Leveraging patients’ longitudinal data to improve the Hospital One-year Mortality Risk
Preprint
Abstract
Purpose: Predicting medium-term survival after admission is necessary for identifying end-of-life patients who may benefit from goals of care (GOC) discussions. Considering that several patients have multiple hospital admissions, this study leverages patients’ longitudinal data and information collected routinely at admission to predict the Hospital One-year Mortality Risk. Methods: We propose an Ensemble Long Short-term Memory neural network (ELSTM) to predict one-year mortality using patients’ longitudinal records. The model was evaluated: (i) with only predictors reported upon admission (AdmDemo); and (ii) also with diagnoses available later during patients’ stay (AdmDemoDx). Using records of 123,646 patients with 250,812 hospitalizations from 2011-2021, our dataset was split into a learning set (2011-2017) to compare models with and without longitudinal information using nested cross-validation, and a holdout set (2017-2021) to assess clinical utility towards GOC discussions. Results: The ELSTM achieved a significant increase in predictive performance using longitudinal information ( p -value < 0.05) for both the AdmDemo and AdmDemoDx predictors. For randomly selected hospitalizations in the holdout set, the ELSTM showed: (i) AUROCs of 0.83 (AdmDemo) and 0.87 (AdmDemoDx); and (ii) superior decision-making properties, notably with an increase in precision from 0.25 for the standard process to 0.28 (AdmDemo) and 0.36 (AdmDemoDx). Feature importance analysis confirmed that the utility of the longitudinal information increases with the number of patient hospitalizations. Conclusion: Integrating patients’ longitudinal data provides better insights into the severity of illness and the overall patient condition, in particular when limited information is available during their stay.Keywords
All Related Versions
- Published version: Health Information Science and Systems, 13 (1), 1.
This publication has 28 references indexed in Scilit:
- Utilizing Longitudinal Data in Assessing All-Cause Mortality in Patients Hospitalized with Heart FailureESC Heart Failure, 2022
- Long-term mortality risk stratification of liver transplant recipients: real-time application of deep learning algorithms on longitudinal dataThe Lancet Digital Health, 2021
- Optuna2019
- mHOMR: a feasibility study of an automated system for identifying inpatients having an elevated risk of 1-year mortalityBMJ Quality & Safety, 2019
- Access to palliative care by disease trajectory: a population-based cohort of Ontario decedentsBMJ Open, 2018
- Effects of End-of-Life Discussions on the Mental Health of Bereaved Family Members and Quality of Patient Death and CareJournal of Pain and Symptom Management, 2017
- The implications of ageing and life expectancy in prostate cancer treatmentNature Reviews Urology, 2016
- The Hospital-patient One-year Mortality Risk score accurately predicted long-term death risk in hospitalized patientsJournal of Clinical Epidemiology, 2014
- Prognostic Indices for Older AdultsJAMA, 2012
- Index for rating diagnostic testsCancer, 1950