Related Experiment Video
Updated: Feb 23, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Effectiveness and cost-effectiveness of a cardiovascular risk prediction algorithm for people with severe mental
Ella Zomer1,2, David Osborn3,4, Irwin Nazareth2
1Department of Epidemiology and Preventive Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
Objectives:
To determine the cost-effectiveness of two bespoke severe mental illness (SMI)-specific risk algorithms compared with standard risk algorithms for primary cardiovascular disease (CVD) prevention in those with SMI.
Setting:
Primary care setting in the UK. The analysis was from the National Health Service perspective.
Participants:
1000 individuals with SMI from The Health Improvement Network Database, aged 30-74 years and without existing CVD, populated the model.
Interventions:
Four cardiovascular risk algorithms were assessed: (1) general population lipid, (2) general population body mass index (BMI), (3) SMI-specific lipid and (4) SMI-specific BMI, compared against no algorithm. At baseline, each cardiovascular risk algorithm was applied and those considered high risk (> 10%) were assumed to be prescribed statin therapy while others received usual care.
Primary And Secondary Outcome Measures:
Quality-adjusted life years (QALYs) and costs were accrued for each algorithm including no algorithm, and cost-effectiveness was calculated using the net monetary benefit (NMB) approach. Deterministic and probabilistic sensitivity analyses were performed to test assumptions made and uncertainty around parameter estimates.
Results:
The SMI-specific BMI algorithm had the highest NMB resulting in 15 additional QALYs and a cost saving of approximately £53 000 per 1000 patients with SMI over 10 years, followed by the general population lipid algorithm (13 additional QALYs and a cost saving of £46 000).
Conclusions:
The general population lipid and SMI-specific BMI algorithms performed equally well. The ease and acceptability of use of an SMI-specific BMI algorithm (blood tests not required) makes it an attractive algorithm to implement in clinical settings.
More Related Videos
12:18A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020