An Association Rule Mining Analysis of Lifestyle Behavioral Risk Factors in Cancer Survivors with High Cardiovascular Disease Risk

Abstract

We aimed to assess which lifestyle risk behaviors have the greatest influence on the risk of cardiovascular disease in cancer survivors and which of these behaviors are most prominently clustered in cancer survivors, using logistic regression and association rule mining (ARM). We analyzed a consecutive series of 897 cancer survivors from the Korean National Health and Nutritional Exam Survey (2012–2016). Cardiovascular disease risks were assessed using the atherosclerotic cardiovascular disease score (ASCVDs). We classified participants as being in a low-risk group if their calculated ASCVDs was less than 10% and as being in a high-risk group if their score was 10% or higher. We used association rule mining to analyze patterns of lifestyle risk behaviors by ASCVDs risk group, based upon public health recommendations described in the Alameda 7 health behaviors (current smoking, heavy drinking, physical inactivity, obesity, breakfast skipping, frequent snacking, and suboptimal sleep duration). Forty-two percent of cancer survivors had a high ASCVD. Current smoking (common odds ratio, 11.19; 95% confidence interval, 3.66–34.20, p < 0.001) and obesity (common odds ratio, 2.67; 95% confidence interval, 1.40–5.08, p < 0.001) were significant predictors of high ASCVD in cancer survivors within a multivariate model. In ARM analysis, current smoking and obesity were identified as important lifestyle risk behaviors in cancer survivors. In addition, various lifestyle risk behaviors co-occurred with smoking in male cancer survivors.

Cardiovascular disease in adolescent and young adult cancer survivors: Impact of sociodemographic and modifiable risk factors

“…In the current study, AYA survivors were significantly more likely to be current or former smokers than controls, similar to previous findings that AYA survivors are more likely to smoke than the general population 43 . It has also been shown that AYA survivors with chronic health conditions are more likely to smoke than AYAs without chronic health conditions and that smoking co‐occurs with other modifiable CVD risk factors in cancer survivors 44,45 . Taken together with our findings that AYA survivors who are current or former smokers have close to twice the odds of CVD as those who never smoked, interventions aimed at smoking cessation and prevention are needed in this population.…”

Another Look at Obesity Paradox in Acute Ischemic Stroke: Association Rule Mining

“…Factors such as high aspartate aminotransferase and high serum sodium were identified as significant rules showing a strong association with cognitive decline. In addition, ARM can specify which non-hierarchical phenotype has been achieved by effective clustering of multiple diseases [40][41][42]. However, ARM usually deals with Boolean data, so it is difficult to analyze associations among the numerical data.…”

SDFP-Growth Algorithm as a Novelty of Association Rule Mining Optimization

“…Initially, association rule mining was used in market basket analysis (MBA) techniques, which functioned to analyze consumer buying patterns in a supermarket [28]; for example, if a consumer buys bread, he usually buys milk. Currently, MBA is used in other sectors, such as the health sector [29][30] and socio-economics [31].…”