1. Predicting Short-Term Mortality in Older Patients Discharged from Acute Hospitalizations Lasting Less Than 24 Hours
- Author
-
Heltø ALK, Rosager EV, Aasbrenn M, Maule CF, Petersen J, Nielsen FE, Suetta C, and Gregersen R
- Subjects
machine-learning ,prediction model ,register-based ,geriatric ,emergency medicine ,early discharge ,Infectious and parasitic diseases ,RC109-216 - Abstract
Amalia Lærke Kjær Heltø,1,2 Emilie Vangsgaard Rosager,1,2 Martin Aasbrenn,3 Cathrine Fox Maule,4 Janne Petersen,4,5 Finn Erland Nielsen,1 Charlotte Suetta,3 Rasmus Gregersen1,4,5 1Department of Emergency Medicine, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark; 2Faculty of Health and Medical Sciences, University of Copenhagen, Copenhagen, Denmark; 3Department of Geriatrics and Palliative Medicine, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark; 4Center of Clinical Research and Prevention, Bispebjerg and Frederiksberg Hospital, Copenhagen, Denmark; 5Section of Biostatistics, Department of Public Health, University of Copenhagen, Copenhagen, DenmarkCorrespondence: Amalia Lærke Kjær Heltø, Bispebjerg and Frederiksberg Hospital, Department of Emergency Medicine, Ebba Lunds Vej 40A, Building 67, 2. floor, Copenhagen, NV, 2400, Denmark, Tel +45 60654575, Email amalia.laerke.kjaer.heltoe.01@regionh.dkPurpose: 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
- Published
- 2023