Jan Kafol, Beatriz Miranda, Rok Sikonja, Jaka Sikonja, Albert Wiegman, Ana Margarida Medeiros, Ana Catarina Alves, Tomas Freiberger, Barbara A Hutten, Matej Mlinaric, Tadej Battelino, Steve E Humphries, Mafalda Bourbon, Urh Groselj
{"title":"Proposal of a Familial Hypercholesterolemia Pediatric Diagnostic Score (FH-PeDS).","authors":"Jan Kafol, Beatriz Miranda, Rok Sikonja, Jaka Sikonja, Albert Wiegman, Ana Margarida Medeiros, Ana Catarina Alves, Tomas Freiberger, Barbara A Hutten, Matej Mlinaric, Tadej Battelino, Steve E Humphries, Mafalda Bourbon, Urh Groselj","doi":"10.1093/eurjpc/zwaf352","DOIUrl":null,"url":null,"abstract":"<p><strong>Background and aims: </strong>Familial hypercholesterolemia (FH) significantly increases cardiovascular risk from childhood yet remains widely underdiagnosed. This cross-sectional study aimed to evaluate existing pediatric FH diagnostic criteria in real-world cohorts and to develop two novel diagnostic tools: a semi-quantitative scoring system (FH-PeDS) and a machine learning model (ML-FH-PeDS) to enhance early FH detection.</p><p><strong>Methods: </strong>Five established FH diagnostic criteria were assesed (Dutch Lipid Clinics Network [DLCN], Simon Broome, EAS, Simplified Canadian, and Japanese Atherosclerosis Society) in Slovenian (N=1,360) and Portuguese (N=340) pediatric hypercholesterolemia cohorts, using FH-causing variants as the reference standard. FH-PeDS was developed from the Slovenian cohort, and ML-FH-PeDS was trained and tested using a 60%/40% split before external validation in the Portuguese cohort.</p><p><strong>Results: </strong>Only 47.4% of genetically confirmed FH cases were identified by all established criteria, while 10.9% were missed entirely. FH-PeDS outperformed DLCN in the combined cohort (AUC 0.897 vs. 0.857; p<0.01). ML-FH-PeDS showed superior predictive power (AUC 0.932 in training, 0.904 in testing vs. 0.852 for DLCN; p<0.01) and performed best as a confirmatory test in the testing subgroup (39.7% sensitivity, 87.7% PPV at 98% specificity). In the Portuguese cohort, ML-FH-PeDS maintained strong predictive performance (AUC 0.867 vs. 0.815 for DLCN; p<0.01) despite population differences.</p><p><strong>Conclusions: </strong>Current FH diagnostic criteria perform suboptimally in children. FH-PeDS and ML-FH-PeDS provide tools to improve FH detection, particularly where genetic testing is limited. They also help guide genetic testing decisions for hypercholesterolemic children. By enabling earlier diagnosis and intervention, these tools may reduce long-term cardiovascular risk and improve outcomes.</p>","PeriodicalId":12051,"journal":{"name":"European journal of preventive cardiology","volume":" ","pages":""},"PeriodicalIF":8.4000,"publicationDate":"2025-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"European journal of preventive cardiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/eurjpc/zwaf352","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Background and aims: Familial hypercholesterolemia (FH) significantly increases cardiovascular risk from childhood yet remains widely underdiagnosed. This cross-sectional study aimed to evaluate existing pediatric FH diagnostic criteria in real-world cohorts and to develop two novel diagnostic tools: a semi-quantitative scoring system (FH-PeDS) and a machine learning model (ML-FH-PeDS) to enhance early FH detection.
Methods: Five established FH diagnostic criteria were assesed (Dutch Lipid Clinics Network [DLCN], Simon Broome, EAS, Simplified Canadian, and Japanese Atherosclerosis Society) in Slovenian (N=1,360) and Portuguese (N=340) pediatric hypercholesterolemia cohorts, using FH-causing variants as the reference standard. FH-PeDS was developed from the Slovenian cohort, and ML-FH-PeDS was trained and tested using a 60%/40% split before external validation in the Portuguese cohort.
Results: Only 47.4% of genetically confirmed FH cases were identified by all established criteria, while 10.9% were missed entirely. FH-PeDS outperformed DLCN in the combined cohort (AUC 0.897 vs. 0.857; p<0.01). ML-FH-PeDS showed superior predictive power (AUC 0.932 in training, 0.904 in testing vs. 0.852 for DLCN; p<0.01) and performed best as a confirmatory test in the testing subgroup (39.7% sensitivity, 87.7% PPV at 98% specificity). In the Portuguese cohort, ML-FH-PeDS maintained strong predictive performance (AUC 0.867 vs. 0.815 for DLCN; p<0.01) despite population differences.
Conclusions: Current FH diagnostic criteria perform suboptimally in children. FH-PeDS and ML-FH-PeDS provide tools to improve FH detection, particularly where genetic testing is limited. They also help guide genetic testing decisions for hypercholesterolemic children. By enabling earlier diagnosis and intervention, these tools may reduce long-term cardiovascular risk and improve outcomes.
期刊介绍:
European Journal of Preventive Cardiology (EJPC) is an official journal of the European Society of Cardiology (ESC) and the European Association of Preventive Cardiology (EAPC). The journal covers a wide range of scientific, clinical, and public health disciplines related to cardiovascular disease prevention, risk factor management, cardiovascular rehabilitation, population science and public health, and exercise physiology. The categories covered by the journal include classical risk factors and treatment, lifestyle risk factors, non-modifiable cardiovascular risk factors, cardiovascular conditions, concomitant pathological conditions, sport cardiology, diagnostic tests, care settings, epidemiology, pharmacology and pharmacotherapy, machine learning, and artificial intelligence.