Classification of electrocardiogram and auscultatory blood pressure signals using machine learning models

In this paper, two real-world medical classification problems using electrocardiogram (ECG) and auscultatory blood pressure (Korotkoff) signals are examined. A total of nine machine learning models are applied to perform classification of the medical data sets. A number of useful performance metrics which include accuracy, sensitivity, specificity, as well as the area under the receiver operating characteristic curve are computed. In addition to the original data sets, noisy data sets are generated to evaluate the robustness of the classifiers against noise. The 10-fold cross validation method is used to compute the performance statistics, in order to ensure statistically reliable results pertaining to classification of the ECG and Korotkoff signals are produced. The outcomes indicate that while logistic regression models perform the best with the original data set, ensemble machine learning models achieve good accuracy rates with noisy data sets.

Cortisol, blood pressure, and heart rate responses to food intake were independent of physical fitness levels in women

This research tested the hypothesis that women who had higher levels of physical fitness will have lower hypothalamo-pituitary-adrenal axis (cortisol) and sympatho-adrenal medullary system (blood pressure and heart rate) responses to food intake compared with women who had low levels of physical fitness. Lower fitness (n = 22; maximal oxygen consumption = 27.4 ± 1.0 mL∙kg(-1)·min(-1)) and higher fitness (n = 22; maximal oxygen consumption = 41.9 ± 1.6 mL∙kg(-1)·min(-1)) women (aged 30-50 years; in the follicular phase of the menstrual cycle) who participated in levels of physical activity that met (lower fitness = 2.7 ± 0.5 h/week) or considerably exceeded (higher fitness = 7.1 ± 1.4 h/week) physical activity guidelines made their own lunch using standardised ingredients at 1200 h. Concentrations of cortisol were measured in blood samples collected every 15 min from 1145-1400 h. Blood pressures and heart rate were also measured every 15 min between 1145 h and 1400 h. The meal consumed by the participants consisted of 20% protein, 61% carbohydrates, and 19% fat. There was a significant overall response to lunch in all of the parameters measured (time effect for all, p < 0.01). The cortisol response to lunch was not significantly different between the groups (time × treatment, p = 0.882). Overall, both groups showed the same pattern of cortisol secretion (treatment p = 0.839). Systolic blood pressure, diastolic blood pressure, mean arterial pressure, or heart rate responses (time × treatment, p = 0.726, 0.898, 0.713, and 0.620, respectively) were also similar between higher and lower fitness women. Results suggest that the physiological response to food intake in women is quite resistant to modification by elevated physical fitness levels.

Breaking up prolonged sitting reduces resting blood pressure in overweight/obese adults

Abstract
Aim:
To compare the effect of 7 h of prolonged sitting on resting blood pressure with asimilar duration of sitting combined with intermittent brief bouts of light-intensity or moderate-intensity physical activity.
Methods and results:
Overweight/obeseadults(nZ19;aged45 e65years) were recruited for a randomized three-treatment crossover trial with a one-week washout between treatments: 1) uninterrupted sitting; 2) sitting with 2 min bouts of light-intensity walking at 3.2 km/h every 20 min;and, 3) sitting with 2 min bouts of moderate-intensity walking at between 5.8 and 6.4 km/h every 20 min. After an initial 2 h period seated, participants consumed a test meal (75 g carbohydrate,50 g fat) and completed each condition over the next 5 h. Resting blood pressure was assessed oscillometrically every hour as a single measurement, 5 min prior to each activity bout. GEE models were adjusted for sex, age, BMI, fasting blood pressure and treatment order. After adjustment for potential confounding variables, breaking up prolonged sitting with lightand moderate-intensity activity breaks was associated with lower systolic blood pressure [light:120

1 mmHg (estimated marginal mean

SEM),
P
Z
0.002; moderate: 121

1 mmHg,
P
Z
0.02], compared to uninterrupted sitting (123

1 mmHg). Diastolic blood pressure was also
signi
fi
cantly lower during both of the activity conditions (light: 76

1 mmHg,
P
Z
0.006; moder-
ate: 77

1mmHg,
P
Z
0.03) compared to uninterrupted sitting (79

1 mmHg). No significant between-condition differences were observed in mean arterial pressure or heart rate.
Conclusion:
Regularly breaking up prolonged sitting may reduce systolic and diastolic blood pressure.

Impact of nurse-mediated management on achieving blood pressure goal levels in primary care: insights from the Valsartan intensified primary carE reduction of blood pressure study

BACKGROUND: Blood pressure targets in individuals treated for hypertension in primary care remain difficult to attain.

AIMS: To assess the role of practice nurses in facilitating intensive and structured management to achieve ideal BP levels.

METHODS: We analysed outcome data from the Valsartan Intensified Primary carE Reduction of Blood Pressure Study. Patients were randomly allocated (2:1) to the study intervention or usual care. Within both groups, a practice nurse mediated the management of blood pressure for 439 patients with endpoint blood pressure data (n=1492). Patient management was categorised as: standard usual care (n=348, 23.3%); practice nurse-mediated usual care (n=156, 10.5%); standard intervention (n=705, 47.3%) and practice nurse-mediated intervention (n=283, 19.0%). Blood pressure goal attainment at 26-week follow-up was then compared.

RESULTS: Mean age was 59.3±12.0 years and 62% were men. Baseline blood pressure was similar in practice nurse-mediated (usual care or intervention) and standard care management patients (150 ± 16/88 ± 11 vs. 150 ± 17/89 ± 11 mmHg, respectively). Practice nurse-mediated patients had a stricter blood pressure goal of ⩽125/75 mmHg (33.7% vs. 27.3%, p=0.026). Practice nurse-mediated intervention patients achieved the greatest blood pressure falls and the highest level of blood pressure goal attainment (39.2%) compared with standard intervention (35.0%), practice nurse-mediated usual care (32.1%) and standard usual care (25.3%; p<0.001). Practice nurse-mediated intervention patients were almost two-fold more likely to achieve their blood pressure goal compared with standard usual care patients (adjusted odds ratio 1.92, 95% confidence interval 1.32 to 2.78; p=0.001).

CONCLUSION: There is greater potential to achieve blood pressure targets in primary care with practice nurse-mediated hypertension management.

No effect of multivitamin supplementation on central blood pressure in healthy older people: a randomized controlled trial

BACKGROUND AND AIMS: Central blood pressure rises with age, which increases cardiovascular risk. There is some evidence that nutritional supplements may be useful to reduce central blood pressures in older people, but no studies have investigated the effects of multivitamin supplements for this purpose. This randomized, double-blind, placebo-controlled study investigated the effects of 16-weeks supplementation with gender-specific multivitamin and herbal supplements.

METHOD: Participants were healthy individuals, free from heart disease, and included 160 females aged ≥ 50 and 79 males aged 50-65 years. Analyses of co-variance, correcting for baseline cardiovascular assessments, were used to determine the effects of supplementation on central cardiovascular measures including augmentation index, augmentation pressure and pulse pressure. Significance was set at p = 0.016.

RESULTS: No effects of multivitamin supplementation were observed in either males or females (respectively) for central augmentation index (p = 0.841; p = 0.296), central augmentation pressure (p = 0.794; p = 0.442), and central pulse pressure (p = 0.078; p = 0.304). Similarly, there was no treatment effect observed for brachial systolic, diastolic or pulse pressures.

CONCLUSION: Four months multivitamin supplementation does not appear to exert any benefit to measures of central blood pressure in healthy older people.

Establishing reference values for central blood pressure and its amplification in a general healthy population and according to cardiovascular risk factors

AIMS: Estimated central systolic blood pressure (cSBP) and amplification (Brachial SBP-cSBP) are non-invasive measures potentially prognostic of cardiovascular (CV) disease. No worldwide, multiple-device reference values are available. We aimed to establish reference values for a worldwide general population standardizing between the different available methods of measurement. How these values were significantly altered by cardiovascular risk factors (CVRFs) was then investigated. METHODS AND RESULTS: Existing data from population surveys and clinical trials were combined, whether published or not. Reference values of cSBP and amplification were calculated as percentiles for 'Normal' (no CVRFs) and 'Reference' (any CVRFs) populations. We included 45,436 subjects out of 82,930 that were gathered from 77 studies of 53 centres. Included subjects were apparently healthy, not treated for hypertension or dyslipidaemia, and free from overt CV disease and diabetes. Values of cSBP and amplification were stratified by brachial blood pressure categories and age decade in turn, both being stratified by sex. Amplification decreased with age and more so in males than in females. Sex was the most powerful factor associated with amplification with 6.6 mmHg (5.8-7.4) higher amplification in males than in females. Amplification was marginally but significantly influenced by CVRFs, with smoking and dyslipidaemia decreasing amplification, but increased with increasing levels of blood glucose. CONCLUSION: Typical values of cSBP and amplification in a healthy population and a population free of traditional CVRFs are now available according to age, sex, and brachial BP, providing values included from different devices with a wide geographical representation. Amplification is significantly influenced by CVRFs, but differently in men and women.

