Predicting Short-Term Mortality in Older Patients Discharged from Acute Hospitalizations Lasting Less Than 24 Hours

Abstract

Purpose

Over coming decades, a rise in the number of short, acute hospitalizations of older people is to be expected. To help physicians identify high-risk patients prior to discharge, we aimed to develop a model capable of predicting the risk of 30-day mortality for older patients discharged from short, acute hospitalizations and to examine how model performance changed with an increasing amount of information.

Methods

This registry-based study included acute hospitalizations in Denmark for 2016–2018 lasting ≤24 hours where patients were permanent residents, ≥65 years old, and discharged alive. Utilizing many different predictor variables, we developed random forest models with an increasing amount of information, compared their performance, and examined important variables.

Results

We included 107,132 patients with a median age of 75 years. Of these, 3.3% (n=3575) died within 30 days of discharge. Model performance improved especially with the addition of laboratory results and information on prior acute admissions (AUROC 0.835), and again with comorbidities and number of prescription drugs (AUROC 0.860). Model performance did not improve with the addition of sociodemographic variables (AUROC 0.861), apart from age and sex. Important variables included age, dementia, number of prescription drugs, C-reactive protein, and eGFR.

Conclusion

The best model accurately estimated the risk of short-term mortality for older patients following short, acute hospitalizations. Trained on a large and heterogeneous dataset, the model is applicable to most acute clinical settings and could be a useful tool for physicians prior to discharge.

Keywords:

• machine learning
• prediction model
• register-based
• geriatric
• emergency medicine
• early discharge

Data Sharing

Register-based data is protected by Danish legislations and cannot be shared neither publicly, nor privately. Danish research institutions can apply for equivalent data through the Danish Health Data Authority and Statistics Denmark.

Ethics Approval

Ethics approval is not required for registry-based studies in Denmark. The project was approved by Statistics Denmark (project 707838), Danish Health Data Authority (FSEID-00004732), and Data Protection Agency (P-2019-616).

Disclosure

The authors have no conflicts of interest to declare for this work.

Additional information

Funding

The project was financed by the Bispebjerg and Frederiksberg Hospital Research Committee and the Department of Emergency Medicine. The financial support was used for salary support. The funding sources did not play any part in the design process, conduction, or analysis of the project.