Application of Machine Learning Methods to Analyze Occurrence and Clinical Features of Ascending Aortic Dilatation in Patients with and without Bicuspid Aortic Valve

Irtyuga, Olga; Kopanitsa, Georgy; Kostareva, Anna; Metsker, Oleg G.; Uspensky, Vladimir; Mikhail, Gordeev; Faggian, Giuseppe; Sefieva, Giunai; Derevitskii, Ilia V.; Malashicheva, Anna; Shlyakhto, Evgeny

doi:10.3390/jpm12050794

Cited by 3 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used a machine learning approach with Random Forest to determine the five most significant features for patients with AS. Two of them, namely older age and hypertension, are similar to the AscAD population in our previous publication [1]. The presence of BAV and dyslipidemia in AS patients was more significant than in AscAD patients.…”

Section: Features Importancesupporting

confidence: 74%

“…This paper is an extension of the paper presented in the pHealth 2021 Conference [1]. AS is the most common acquired valvular heart disease [2][3][4][5], and the prevalence of moderate or severe valvular disease increases with age, which poses a burden on healthcare systems in developed countries [2][3][4].…”

Section: Introductionmentioning

confidence: 90%

“…The database encompassed 145,454 echocardiograms from both outpatients and hospitalized patients who received observation and treatment at the center between January 2010 and November 2018. It is important to note that the patient cohort used in this analysis is the same as the one utilized in our previous study [1]. Please see Table 1.…”

Section: Study Cohortmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Prevalence and Clinical Features of Aortic Stenosis in Patients with and without Bicuspid Aortic Valve Using Machine Learning Methods

Irtyuga,

Babakekhyan,

Kostareva

et al. 2023

JPM

Self Cite

View full text Add to dashboard Cite

Aortic stenosis (AS) is the most commonly diagnosed valvular heart disease, and its prevalence increases with the aging of the general population. However, AS is often diagnosed at a severe stage, necessitating surgical treatment, due to its long asymptomatic period. The objective of this study was to analyze the frequency of AS in a population of cardiovascular patients using echocardiography (ECHO) and to identify clinical factors and features associated with these patient groups. We utilized machine learning methods to analyze 84,851 echocardiograms performed between 2010 and 2018 at the National Medical Research Center named after V.A. Almazov. The primary indications for ECHO were coronary artery disease (CAD) and hypertension (HP), accounting for 33.5% and 14.2% of the cases, respectively. The frequency of AS was found to be 13.26% among the patients (n = 11,252). Within our study, 1544 patients had a bicuspid aortic valve (BAV), while 83,316 patients had a tricuspid aortic valve (TAV). BAV patients were observed to be younger compared to TAV patients. AS was more prevalent in the BAV group (59%) compared to the TAV group (12%), with a p-value of <0.0001. By employing a machine learning algorithm, we randomly identified significant features present in AS patients, including age, hypertension (HP), aortic regurgitation (AR), ascending aortic dilatation (AscAD), and BAV. These findings could serve as additional indications for earlier observation and more frequent ECHO in specific patient groups for the earlier detection of developing AS.

show abstract

Section: Features Importancesupporting

confidence: 74%

Section: Introductionmentioning

confidence: 90%

See 1 more Smart Citation

Analysis of Prevalence and Clinical Features of Aortic Stenosis in Patients with and without Bicuspid Aortic Valve Using Machine Learning Methods

Irtyuga,

Babakekhyan,

Kostareva

et al. 2023

JPM

Self Cite

View full text Add to dashboard Cite

show abstract

Machine Learning Approaches for Segmentation of Cardiovascular Neurocristopathy Related Images

