Phenotypes Determined by Cluster Analysis in Moderate to Severe Bronchial Asthma

Youroukova, Vania; Dimitrova, Denitsa; Valerieva, Anna; Lesichkova, Spaska; Velikova, Tsvetelina; Ivanova‐Todorova, Ekaterina; Tumangelova-Yuzeir, Kalina

doi:10.1515/folmed-2017-0031

Cited by 9 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All baseline parameters in the SPRINT trial clinically relevant for hypertension phenotypes were selected. Cluster analysis by an approach similar to that in a previous report 8 was performed on values centred to a mean value of 0 and a standard deviation (SD) of 1. A two-step clustering algorithm was carried out, in which the first step estimates the optimal number of clusters on the basis of silhouette width and the second step does hierarchical clustering for two to 15 clusters using log-likelihood as a distance measure and Schwarz’s Bayesian criterion for clustering.…”

Section: Methodsmentioning

confidence: 99%

Phenomapping of subgroups in hypertensive patients using unsupervised data-driven cluster analysis: An exploratory study of the SPRINT trial

Yang

Nie²,

Liao

et al. 2019

Eur J Prev Cardiolog

View full text Add to dashboard Cite

Background Hypertensive patients are highly heterogeneous in cardiovascular prognosis and treatment responses. A better classification system with phenomapping of clinical features would be of greater value to identify patients at higher risk of developing cardiovascular outcomes and direct individual decision-making for antihypertensive treatment. Methods An unsupervised, data-driven cluster analysis was performed for all baseline variables related to cardiovascular outcomes and treatment responses in subjects from the Systolic Blood Pressure Intervention Trial (SPRINT), in order to identify distinct subgroups with maximal within-group similarities and between-group differences. Cox regression was used to calculate hazard ratios (HRs) with 95% confidence intervals (CIs) for cardiovascular outcomes and compare the effect of intensive antihypertensive treatment in different clusters. Results Four replicable clusters of patients were identified: cluster 1 (index hypertensives); cluster 2 (chronic kidney disease hypertensives); cluster 3 (obese hypertensives) and cluster 4 (extra risky hypertensives). In terms of prognosis, individuals in cluster 4 had the highest risk of developing primary outcomes. In terms of treatment responses, intensive antihypertensive treatment was shown to be beneficial only in cluster 4 (HR 0.73, 95% CI 0.55–0.98) and cluster 1 (HR 0.54, 95% CI 0.37–0.79) and was associated with an increased risk of severe adverse effects in cluster 2 (HR 1.18, 95% CI 1.05–1.32). Conclusion Using a data-driven approach, SPRINT subjects can be stratified into four phenotypically distinct subgroups with different profiles on cardiovascular prognoses and responses to intensive antihypertensive treatment. Of note, these results should be taken as hypothesis generating that warrant further validation in future prospective studies.

show abstract

Section: Methodsmentioning

confidence: 99%

Phenomapping of subgroups in hypertensive patients using unsupervised data-driven cluster analysis: An exploratory study of the SPRINT trial

Yang

Nie²,

Liao

et al. 2019

Eur J Prev Cardiolog

View full text Add to dashboard Cite

show abstract

“…In the field of human medical science, studies using cluster analysis for disease classification and diagnosis have been reported (Li, Yang, Li, Wang, & Guan, 2015; Youroukova et al., 2017). In the field of animal science, cluster analysis was used for the classification of genotypes of bovine populations (Fraga et al., 2016) and the classification of sperm motility of swine (Ibănescu, Leiding, & Bollwein, 2018).…”

Section: Discussionmentioning

confidence: 99%

Cluster analysis to evaluate disease risk in periparturient dairy cattle

Ishikawa

Ikuta

Obara³

et al. 2020

Animal Science Journal

View full text Add to dashboard Cite

Since periparturient diseases reduce milk production and reproductive performance (Deluyker, Gay, Weaver, & Azari, 1991; Venjakob, Pieper, Heuwieser, & Borchardt, 2018) leading to major economic loss (Gohary et al., 2016), minimizing their occurrence is important. Consequently, prevention and prediction of periparturient diseases are of immense value to the dairy industry. Although several preventive measures are available for periparturient diseases (McArt, Nydam, & Oetzel, 2012; Moore et al., 2000), the ability to evaluate the onset risk for individual animals will allow implementation of more thorough management of high-risk cattle. The body condition score (BCS) (Ferguson, Galligan, & Thomsen, 1994) is one measure that is used to evaluate disease risk in cattle. High BCS (over-conditioned) at calving is known to exacerbate post-partum negative energy balance (Allbrahim et al., 2010). Many studies have also reported a relationship between blood parameters and the risk of periparturient diseases

show abstract

“…Programming and modelling the data with R language are done according to the data characteristics of Chinese medicine medication rules, within which the core herbs were clustered by Hierarchical clustering algorithm. For example, Vania M. Youroukova et al analyzed the phenotype of severe bronchial asthma by using cluster analysis and obtained four clusters that provided reference for clinical treatment [9]. The Apriori algorithm in R language data mining software is used to analyze the association rules of core herbs, which is similar to Mateen Shaikh's applying association rule replacement test to test the relationship between genotype and phenotype, and deduced the genotype of candidate population [10].…”

Section: Methodsmentioning

confidence: 99%

A Data Mining-Based Analysis of Medication Rules in Treating Bone Marrow Suppression by Kidney-Tonifying Method

You

Huang

et al. 2019

Evidence-Based Complementary and Alternative Medicine

View full text Add to dashboard Cite

Objective. To investigate the rule of kidney-tonifying method in Chinese medicine for the treatment of bone marrow suppression (BMS), in order to provide evidence and references for the clinical application of herbs and formulae. Design. Collecting and sorting the information about the treatment of BMS related to kidney-tonifying (Bushen) method in Chinese medicine literatures on databases including Chinese National Knowledge Infrastructure (CNKI), and Chinese Biomedical Literature Database (CBM), establishing a database of BMS treating formulae after radiotherapy and chemotherapy with traditional Chinese medicine (TCM) kidney-tonifying method, and finally applying the relevant theories and techniques of data mining to analyze the medication rules of it. Results. A total of 239 formulae and 202 herbs were included in this database, in which the herbs occurred 2,602 times in general. The high frequency herbs included Astragali Radix (Huangqi), Atractylodis Macrocephalae Rhizoma (Baizhu), and Ligustri Lucidi Fructus (Nvzhenzi). The main herb categories were deficiency-tonifying herbs, blood-activating herbs, dampness-draining diuretic herbs, heat-clearing herbs, and digestant herbs. Deficiency-tonifying herbs accounted for 64.60% of the total number. A total of 8 clustering formulae are summarized according to cluster analysis and 26 herb suits association rules are identified by Apriori algorithm. Conclusion. The treatment of BMS is mainly based on the method of invigorating the spleen and tonifying the kidney and liver to strengthen healthy qi, supplementing with blood-activating herbs, and dampness-draining diuretic herbs to eliminate pathogenic factors.

show abstract

Phenotypes Determined by Cluster Analysis in Moderate to Severe Bronchial Asthma

Cited by 9 publications

References 23 publications

Phenomapping of subgroups in hypertensive patients using unsupervised data-driven cluster analysis: An exploratory study of the SPRINT trial

Phenomapping of subgroups in hypertensive patients using unsupervised data-driven cluster analysis: An exploratory study of the SPRINT trial

Cluster analysis to evaluate disease risk in periparturient dairy cattle

A Data Mining-Based Analysis of Medication Rules in Treating Bone Marrow Suppression by Kidney-Tonifying Method

Contact Info

Product

Resources

About