Improving identification and management of familial hypercholesterolaemia in primary care: Pre- and post-intervention study

Weng, Stephen; Kai, Joe; Tranter, Jennifer; Leonardi‐Bee, Jo; Qureshi, Nadeem

doi:10.1016/j.atherosclerosis.2018.04.037

Cited by 19 publications

(15 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, there has been a drive to develop bespoke algorithms derived from large electronic health records (EHRs) to detect FH. The SEARCH study in the US 13 used an electronic version of the DLCN criteria, while the FAMCAT tool in the UK 14 – 16 and FindFH model in the US 17 have been recently developed from prediction modelling. Using standard logistic regression, area under receiver operating curves (AUC) for FAMCAT were from 0.86 in its development database (UK Clinical Practice Research Datalink) 18 , to 0.83 and 0.84 in two separate external validation databases 14 , 15 (QRESEARCH and RCGP Surveillance Network).…”

Section: Introductionmentioning

confidence: 99%

Performance and clinical utility of supervised machine-learning approaches in detecting familial hypercholesterolaemia in primary care

et al. 2020

Self Cite

View full text Add to dashboard Cite

Familial hypercholesterolaemia (FH) is a common inherited disorder, causing lifelong elevated low-density lipoprotein cholesterol (LDL-C). Most individuals with FH remain undiagnosed, precluding opportunities to prevent premature heart disease and death. Some machine-learning approaches improve detection of FH in electronic health records, though clinical impact is under-explored. We assessed performance of an array of machine-learning approaches for enhancing detection of FH, and their clinical utility, within a large primary care population. A retrospective cohort study was done using routine primary care clinical records of 4,027,775 individuals from the United Kingdom with total cholesterol measured from 1 January 1999 to 25 June 2019. Predictive accuracy of five common machine-learning algorithms (logistic regression, random forest, gradient boosting machines, neural networks and ensemble learning) were assessed for detecting FH. Predictive accuracy was assessed by area under the receiver operating curves (AUC) and expected vs observed calibration slope; with clinical utility assessed by expected case-review workload and likelihood ratios. There were 7928 incident diagnoses of FH. In addition to known clinical features of FH (raised total cholesterol or LDL-C and family history of premature coronary heart disease), machine-learning (ML) algorithms identified features such as raised triglycerides which reduced the likelihood of FH. Apart from logistic regression (AUC, 0.81), all four other ML approaches had similarly high predictive accuracy (AUC > 0.89). Calibration slope ranged from 0.997 for gradient boosting machines to 1.857 for logistic regression. Among those screened, high probability cases requiring clinical review varied from 0.73% using ensemble learning to 10.16% using deep learning, but with positive predictive values of 15.5% and 2.8% respectively. Ensemble learning exhibited a dominant positive likelihood ratio (45.5) compared to all other ML models (7.0–14.4). Machine-learning models show similar high accuracy in detecting FH, offering opportunities to increase diagnosis. However, the clinical case-finding workload required for yield of cases will differ substantially between models.

show abstract

Section: Introductionmentioning

confidence: 99%

Performance and clinical utility of supervised machine-learning approaches in detecting familial hypercholesterolaemia in primary care

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In a study of 32 patients diagnosed with possible FH, Weng et al found that primary care intervention resulted in small and non-significant reductions in total cholesterol (−2%) and LDL-cholesterol (−3%). 24 Our research has extended these studies to an Australia-wide primary care-based programme for detection and management of new FH index cases.…”

Section: Discussionmentioning

confidence: 99%

Improving detection and management of familial hypercholesterolaemia in Australian general practice

Brett

Chan

Radford

et al. 2021

Heart

View full text Add to dashboard Cite

ObjectiveFamilial hypercholesterolaemia (FH) is characterised by elevated low-density lipoprotein (LDL)-cholesterol and increased risk of cardiovascular disease. However, FH remains substantially underdiagnosed and undertreated. We employed a two-stage pragmatic approach to identify and manage patients with FH in primary healthcare.MethodsMedical records for 232 139 patients who attended 15 general practices at least once in the previous 2 years across five Australian States were first screened for potential risk of FH using an electronic tool (TARB-Ex) and confirmed by general practitioner (GP) clinical assessment based on phenotypic Dutch Lipid Clinic Network Criteria (DLCNC) score. Follow-up GP consultation and management was provided for patients with phenotypic FH.ResultsA total of 1843 patients were identified by TARB-Ex as at potential risk of FH (DLCNC score ≥5). After GP medical record review, 900 of these patients (49%) were confirmed with DLCNC score ≥5 and classified as high-risk of FH. From 556 patients subsequently clinically assessed by GPs, 147 (26%) were diagnosed with phenotypic FH (DLCNC score >6). Follow-up GP consultation and management for 77 patients resulted in a significant reduction in LDL-cholesterol (−16%, p<0.01). A higher proportion of these patients attained the treatment target of 50% reduction in LDL-cholesterol (74% vs 62%, p<0.001) and absolute levels of LDL-cholesterol goals compared with baseline (26% vs 12%, p<0.05).ConclusionsA pragmatic approach integrating electronic medical record tools and clinical GP follow-up consultation is a feasible method to identify and better manage patients with FH in the primary healthcare setting.Trial registration number12616000630415.

show abstract

“…A UK study by Weng et al showed that an intervention to identify and manage patients with FH in a primary health setting could be successfully adopted. 22 Their research revealed improvements in best practice for identification and management of FH following an educational intervention among participating general practices.…”

Section: Discussionmentioning

confidence: 99%

Awareness of familial hypercholesterolaemia in Australian primary care: A qualitative descriptive study

Bulsara¹,

Brett²,

Radford³

et al. 2021

Aust J Gen Pract

View full text Add to dashboard Cite

Background and objectiveA lack of public and health professional awareness about familial hypercholesterolaemia (FH) leads to an estimated 90,000 Australians remaining undiagnosed. The aim of this study was to establish the level of knowledge and awareness of FH in Australian general practices. MethodsA qualitative descriptive methodology was used to explore baseline knowledge and perceptions of practice staff about diagnosing and managing FH. Overall, 63 interviews were conducted with general practice staff at 15 practices taking part in a National Health and Medical Research Council partnership grant study (GNT1142883). ResultsData were analysed thematically and coded into themes -knowledge/awareness/recall, management, use of guidelines/referrals, and contacting family members. Most general practitioners treated the high cholesterol component as their primary focus. Guidelines and referrals were rarely used. DiscussionThis research reflected a lack of knowledge, awareness and use of guidelines similar to that shown in other published studies. Improved primary care infrastructure, knowledge and awareness of FH need to be addressed.

show abstract

Improving identification and management of familial hypercholesterolaemia in primary care: Pre- and post-intervention study

Cited by 19 publications

References 31 publications

Performance and clinical utility of supervised machine-learning approaches in detecting familial hypercholesterolaemia in primary care

Performance and clinical utility of supervised machine-learning approaches in detecting familial hypercholesterolaemia in primary care

Improving detection and management of familial hypercholesterolaemia in Australian general practice

Awareness of familial hypercholesterolaemia in Australian primary care: A qualitative descriptive study

Contact Info

Product

Resources

About