Dataset Information

Classification-based data mining for identification of risk patterns associated with hypertension in Middle Eastern population: A 12-year longitudinal study.

ABSTRACT: Hypertension is a critical public health concern worldwide. Identification of risk factors using traditional multivariable models has been a field of active research. The present study was undertaken to identify risk patterns associated with hypertension incidence using data mining methods in a cohort of Iranian adult population.Data on 6205 participants (44% men) age > 20 years, free from hypertension at baseline with no history of cardiovascular disease, were used to develop a series of prediction models by 3 types of decision tree (DT) algorithms. The performances of all classifiers were evaluated on the testing data set.The Quick Unbiased Efficient Statistical Tree algorithm among men and women and Classification and Regression Tree among the total population had the best performance. The C-statistic and sensitivity for the prediction models were (0.70 and 71%) in men, (0.79 and 71%) in women, and (0.78 and 72%) in total population, respectively. In DT models, systolic blood pressure (SBP), diastolic blood pressure, age, and waist circumference significantly contributed to the risk of incident hypertension in both genders and total population, wrist circumference and 2-h postchallenge plasma glucose among women and fasting plasma glucose among men. In men, the highest hypertension risk was seen in those with SBP > 115?mm Hg and age > 30 years. In women those with SBP > 114?mm Hg and age > 33 years had the highest risk for hypertension. For the total population, higher risk was observed in those with SBP > 114?mm Hg and age > 38 years.Our study emphasizes the utility of DTs for prediction of hypertension and exploring interaction between predictors. DT models used the easily available variables to identify homogeneous subgroups with different risk pattern for the hypertension.

SUBMITTER: Ramezankhani A

PROVIDER: S-EPMC5008529 | biostudies-literature | 2016 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Classification-based data mining for identification of risk patterns associated with hypertension in Middle Eastern population: A 12-year longitudinal study.

Ramezankhani Azra A Kabir Ali A Pournik Omid O Azizi Fereidoun F Hadaegh Farzad F Hadaegh Farzad F

Medicine 20160801 35

Hypertension is a critical public health concern worldwide. Identification of risk factors using traditional multivariable models has been a field of active research. The present study was undertaken to identify risk patterns associated with hypertension incidence using data mining methods in a cohort of Iranian adult population.Data on 6205 participants (44% men) age > 20 years, free from hypertension at baseline with no history of cardiovascular disease, were used to develop a series of predic ...[more]

PMID: 27583845

Similar Datasets

Project description:BackgroundAssessment the impact of disability on mortality among the elderly is vital to healthy ageing. The present study aimed to assess the long-term influence of disability on death in the elderly based on a longitudinal study.MethodThis study used the Chinese Longitudinal Healthy Longevity Study (CLHLS) data from 2002 to 2014, including 13,666 participants aged 65 years and older in analyses. The Katz ADL index was used to assess disability status and levels. Cumulative mortality rates were estimated by the Kaplan-Meier method. Cox proportional hazards models were conducted to estimate associations between disability and all-cause mortality for overall participants, two age groups as well as specific chronic disease groups. All reported results were adjusted by survey weights to account for the complex survey design.ResultsDuring the 12-year follow-up, the death density was 6.01 per 100 person-years. The 3-years' cumulative mortality rate of nondisabled elderly was 11.9% (95%CI: 10.9, 12.9%). As the level of disability increased, the cumulative mortality rate was from 28.1% (95%CI: 23.0, 33.1%) to 77.6% (95%CI: 63.8, 91.4%). Compared with non-disabled elderly, the multiple-adjusted hazard ratio of death due to disability was 1.68 (95% CI: 1.48, 1.90). The hazard ratios varied from 1.44 (95%CI: 1.23, 1.67) to 4.45 (95%CI: 2.69, 7.38) after classifying the disability levels. The hazard ratios of death in the young-old group (65-79 years) were higher than the old-old group (80 years and over) in both level B (HR = 1.58, 95%CI: 1.25, 2.00 vs. HR = 1.22, 95%CI: 1.06, 1.39, P = 0.029) and level G (HR = 24.09, 95%CI: 10.83, 53.60 vs. HR = 2.56, 95%CI: 1.75, 3.74, P < 0.001). For patients with hypertension, diabetes, heart disease, cerebrovascular disease as well as dementia, disability increases their relative risk of mortality by 1.64 (95%CI: 1.40, 1.93), 2.85 (95%CI: 1.46, 5.58), 1.45 (95%CI: 1.02, 2.05), 2.13 (95%CI: 1.54, 2.93) and 3.56 (95%CI: 1.22, 10.38) times, respectively.ConclusionsDisability increases the risk of all-cause death in the elderly, especially those with chronic diseases and the young-old group. Further studies are needed to better understand how to effectively prevent disability in the older population.

