Detection of familial hypercholesterolaemia: external validation of the FAMCAT clinical case-finding algorithm to identify patients in primary care

Abstract

Background: The vast majority of individuals with familial hypercholesterolaemia in the general population remain unidentified worldwide. Recognising patients most likely to have the condition, to enable targeted specialist assessment and treatment, could prevent major coronary morbidity and mortality. We aimed to evaluate a clinical case-finding algorithm, the familial hypercholesterolaemia case ascertainment tool (FAMCAT), and compare it with currently recommended methods for detection of familial hypercholesterolaemia in primary care.

Methods: In this external validation study, FAMCAT regression equations were applied to a retrospective cohort of patients aged 16 years or older with cholesterol assessed, who were randomly selected from 1500 primary care practices across the UK contributing to the QResearch database. In the main analysis, we assessed the ability of FAMCAT to detect familial hypercholesterolaemia (ie, its discrimination) and compared it with that of other established clinical case-finding approaches recommended internationally (Simon Broome, Dutch Lipid Clinic Network, Make Early Diagnosis to Prevent Early Deaths [MEDPED] and cholesterol concentrations higher than the 99th percentile of the general population in the UK). We assessed discrimination by area under the receiver operating curve (AUROC; ranging from 0·5, indicating pure chance, to 1, indicating perfect discrimination). Using a probability threshold of more than 1 in 500 (prevalence of familial hypercholesterolaemia), we also assessed sensitivity, specificity, positive predictive values, and negative predictive values in the main analysis.

Findings: A sample of 750 000 patients who registered in 1500 UK primary care practices that contribute anonymised data to the QResearch database between Jan 1, 1999, and Sept 1, 2017, was randomly selected, of which 747 000 patients were assessed. FAMCAT showed a high degree of discrimination (AUROC 0·832, 95% CI 0·820-0·845), which was higher than that of Simon Broome criteria (0·694, 0·681-0·703), Dutch Lipid Clinic Network criteria (0·724, 0·710-0·738), MEDPED criteria (0·624, 0·609-0·638), and screening cholesterol concentrations higher than the 99th percentile (0·581, 0·570-0·591). Using a 1 in 500 probability threshold, FAMCAT achieved a sensitivity of 84% (1028 predicted vs 1219 observed cases) and specificity of 60% (443 949 predicted vs 745 781 observed non-cases), with a corresponding positive predictive value of 0·84% and a negative predictive value of 99·2%.

Interpretation: FAMCAT identifies familial hypercholesterolaemia with greater accuracy than currently recommended approaches and could be considered for clinical case finding of patients with the highest likelihood of having hypercholesterolaemia in primary care.

Funding: UK National Institute for Health Research School for Primary Care Research.

Figure 1

AUROCs derived from the external validation cohort (n=747 000) for FAMCAT subgroup analysis Higher area under the curve (c statistic) confers better discrimination. AUROC=area under the receiver operating curve. FAMCAT=familial hypercholesterolaemia case ascertainment tool.

Figure 2

AUROCs derived from the external validation cohort (n=747 000) for FAMCAT sensitivity analysis Higher area under the curve (c statistic) confers better discrimination. AUROC=area under the receiver operating curve. FAMCAT=familial hypercholesterolaemia case ascertainment tool.