1. |
- Albuquerque, João, et al.
(author)
-
Generation and validation of a classification model to diagnose familial hypercholesterolaemia in adults.
- 2023
-
In: Atherosclerosis. - 1879-1484. ; 383
-
Journal article (peer-reviewed)abstract
- 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.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.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.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.
|
|
2. |
|
|
3. |
- Pavanello, Chiara, et al.
(author)
-
Individuals with familial hypercholesterolemia and cardiovascular events have higher circulating Lp(a) levels.
- 2019
-
In: Journal of clinical lipidology. - : Elsevier BV. - 1933-2874. ; 13:5
-
Journal article (peer-reviewed)abstract
- Cardiovascular disease (CVD) is a major cause of mortality and morbidity. Increased low-density lipoprotein cholesterol (LDL-C) level is its major risk factor. Familial hypercholesterolemia (FH) is a genetic disorder characterized by elevated LDL-C since birth and subsequent premature CVD. There is a heterogeneity in the CVD onset in patients with FH. This is potentially due to the presence of other independent risk factors. Lipoprotein(a) [Lp(a)] is an LDL-like particle and represents a strong risk factor for CVD.Our objective was to understand the contribution of Lp(a) in the susceptibility to CVD in individuals with genetic diagnosis of FH.We measured Lp(a) levels in 2 independent and well-characterized genetic-FH cohorts: the FH-Gothenburg cohort (n=190) and the FH-CEGP Milan cohort (n=160). The genetic diagnosis was performed by targeted next-generation sequencing (FH-Gothenburg and part of the FH-CEGP Milan cohort), or by Sanger sequencing.We show that among individuals with genetic diagnosis of FH, those with previous CVD had higher Lp(a) levels. In addition, analyzing the response to the lipid-lowering therapies, we have also shown that statins had the same LDL-C-lowering effect irrespective of the type of FH-causative mutation. However, when we examined the lipid-lowering effect of proprotein convertase subtilisin/kexin type 9 inhibition by antibodies, we observed a trend in a better reduction of the LDL-C level in carriers of nonsense mutations.In conclusion, our results suggest that Lp(a) contributes to CVD onset in individuals with genetic diagnosis of FH. Our finding supports the importance to identify an efficacious therapy to lower Lp(a) in patients with FH to prevent CVD onset or recurrence.
|
|
4. |
- Pedrelli, Matteo, et al.
(author)
-
Vasculoprotective Properties of Plasma Lipoproteins from Brown Bears (Ursus arctos)
- 2021
-
In: Journal of Lipid Research. - : American Society for Biochemistry and Molecular Biology. - 0022-2275 .- 1539-7262. ; 62
-
Journal article (peer-reviewed)abstract
- Plasma cholesterol and triglyceride levels are twice as high in hibernating brown bears (Ursus arctos) than healthy humans. Yet, bears display no signs of early-stage atherosclerosis development when adult. To explore this apparent paradox, we analysed plasma lipoproteins from the same ten bears in winter (hibernation) and in summer using size exclusion chromatography, ultracentrifugation and electrophoresis. LDL cholesterol binding to arterial proteoglycans, and plasma cholesterol efflux capacity were also evaluated. The data collected and analysed from bears were also compared with those from healthy humans. In bears the cholesterol esters, unesterified cholesterol, triglyceride and phospholipid content of VLDL and LDL were higher in winter than in summer. The percentage lipid composition of LDL differed between bears and humans, but did not change seasonally in bears. Bear LDL was larger, richer in triglycerides, showed pre-beta electrophoretic mobility and had 5-10 times lower binding to arterial proteoglycans than human LDL. Finally, plasma cholesterol efflux capacity was higher in bears than in humans, especially the HDL fraction when mediated by ABCA1. These results suggest that in brown bears the absence of early atherogenesis is likely associated with a lower affinity of LDL cholesterol for arterial proteoglycans and an elevated cholesterol efflux capacity of bear plasma.
|
|
5. |
- Pedrelli, Matteo, et al.
(author)
-
Vasculoprotective properties of plasma lipoproteins from brown bears (Ursus arctos)
- 2021
-
In: Journal of Lipid Research. - : Elsevier. - 0022-2275 .- 1539-7262. ; 62
-
Journal article (peer-reviewed)abstract
- Plasma cholesterol and triglyceride (TG) levels are twice as high in hibernating brown bears (Ursus arctos) than healthy humans. Yet, bears display no signs of early stage atherosclerosis development when adult. To explore this apparent paradox, we analyzed plasma lipoproteins from the same 10 bears in winter (hibernation) and summer using size exclusion chromatography, ultracentrifugation, and electrophoresis. LDL binding to arterial proteoglycans (PGs) and plasma cholesterol efflux capacity (CEC) were also evaluated. The data collected and analyzed from bears were also compared with those from healthy humans. In bears, the cholesterol ester, unesterified cholesterol, TG, and phospholipid contents of VLDL and LDL were higher in winter than in summer. The percentage lipid composition of LDL differed between bears and humans but did not change seasonally in bears. Bear LDL was larger, richer in TGs, showed prebeta electrophoretic mobility, and had 5-10 times lower binding to arterial PGs than human LDL. Finally, plasma CEC was higher in bears than in humans, especially the HDL fraction when mediated by ABCA1. These results suggest that in brown bears the absence of early atherogenesis is likely associated with a lower affinity of LDL for arterial PGs and an elevated CEC of bear plasma.
|
|
6. |
- Pina, Ana, et al.
(author)
-
Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning.
- 2020
-
In: European journal of preventive cardiology. - : Oxford University Press (OUP). - 2047-4881 .- 2047-4873. ; 27:15, s. 1639-1646
-
Journal article (peer-reviewed)abstract
- Familial hypercholesterolemia (FH) is the most common genetic disorder of lipid metabolism. The gold standard for FH diagnosis is genetic testing, available, however, only in selected university hospitals. Clinical scores - for example, the Dutch Lipid Score - are often employed as alternative, more accessible, albeit less accurate FH diagnostic tools. The aim of this study is to obtain a more reliable approach to FH diagnosis by a "virtual" genetic test using machine-learning approaches.We used three machine-learning algorithms (a classification tree (CT), a gradient boosting machine (GBM), a neural network (NN)) to predict the presence of FH-causative genetic mutations in two independent FH cohorts: the FH Gothenburg cohort (split into training data (N=174) and internal test (N=74)) and the FH-CEGP Milan cohort (external test, N=364). By evaluating their area under the receiver operating characteristic (AUROC) curves, we found that the three machine-learning algorithms performed better (AUROC 0.79 (CT), 0.83 (GBM), and 0.83 (NN) on the Gothenburg cohort, and 0.70 (CT), 0.78 (GBM), and 0.76 (NN) on the Milan cohort) than the clinical Dutch Lipid Score (AUROC 0.68 and 0.64 on the Gothenburg and Milan cohorts, respectively) in predicting carriers of FH-causative mutations.In the diagnosis of FH-causative genetic mutations, all three machine-learning approaches we have tested outperform the Dutch Lipid Score, which is the clinical standard. We expect these machine-learning algorithms to provide the tools to implement a virtual genetic test of FH. These tools might prove particularly important for lipid clinics without access to genetic testing.
|
|