that screening is discrimination on age. Care providers should communicate respectfully with frail older patients and involve them in decision-making.ConclusionsOlder patients experienced geriatric screening as a normal part of ED care and had predominantly positive attitudes towards its use in the ED. This qualitative study advocates for continuing the implementation of geriatric screening in routine ED practice. Show less