Cardiovascular risk prediction - a systems medicine approach

E-print/Working paper (2023)

Background Guidelines for the prevention of cardiovascular disease (CVD) have recommended the assessment of the total CVD risk by risk scores. Current risk algorithms are low in sensitivity and ... [more ▼]

Background Guidelines for the prevention of cardiovascular disease (CVD) have recommended the assessment of the total CVD risk by risk scores. Current risk algorithms are low in sensitivity and specificity and they have not incorporated emerging risk markers for CVD. We suggest that CVD risk assessment can be still improved. We have developed a long-term risk prediction model of cardiovascular mortality in patients with stable coronary artery disease (CAD) based on newly available machine learning and on an extended dataset of new biomarkers.Methods 2953 participants of the Ludwigshafen Risk and Cardiovascular Health (LURIC) study were included. 184 laboratory and 21 demographic markers were ranked according to their contribution to risk of cardiovascular (CV) mortality using different data mining approaches. A self-learning bioinformatics workflow, including seven different machine learning algorithms, was developed for CV risk prediction. The study population was stratified into patients with and without significant CAD. Thereby, significant CAD was defined as a lumen narrowing of 50 or more in at least one of the coronary segments or a history of definite myocardial infarction. The machine learning models in both subpopulations were compared with established CV risk assessment tools.Results After a follow-up of 10 years, 603 (20.4%) patients died of cardiovascular causes. 95% patients without CAD deceased within ten years and 247 (13.2 %) patients with CAD within 5 years. Overall and in patients without CAD, NT-proBNP (N-terminal pro B-type natriuretic peptide), TnT (Troponin T), estimated cystatin c based GFR (glomerular filtration rate) and age were the highest ranked predictors, while in patients with CAD, NT-proBNP, GFR, CT-proAVP (C-terminal pro arginine vasopressin) and TNT were highest predictive. In the comparison with the FRS, PROCAM and ESC risk scores, the machine learning workflow produced more accurate and robust CV mortality prediction in patients without CAD. Equivalent CV risk prediction was obtained in the CAD subpopulation in comparison with the Marschner risk score. Overall, the existing algorithms in general tend to assign more patients into the medium risk groups, while the machine learning algorithms tend to have a clearer risk/no risk assignment. The framework is available upon request.Conclusion We have developed a fully automated and self-validating computational framework of machine learning techniques using an extensive database of clinical, routinely and non-routinely measured laboratory data. Our framework predicts long-term CV mortality at least as accurate as existing CVD risk scores. A combination of four highly ranked biomarkers and the random forest approach showed the best predictive results. Moreover, a dynamic computational model has several advantages over static CVD risk prediction tools: it is freeware, transparent, variable, transferable and expandable to any population, types of events and time frames. [less ▲]

An efficient machine learning-based approach for screening individuals at risk of hereditary haemochromatosis.

in Scientific reports (2020), 10(1), 20613

Hereditary haemochromatosis (HH) is an autosomal recessive disease, where HFE C282Y homozygosity accounts for 80-85% of clinical cases among the Caucasian population. HH is characterised by the ... [more ▼]

Hereditary haemochromatosis (HH) is an autosomal recessive disease, where HFE C282Y homozygosity accounts for 80-85% of clinical cases among the Caucasian population. HH is characterised by the accumulation of iron, which, if untreated, can lead to the development of liver cirrhosis and liver cancer. Since iron overload is preventable and treatable if diagnosed early, high-risk individuals can be identified through effective screening employing artificial intelligence-based approaches. However, such tools expose novel challenges associated with the handling and integration of large heterogeneous datasets. We have developed an efficient computational model to screen individuals for HH using the family study data of the Hemochromatosis and Iron Overload Screening (HEIRS) cohort. This dataset, consisting of 254 cases and 701 controls, contains variables extracted from questionnaires and laboratory blood tests. The final model was trained on an extreme gradient boosting classifier using the most relevant risk factors: HFE C282Y homozygosity, age, mean corpuscular volume, iron level, serum ferritin level, transferrin saturation, and unsaturated iron-binding capacity. Hyperparameter optimisation was carried out with multiple runs, resulting in 0.94 ± 0.02 area under the receiving operating characteristic curve (AUCROC) for tenfold stratified cross-validation, demonstrating its outperformance when compared to the iron overload screening (IRON) tool. [less ▲]

An Efficient Machine Learning Method to Solve Imbalanced Data in Metabolic Disease Prediction

in Cecchini, Vania Filipa (Ed.) An Efficient Machine Learning Method to Solve Imbalanced Data in Metabolic Disease Prediction (2019)

Stratifying cancer patients based on multiple kernel learning and dimensionality reduction

in Giang, Thanh Trung; Nguyen, Thanh-Phuong; Tran (Eds.) 9th International Conference on Knowledge and Systems Engineering (KSE) (2017)

Systems biology integration of proteomic data in rodent models of depression reveals involvement of the immune response and glutamatergic signalling

in Proteomics. Clinical Applications (2016)

Purpose The pathophysiological basis of major depression is incompletely understood. Recently, numerous proteomic studies have been performed in rodent models of depression to investigate the molecular ... [more ▼]

Purpose The pathophysiological basis of major depression is incompletely understood. Recently, numerous proteomic studies have been performed in rodent models of depression to investigate the molecular underpinnings of depressive-like behaviours with an unbiased approach. The objective of the study was to integrate the results of these proteomic studies in depression models to shed light on the most relevant molecular pathways involved in the disease. Experimental design Network analysis was performed integrating pre-existing proteomic data from rodent models of depression. The IntAct mouse and the HRPD were used as reference protein-protein interaction databases. The functionality analyses of the networks were then performed by testing over-represented GO biological process terms and pathways. Results Functional enrichment analyses of the networks revealed an association with molecular processes related to depression in humans, such as those involved in the immune response. Pathways impacted by clinically effective antidepressants were modulated, including glutamatergic signalling and neurotrophic responses. Moreover, dysregulations of proteins regulating energy metabolism and circadian rhythms were implicated. The comparison with protein pathways modulated in depressive patients revealed significant overlapping. Conclusions and clinical relevance This systems biology study supports the notion that animal models could contribute to the research into the biology and therapeutics of depression. [less ▲]

Cell type-selective disease-association of genes under high regulatory load

in Nucleic Acids Research (2015), 43(18), 8839-8855

We previously showed that disease-linked metabolic genes are often under combinatorial regulation. Using the genome-wide ChIP-Seq binding profiles for 93 transcription factors in nine different cell lines ... [more ▼]

We previously showed that disease-linked metabolic genes are often under combinatorial regulation. Using the genome-wide ChIP-Seq binding profiles for 93 transcription factors in nine different cell lines, we show that genes under high regulatory load are significantly enriched for disease-association across cell types. We find that transcription factor load correlates with the enhancer load of the genes and thereby allows the identification of genes under high regulatory load by epigenomic mapping of active enhancers. Identification of the high enhancer load genes across 139 samples from 96 different cell and tissue types reveals a consistent enrichment for disease-associated genes in a cell type-selective manner. The underlying genes are not limited to super-enhancer genes and show several types of disease-association evidence beyond genetic variation (such as biomarkers). Interestingly, the high regulatory load genes are involved in more KEGG pathways than expected by chance, exhibit increased betweenness centrality in the interaction network of liver disease genes, and carry longer 3'UTRs with more microRNA (miRNA) binding sites than genes on average, suggesting a role as hubs integrating signals within regulatory networks. In summary, epigenetic mapping of active enhancers presents a promising and unbiased approach for identification of novel disease genes in a cell type-selective manner. [less ▲]

A systems biology investigation of neurodegenerative dementia reveals a pivotal role of autophagy

in BMC Systems Biology (2014), 8(1), 65

Inference of Autism-Related Genes by Integrating Protein-Protein Interactions and miRNA-Target Interactions

in Knowledge and Systems Engineering (2014)

Detecting disease genes based on semi-supervised learning and protein--protein interaction networks

in Artificial Intelligence in Medicine (2012), 54(1), 63--71

Objective Predicting or prioritizing the human genes that cause disease, or “disease genes”, is one of the emerging tasks in biomedicine informatics. Research on network-based approach to this problem is ... [more ▼]

Objective Predicting or prioritizing the human genes that cause disease, or “disease genes”, is one of the emerging tasks in biomedicine informatics. Research on network-based approach to this problem is carried out upon the key assumption of “the network-neighbour of a disease gene is likely to cause the same or a similar disease”, and mostly employs data regarding well-known disease genes, using supervised learning methods. This work aims to find an effective method to exploit the disease gene neighbourhood and the integration of several useful omics data sources, which potentially enhance disease gene predictions. Methods We have presented a novel method to effectively predict disease genes by exploiting, in the semi-supervised learning (SSL) scheme, data regarding both disease genes and disease gene neighbours via protein–protein interaction network. Multiple proteomic and genomic data were integrated from six biological databases, including Universal Protein Resource, Interologous Interaction Database, Reactome, Gene Ontology, Pfam, and InterDom, and a gene expression dataset. Results By employing a 10 times stratified 10-fold cross validation, the SSL method performs better than the k-nearest neighbour method and the support vector machines method in terms of sensitivity of 85%, specificity of 79%, precision of 81%, accuracy of 82%, and a balanced F-function of 83%. The other comparative experimental evaluations demonstrate advantages of the proposed method given a small amount of labeled data with accuracy of 78%. We have applied the proposed method to detect 572 putative disease genes, which are biologically validated by some indirect ways. Conclusion Semi-supervised learning improved ability to study disease genes, especially a specific disease when the known disease genes (as labeled data) are very often limited. In addition to the computational improvement, the analysis of predicted disease proteins indicates that the findings are beneficial in deciphering the pathogenic mechanisms. [less ▲]

Mining multiple biological data for reconstructing signal transduction networks

in Data Mining: Foundations and Intelligent Paradigms (2012)