Proof-of-concept for an automatable mortality prediction scoring in hospitalised older adults

TL;DR

This study presents a mortality prediction tool for older hospitalized patients using electronic health records to improve end-of-life care and reduce unnecessary healthcare use.

Contribution

A novel automatable mortality prediction model for older adults using electronic health records with minimal manual input.

Findings

The model achieved an AUC of 0.752 for predicting early death and 0.691 for late death.

Key predictors of mortality included age, frailty, comorbidity index, and specific diagnoses like pneumonia and AMI.

The tool could enable automated alerts for personalized care in hospitalized older adults.

Abstract

It is challenging to prognosticate hospitalised older adults. Delayed recognition of end-of-life leads to failure in delivering appropriate palliative care and increases healthcare utilisation. Most mortality prediction tools specific for older adults require additional manual input, resulting in poor uptake. By leveraging on electronic health records, we aim to create an automatable mortality prediction tool for hospitalised older adults.

We retrospectively reviewed electronic records of general medicine patients ≥75 years at a tertiary hospital between April–September 2021. Demographics, comorbidities, ICD-codes, age-adjusted Charlson Comorbidity Index (CCI), Hospital Frailty Risk Score, mortality and resource utilization were collected. We defined early deaths, late deaths and survivors as patients who died within 30 days, 1 year, and lived beyond 1 year of admission, respectively. Multivariate logistic regression analyses were adjusted for age, gender, race, frailty, and CCI. The final prediction model was created using a stepwise logistic regression.

Of 1,224 patients, 168 (13.7%) died early and 370 (30.2%) died late. From adjusted multivariate regression, risk of early death was significantly associated with ≥85 years, intermediate or high frail risk, CCI > 6, cardiovascular risk factors, AMI and pneumonia. For late death, risk factors included ≥85 years, intermediate frail risk, CCI >6, delirium, diabetes, AMI and pneumonia. Our mortality prediction tool which scores 1 point each for age, pneumonia and AMI had an AUC of 0.752 for early death and 0.691 for late death.

Our mortality prediction model is a proof-of-concept demonstrating the potential for automated medical alerts to guide physicians towards personalised care for hospitalised older adults.