• Catriona Crossan, Emmanuel A Tsochatzis, Louise Longworth, Kurinchi Gurusamy, Brian Davidson, Manuel Rodríguez-Perálvarez, Konstantinos Mantzoukis, Julia O'Brien, Evangelos Thalassinos, Vassilios Papastergiou, and Andrew Burroughs.
• Health Economics Research Group, Brunel University London, Uxbridge, UK.
• Health Technol Assess. 2015 Jan 1; 19 (9): 1-409, v-vi.

BackgroundLiver biopsy is the reference standard for diagnosing the extent of fibrosis in chronic liver disease; however, it is invasive, with the potential for serious complications. Alternatives to biopsy include non-invasive liver tests (NILTs); however, the cost-effectiveness of these needs to be established.ObjectiveTo assess the diagnostic accuracy and cost-effectiveness of NILTs in patients with chronic liver disease.Data SourcesWe searched various databases from 1998 to April 2012, recent conference proceedings and reference lists.MethodsWe included studies that assessed the diagnostic accuracy of NILTs using liver biopsy as the reference standard. Diagnostic studies were assessed using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. Meta-analysis was conducted using the bivariate random-effects model with correlation between sensitivity and specificity (whenever possible). Decision models were used to evaluate the cost-effectiveness of the NILTs. Expected costs were estimated using a NHS perspective and health outcomes were measured as quality-adjusted life-years (QALYs). Markov models were developed to estimate long-term costs and QALYs following testing, and antiviral treatment where indicated, for chronic hepatitis B (HBV) and chronic hepatitis C (HCV). NILTs were compared with each other, sequential testing strategies, biopsy and strategies including no testing. For alcoholic liver disease (ALD), we assessed the cost-effectiveness of NILTs in the context of potentially increasing abstinence from alcohol. Owing to a lack of data and treatments specifically for fibrosis in patients with non-alcoholic fatty liver disease (NAFLD), the analysis was limited to an incremental cost per correct diagnosis. An analysis of NILTs to identify patients with cirrhosis for increased monitoring was also conducted.ResultsGiven a cost-effectiveness threshold of £20,000 per QALY, treating everyone with HCV without prior testing was cost-effective with an incremental cost-effectiveness ratio (ICER) of £9204. This was robust in most sensitivity analyses but sensitive to the extent of treatment benefit for patients with mild fibrosis. For HBV [hepatitis B e antigen (HBeAg)-negative)] this strategy had an ICER of £28,137, which was cost-effective only if the upper bound of the standard UK cost-effectiveness threshold range (£30,000) is acceptable. For HBeAg-positive disease, two NILTs applied sequentially (hyaluronic acid and magnetic resonance elastography) were cost-effective at a £20,000 threshold (ICER: £19,612); however, the results were highly uncertain, with several test strategies having similar expected outcomes and costs. For patients with ALD, liver biopsy was the cost-effective strategy, with an ICER of £822.LimitationsA substantial number of tests had only one study from which diagnostic accuracy was derived; therefore, there is a high risk of bias. Most NILTs did not have validated cut-offs for diagnosis of specific fibrosis stages. The findings of the ALD model were dependent on assuptions about abstinence rates assumptions and the modelling approach for NAFLD was hindered by the lack of evidence on clinically effective treatments.ConclusionsTreating everyone without NILTs is cost-effective for patients with HCV, but only for HBeAg-negative if the higher cost-effectiveness threshold is appropriate. For HBeAg-positive, two NILTs applied sequentially were cost-effective but highly uncertain. Further evidence for treatment effectiveness is required for ALD and NAFLD.Study RegistrationThis study is registered as PROSPERO CRD42011001561.FundingThe National Institute for Health Research Health Technology Assessment programme.

64 keywords...

hide…