Project description:BackgroundThe study aimed to estimate the incidence of and period of progression to stage 2 hypertension from normal blood pressure.MethodsWe selected a total of 21,172 normotensive individuals between 2003 and 2004 from the National Health Insurance Service-Health Screening and followed them up until 2015. The criteria for blood pressure were based on the American College of Cardiology/American Heart Association 2017 guideline (normal BP: SBP < 120 and DBP < 80 mmHg, elevated BP: SBP 120-129 and DBP < 80 mmHg, stage 1 hypertension: SBP 130-139 or DBP 80-89 mmHg, stage 2 hypertension: SBP ≥140 or DBP ≥ 90 mmHg). We classified the participants into four courses (Course A: normal BP → elevated BP → stage 1 hypertension→ stage 2 hypertension, Course B: normal BP → elevated BP → stage 2 hypertension, Course C: normal BP → stage 1 hypertension → stage 2 hypertension, Course D: normal BP → stage 2 hypertension) according to their progression from normal blood pressure to stage 2 hypertension.ResultsDuring the median 12.23 years of follow-up period, 52.8% (n= 11,168) and 23.6% (n=5004) of the participants had stage 1 and stage 2 hypertension, respectively. In particular, over 60 years old had a 2.8-fold higher incidence of stage 2 hypertension than 40-49 years old. After the follow-up period, 77.5% (n=3879) of participants with stage 2 hypertension were found to be course C (n= 2378) and D (n=1501). After the follow-up period, 77.5% (n=3879) of participants with stage 2 hypertension were found to be course C (n= 2378) and D (n=1501). The mean years of progression from normal blood pressure to stage 2 hypertension were 8.7±2.6 years (course A), 6.1±2.9 years (course B), 7.5±2.8 years (course C) and 3.2±2.0 years, respectively.ConclusionsThis study found that the incidence of hypertension is associated with the progression at each stage. We suggest that the strategies necessary to prevent progression to stage 2 hypertension need to be set differently for each target course.

Project description:OBJECTIVE:Few studies have examined the spectrum and trends of non-communicable diseases (NCDs) in inpatients in eastern coastal China, which is transforming from an industrial economy to a service-oriented economy and is the most economically developed region in the country. This study aimed to dynamically elucidate the spectrum and characteristics of severe NCDs in eastern coastal China by analysing patients' longitudinal electronic health records (EHRs). SETTING:To monitor the spectrum of NCDs dynamically, we extracted the EHR data from 12 general tertiary hospitals in eastern coastal China from 2003 to 2014. The rankings of and trends in the proportions of different NCDs presented by inpatients in different gender and age groups were calculated and analysed. PARTICIPANTS:We obtained a total sample of 1 907 484 inpatients with NCDs from 2003 to 2014, 50.05% of whom were men and 81.53% were aged 50 years or older. RESULTS:There was an increase in the number of total NCD inpatients in eastern coastal China from 2003 to 2014. However, the proportion of chronic respiratory diseases and cancer inpatients decreased over the 12-year period. Compared with men, women displayed a significant increase in the proportion of mental and behavioural disorders (p<0.001) over time. Additionally, digestive diseases and sensory organ diseases significantly decreased among men, but not women. The older group accounted for a larger and growing proportion of the NCD inpatients, and the most common conditions in this group were cerebral infarctions, coronary heart disease and hypertension. In addition, the proportion of 21-year-old to 50-year-old inpatients with diabetes, blood diseases or endocrine diseases skyrocketed from 2003 to 2014 (p<0.001). CONCLUSIONS:The burden of inpatients' NCDs increased rapidly, particularly among women and younger people. The NCD spectrum observed in eastern coastal China is a good source of evidence for developing prevention guides for regions experiencing transition.

Dataset Information

Classification-based data mining for identification of risk patterns associated with hypertension in Middle Eastern population: A 12-year longitudinal study.

Publications

Classification-based data mining for identification of risk patterns associated with hypertension in Middle Eastern population: A 12-year longitudinal study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets