Dataset Information

Biological knowledge-slanted random forest approach for the classification of calcified aortic valve stenosis.

ABSTRACT:

Background

Calcific aortic valve stenosis (CAVS) is a fatal disease and there is no pharmacological treatment to prevent the progression of CAVS. This study aims to identify genes potentially implicated with CAVS in patients with congenital bicuspid aortic valve (BAV) and tricuspid aortic valve (TAV) in comparison with patients having normal valves, using a knowledge-slanted random forest (RF).

Results

This study implemented a knowledge-slanted random forest (RF) using information extracted from a protein-protein interactions network to rank genes in order to modify their selection probability to draw the candidate split-variables. A total of 15,191 genes were assessed in 19 valves with CAVS (BAV, n = 10; TAV, n = 9) and 8 normal valves. The performance of the model was evaluated using accuracy, sensitivity, and specificity to discriminate cases with CAVS. A comparison with conventional RF was also performed. The performance of this proposed approach reported improved accuracy in comparison with conventional RF to classify cases separately with BAV and TAV (Slanted RF: 59.3% versus 40.7%). When patients with BAV and TAV were grouped against patients with normal valves, the addition of prior biological information was not relevant with an accuracy of 92.6%.

Conclusion

The knowledge-slanted RF approach reflected prior biological knowledge, leading to better precision in distinguishing between cases with BAV, TAV, and normal valves. The results of this study suggest that the integration of biological knowledge can be useful during difficult classification tasks.

SUBMITTER: Cantor E

PROVIDER: S-EPMC8305490 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundAortic valve stenosis is the most common type of valvular heart disease in the USA and Europe. Aortic valve stenosis is considered similar to atherosclerotic disease. Some studies have evaluated statins for aortic valve stenosis.ObjectivesTo evaluate the effectiveness and safety of statins in aortic valve stenosis.Search methodsWe searched the Cochrane Central Register of Controlled Trials (CENTRAL), MEDLINE, Embase, LILACS - IBECS, Web of Science and CINAHL Plus. These databases were searched from their inception to 24 November 2015. We also searched trials in registers for ongoing trials. We used no language restrictions.Selection criteriaRandomised controlled clinical trials (RCTs) comparing statins alone or in association with other systemic drugs to reduce cholesterol levels versus placebo or usual care.Data collection and analysisPrimary outcomes were severity of aortic valve stenosis (evaluated by echocardiographic criteria: mean pressure gradient, valve area and aortic jet velocity), freedom from valve replacement and death from cardiovascular cause. Secondary outcomes were hospitalisation for any reason, overall mortality, adverse events and patient quality of life.Two review authors independently selected trials for inclusion, extracted data and assessed the risk of bias. The GRADE methodology was employed to assess the quality of result findings and the GRADE profiler (GRADEPRO) was used to import data from Review Manager 5.3 to create a 'Summary of findings' table.Main resultsWe included four RCTs with 2360 participants comparing statins (1185 participants) with placebo (1175 participants). We found low-quality evidence for our primary outcome of severity of aortic valve stenosis, evaluated by mean pressure gradient (mean difference (MD) -0.54, 95% confidence interval (CI) -1.88 to 0.80; participants = 1935; studies = 2), valve area (MD -0.07, 95% CI -0.28 to 0.14; participants = 127; studies = 2), and aortic jet velocity (MD -0.06, 95% CI -0.26 to 0.14; participants = 155; study = 1). Moderate-quality evidence showed no effect on freedom from valve replacement with statins (risk ratio (RR) 0.93, 95% CI 0.81 to 1.06; participants = 2360; studies = 4), and no effect on muscle pain as an adverse event (RR 0.91, 95% CI 0.75 to 1.09; participants = 2204; studies = 3; moderate-quality evidence). Low- and very low-quality evidence showed uncertainty around the effect of statins on death from cardiovascular cause (RR 0.80, 95% CI 0.56 to 1.15; participants = 2297; studies = 3; low-quality evidence) and hospitalisation for any reason (RR 0.84, 95% CI 0.39 to 1.84; participants = 155; study = 1; very low-quality evidence). None of the four included studies reported on overall mortality and patient quality of life.Authors' conclusionsResult findings showed uncertainty surrounding the effect of statins for aortic valve stenosis.The quality of evidence from the reported outcomes ranged from moderate to very low. These results give support to European and USA guidelines (2012 and 2014, respectively) that so far there is no clinical treatment option for aortic valve stenosis.