Iqbal,

Soliman,

Sultan

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Cardiovascular neurocristopathy is associated with abnormal migration and development of neural crest cells, impacting the neural and the human cardiovascular system and leading to diseases such as cardiomyopathy, aortic disease, and aortic valve dysfunction. With advancements in biomedical imaging tools, efforts are made to understand the underlying causes of cardiovascular neurocristopathy and develop new diagnostic methods, especially using machine learning or specifically its sub-branch deep learning models. This article provides a systematic survey of the literature related to machine/deep learningbased segmentation of the diseases mentioned above in computer tomography (CT), magnetic resonance imaging (MRI), X-rays, and echocardiogram (Echos) images. The review identified gaps and provides future directions, such as the need for better interpretable and explainable AI models, addressing the lack of publicly available datasets, standardizing the result reporting procedure for better repeatability of the result, and the development of standard performance measurement metrics. The general conclusion suggests that there is a need for multimodalities, multimodel, high-quality data sets, and open-source disease-specific dataspaces that will help develop trustworthy deep learning models that could be implemented in imaging devices/tools and provide medical-grade segmented outputs that will augment and speed up clinician decision making.

show abstract

Pathomorphological features of complications inpatients with bicuspid aortic valve

Pugina,

Gareev,

Korzhova

et al. 2023

jour

Self Cite

View full text Add to dashboard Cite

Purpose: to evaluate the features of the course of complications in patients with BAV based on the results of a pathomorphological study.Material and methods: a retrospective analysis of a register of 328 patients with AS and dilation of the ascending aorta (DAA), based on histological studies performed in 2010–2022 was carried out. 209 patients were diagnosed with BAV as a result of histological examination, and 119 patients were diagnosed with tricuspid aortic valve (TAV). The type of BAV was analyzed in 139 operated patients based on the results of the analysis of surgical protocols.Results: according to the obtained results, the first type with fusion of the right and left coronary cusps prevailed among patients with BAV (78%), the smallest number of patients with BAV was with fusion of the right coronary and non-coronary cusps of the aortic valve (4%), while fusion of the left coronary with the non-coronary cusps of the aortic valve (AV) and patients with "true" BAV occurred in each case in 9% of patients. The formation of AS (75.6%), DAA (68.4%), and the combination of AS+DAA (81%) was more observed in the group of patients with the first type of BAV. According to the results of histology of the AV, there were no significant differences depending on the morphology of the valve. In particular, according to the results of AV histology, the frequency of calcification did not differ in groups of patients with BAV and TAV. Fibrosis with erasing of the layered histoarchitectonics of the AV of varying severity was detected in every second patient, regardless of the presence of congenital heart disease (CHD). According to the results of aortic histology, hemodynamic aneurysm in patients with BAV was much more common than in patients with TAV (p=0.0027). In addition, it was verified that in 39 patients out of 40 without pathomorphological changes in the aortic wall, aortic stenosis appeared in the diagnosis, of which 80% of patients had CHD: BAV. It was verified that 39 out of 40 patients without pathomorphological changes in the aortic wall had aortic stenosis in the diagnosis. Moreover, in 80% of patients, the main cause of aortic dilatation was identified as BAV.Conclusions: the results of this study demonstrated that in the vast majority of cases, aortic dilatation and aortic stenosis are formed during fusion of the right and left coronary cusps. The absence of morphological changes in the aortic wall in almost every third patient with DAA and BAV, confirms the genetic contribution to the formation of aortic dilatation in this category of patients and requires further study.

show abstract

Application of Machine Learning Methods to Analyze Occurrence and Clinical Features of Ascending Aortic Dilatation in Patients with and without Bicuspid Aortic Valve

Cited by 3 publications

References 45 publications

Analysis of Prevalence and Clinical Features of Aortic Stenosis in Patients with and without Bicuspid Aortic Valve Using Machine Learning Methods

Analysis of Prevalence and Clinical Features of Aortic Stenosis in Patients with and without Bicuspid Aortic Valve Using Machine Learning Methods

Machine Learning Approaches for Segmentation of Cardiovascular Neurocristopathy Related Images

Pathomorphological features of complications inpatients with bicuspid aortic valve

Contact Info

Product

Resources

About