A review of the evidence on the effects and costs of implantable cardioverter defibrillator therapy in different patient groups, and modelling of cost-effectiveness and cost-utility for these groups in a UK context

Abstract

Objectives: To update the systematic review evidence on the effectiveness, health-related quality of life (HRQoL) and cost-effectiveness of implantable cardioverter defibrillators (ICDs); compilation of new data on the service provision in the UK; and on the clinical characteristics, survival, quality of life and costs of ICD patients in the UK, and a new cost-effectiveness model using both international RCT and UK-specific data.

Data sources: Electronic databases searched from November 1999 to March 2003, this was supplemented by a systematic review of research published during 2003-5. Survey data.

Review methods: Studies were selected and assessed. A survey of ICD centres was carried out. Basic data were obtained from two major implanting centres including 535 patients (approximately 10% of overall UK activity) implanted between 1991 and 2002, and retrieval of fuller data, on patient characteristics, management and resource use, from patient notes for a sample of 426 patients was attempted. A cross-sectional survey collected HRQoL data (using the Nottingham Health Profile, Short Form 36, Hospital Anxiety and Depression questionnaire, EuroQoL 5 Dimensions and disease-specific questions) on a sample of 229 patients. A Markov model combined UK patient data with data from published randomised controlled trials (RCTs) to estimate incremental costs per life-year or quality-adjusted life-year (QALY) gained.

Results: None of the economic analyses in the studies found could be directly applied to the UK. The multiple sources of routine data available (including the national ICD database) provide an imperfect picture of the need for and use of ICDs. Implantation rates have been rising to a rate of around 20 per million population. Mean age is increasing and most ICDs are implanted into men aged 45-74 years. There is significant geographical variation. A survey of 41 UK centres provided additional evidence, particularly of variation in level of activity and resourcing. Most detailed data were obtained for 380 patients (89%). The postal survey produced a 73% response rate. Demographic characteristics of these patients were similar to ICD recipients in the UK as a whole and patients included in secondary prevention RCTs. Mean actuarial survival at 1, 3 and 5 years was 92%, 86% and 71%, respectively. Patient age at implantation and functional status significantly affected survival. Levels of most of the HRQoL measures were lower than for a UK general population. There was no evidence of a change with time from implantation. Patients who had suffered ICD shocks had significantly poorer HRQoL. Most patients nevertheless expressed a high level of satisfaction with ICD therapy. Mean initial costs of implantation showed little variation between centres (23,300 pounds versus 22,100 pounds) or between earlier and more recent implants. There appeared to be greater variation between patients presenting along different pathways. Postdischarge costs (tests, medications and follow-up consultations) and costs of additional hospitalisations were also calculated. Using the Markov model it was found that over a 20-year horizon, mean discounted incremental costs were 70,900 pounds (35,000-142,400 pounds). Mean discounted gain was 1.24 years (0.29-2.32) or 0.93 QALYs. Cost-effectiveness was most favourable for men aged over 70 years with a left ventricular ejection fraction (LVEF) below 35%. If the treatment effect were to continue, then the cost per life-year over a lifetime might fall to around 32,000 pounds. Five RCTs of ICDs, a meta-analysis and, a cost-effectiveness analysis of ICDs used in primary prevention, and a meta-analysis of ICDs in patients with non-ischaemic cardiomyopathy have been published recently. These trials provide confirmation of survival benefit of ICDs used in primary prevention in both ischaemic and non-ischaemic cardiomyopathy patients. Costs per QALY ranged from US$34,000 in older trials to controls being both less expensive and more effective (CABG Patch, DINAMIT). More recent trials estimated cost per QALY between $50,300 and $70,200. The inconsistency in evidence for a HRQoL benefit has not been resolved and further work on risk stratification is necessary.

Conclusions: The evidence of short- to medium-term patient benefit from ICDs is strong but cost-effectiveness modelling indicates that the extent of that benefit is probably not sufficient to make the technology cost-effective as used currently in the UK. One reason is the high rates of postimplantation hospitalisation. Better patient targeting and efforts to reduce the need for such hospitalisation may improve cost-effectiveness. Further cost-effectiveness modelling, underpinned by an improved ICD database with reliable long-term follow-up, is required. The absence of a robust measure of the incidence of sudden cardiac death is noted and this may be an area where further organisational changes with improved data collection would help.