Do Patient-Reported Outcome Measures help Predict Unplanned Hospital Readmission or Mortality?

Date:

Tue, 22 Oct 2024

Time:

2.30 pm-3.30pm [Singapore [GMT +8]

Location:

Conference Room 1 & 2, Level 10
Tahir Foundation Building (MD1)
National University of Singapore
12 Science Drive 2, Singapore 117549

Details:

You are cordially invited to the ON-SITE SSHSPH Staff Research Round. We look forward to your attendance and we hope for an interesting discussion.

Do hang around after the talk as coffee and tea will be provided.

Abstract:

Unplanned hospital readmissions significantly impact patient outcomes and healthcare costs globally. While prediction models are widely used to identify patients at high risk of readmissions, their discriminative ability often falls short of achieving adequate accuracy. It has been hypothesized that including routinely collected patient reported outcomes measures (PROMs) might improve predictions since they include aspects of health (e.g. pain, mobility, anxiety) not captured in administrative or clinical data. This talk will describe results from a retrospective population-based cohort study in British Columbia, Canada where surveys in patients recently discharged from hospital were linked to longitudinal administrative healthcare databases. The analysis includes 9,148 patients who completed surveys (which included the PROMs EQ-5D and VR-12) within 60 days of discharge. Prediction models were constructed using both traditional statistical methods and machine learning techniques. Models were run with and without PROM data and model performance compared.

Speakers:

Dr Nick Bansback
Professor of Health Economics, School of Population and Public Health, University of British Columbia

Dr Bansback is a Professor of Health Economics at the School of Population and Public Health at the University of British Columbia, and Honorary visiting Professor at the Saw Swee Hock School of Public Health. His research focuses on policymakers and aims to increase value in the health care system, through research on economic evaluation, patient preferences and patient reported outcomes.