Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults
Carregando...
Citações na Scopus
1
Tipo de produção
article
Data de publicação
2023
Título da Revista
ISSN da Revista
Título do Volume
Editora
ELSEVIER IRELAND LTD
Autores
ALBUQUERQUE, Joao
MEDEIROS, Ana Margarida
ALVES, Ana Catarina
MANCINA, Rosellina M.
PAVANELLO, Chiara
CHORA, Joana Rita
MOMBELLI, Giuliana
CALABRESI, Laura
Citação
ATHEROSCLEROSIS, v.383, article ID 117314, 8p, 2023
Resumo
Background and aims: The early diagnosis of familial hypercholesterolaemia is associated with a significant reduction in cardiovascular disease (CVD) risk. While the recent use of statistical and machine learning algorithms has shown promising results in comparison with traditional clinical criteria, when applied to screening of potential FH cases in large cohorts, most studies in this field are developed using a single cohort of patients, which may hamper the application of such algorithms to other populations. In the current study, a logistic regression (LR) based algorithm was developed combining observations from three different national FH cohorts, from Portugal, Brazil and Sweden. Independent samples from these cohorts were then used to test the model, as well as an external dataset from Italy.Methods: The area under the receiver operating characteristics (AUROC) and precision-recall (AUPRC) curves was used to assess the discriminatory ability among the different samples. Comparisons between the LR model and Dutch Lipid Clinic Network (DLCN) clinical criteria were performed by means of McNemar tests, and by the calculation of several operating characteristics.Results: AUROC and AUPRC values were generally higher for all testing sets when compared to the training set. Compared with DLCN criteria, a significantly higher number of correctly classified observations were identified for the Brazilian (p < 0.01), Swedish (p < 0.01), and Italian testing sets (p < 0.01). Higher accuracy (Acc), G mean and F1 score values were also observed for all testing sets.Conclusions: Compared to DLCN criteria, the LR model revealed improved ability to correctly classify observations, and was able to retain a similar number of FH cases, with less false positive retention. Generalization of the LR model was very good across all testing samples, suggesting it can be an effective screening tool if applied to different populations.
Palavras-chave
Familial hypercholesterolaemia, Dutch lipid clinic network criteria, Logistic regression, Validation
Referências
- Abul-Husn NS, 2016, SCIENCE, V354, DOI 10.1126/science.aaf7000
- Akyea RK, 2020, NPJ DIGIT MED, V3, DOI 10.1038/s41746-020-00349-5
- Albuquerque J, 2022, PLOS ONE, V17, DOI 10.1371/journal.pone.0269713
- Albuquerque J, 2022, SCI REP-UK, V12, DOI 10.1038/s41598-022-05063-8
- Austin MA, 2004, AM J EPIDEMIOL, V160, P407, DOI 10.1093/aje/kwh236
- Banda JM, 2019, NPJ DIGIT MED, V2, DOI 10.1038/s41746-019-0101-5
- Beheshti SO, 2020, J AM COLL CARDIOL, V75, P2553, DOI 10.1016/j.jacc.2020.03.057
- Benito-Vicente A, 2015, GENET MED, V17, P980, DOI 10.1038/gim.2015.14
- Benlian P, 2009, J PEDIATR GASTR NUTR, V48, P456, DOI 10.1097/MPG.0b013e3181810b30
- Besseling J, 2017, EUR HEART J, V38, P565, DOI 10.1093/eurheartj/ehw135
- Bouhairie VE, 2015, CARDIOL CLIN, V33, P169, DOI 10.1016/j.ccl.2015.01.001
- Branco P., 2015, ARXIV
- Chan DC, 2018, J CLIN ENDOCR METAB, V103, P1704, DOI 10.1210/jc.2017-02622
- Chawla NV, 2002, J ARTIF INTELL RES, V16, P321, DOI 10.1613/jair.953
- Chora JR, 2022, GENET MED, V24, P293, DOI 10.1016/j.gim.2021.09.012
- Chora JR, 2018, GENET MED, V20, P591, DOI 10.1038/gim.2017.151
- Damgaard D, 2005, ATHEROSCLEROSIS, V180, P155, DOI 10.1016/j.atherosclerosis.2004.12.001
- Defesche JC, 2017, NAT REV DIS PRIMERS, V3, DOI 10.1038/nrdp.2017.93
- Dhiman P, 2014, PLOS ONE, V9, DOI 10.1371/journal.pone.0081998
- Fawcett T, 2006, PATTERN RECOGN LETT, V27, P861, DOI 10.1016/j.patrec.2005.10.010
- Hosmer DW, 2013, WILEY SER PROBAB ST, P1
- Hovingh GK, 2013, EUR HEART J, V34, P962, DOI 10.1093/eurheartj/eht015
- Knowles JW, 2017, JAMA-J AM MED ASSOC, V318, P381, DOI 10.1001/jama.2017.8543
- Maglio C, 2014, J INTERN MED, V276, P396, DOI 10.1111/joim.12263
- Medeiros AM, 2010, ATHEROSCLEROSIS, V212, P553, DOI 10.1016/j.atherosclerosis.2010.07.012
- Najam O, 2015, CARDIOL THER, V4, P25, DOI 10.1007/s40119-015-0037-z
- Niehaus KE, 2015, P DATA MINING MEDICA
- Nordestgaard BG, 2013, EUR HEART J, V34, P3478, DOI 10.1093/eurheartj/eht273
- Patel AP, 2020, JAMA NETW OPEN, V3, DOI 10.1001/jamanetworkopen.2020.3959
- Pina A, 2020, EUR J PREV CARDIOL, V27, P1639, DOI 10.1177/2047487319898951
- Pirillo A, 2017, ATHEROSCLEROSIS SUPP, V29, P17, DOI 10.1016/j.atherosclerosissup.2017.07.002
- Silva PRS, 2017, ATHEROSCLEROSIS, V263, P257, DOI 10.1016/j.atherosclerosis.2017.06.917
- Tharwat A., 2018, APPL COMPUTING INFOR
- Vallejo-Vaz AJ, 2018, ATHEROSCLEROSIS, V277, P289, DOI 10.1016/j.atherosclerosis.2018.06.855
- Weng S, 2019, LANCET PUBLIC HEALTH, V4, pE256, DOI 10.1016/S2468-2667(19)30061-1
- Weng SF, 2015, ATHEROSCLEROSIS, V238, P336, DOI 10.1016/j.atherosclerosis.2014.12.034