Chronic mental stress is a cause of essential hypertension : presence of biological markers of stress

1. In searching for biological evidence that essential hypertension is caused by chronic mental stress, a disputed proposition, parallels are noted with panic disorder, which provides an explicit clinical model of recurring stress responses.
2. There is clinical comorbidity; panic disorder prevalence is increased threefold in essential hypertension. Plasma cortisol is elevated in both.
3. In panic disorder and essential hypertension, but not in health, single sympathetic nerve fibres commonly fire repeatedly within an individual cardiac cycle; this appears to be a signature of stress exposure. For both conditions, adrenaline cotransmission is present in sympathetic nerves.
4. Tissue nerve growth factor is increased in both (nerve growth factor is a stress reactant). There is induction of the adrenaline synthesizing enzyme, phenylethanolamine-N-methyltransferase, in sympathetic nerves, an explicit indicator of mental stress exposure.
5. The question of whether chronic mental stress causes high blood pressure, still hotly debated, has been reviewed by an Australian Government body, the Specialist Medical Review Council. Despite the challenging medicolegal implications, the Council determined that stress is one proven cause of hypertension, this ruling being published in the 27 March 2002 Australian Government Gazette. This judgement was reached after consideration of the epidemiological evidence, but in particular after review of the specific elements of the neural pathophysiology of essential hypertension, described above.

Physical activity and healthy weight maintenance from childhood to adulthood

The objective of this study was to determine whether change in physical activity was associated with maintaining a healthy weight from childhood to adulthood. This prospective cohort study examined 1,594 young Australian adults (48.9% female) aged 27–36 years who were first examined at age 9–15 years as part of a national health and fitness survey. BMI was calculated from measured height and weight, and physical activity was self-reported at both time points; pedometers were also used at follow-up. Change in physical activity was characterized by calculating the difference between baseline and follow-up z-scores. Change scores were categorized as decreasing (large, moderate), stable, or increasing (large, moderate). Healthy weight was defined in childhood as a BMI less than international overweight cutoff points, and in adulthood as BMI<25 kg/m2. Healthy weight maintainers were healthy weight at both time points. Compared with those who demonstrated large relative decreases in physical activity, females in all other groups were 25–37% more likely to be healthy weight maintainers, although associations differed according to the physical activity measure used at follow-up and few reached statistical significance. Although younger males whose relative physical activity moderately or largely increased were 27–34% more likely to be healthy weight maintainers than those whose relative physical activity largely decreased, differences were not statistically significant. In conclusion, relatively increasing and stable physical activity from childhood to adulthood was only weakly associated with healthy weight maintenance. Examining personal, social, and environmental factors associated with healthy weight maintenance will be an important next step in understanding why some groups avoid becoming overweight.

Consumer knowledge and attitudes to salt intake and labelled salt information

The objective of this study was to investigate consumers’ knowledge of health risks of high salt intake and frequency of use and understanding of labelled salt information. We conducted a cross-sectional survey in shopping centres within Metropolitan Melbourne. A sample of 493 subjects was recruited. The questionnaire assessed salt related shopping behaviours, attitudes to salt intake and health and their ability to interpret labelled sodium information. Four hundred and seventy four valid surveys were collected (65% female, 64% being the main shopper). Most participants knew of the relationship between salt intake and high blood pressure (88%). Sixty five percent of participants were unable to correctly identify the relationship between salt and sodium. Sixty nine percent reported reading the salt content of food products when shopping. Salt label usage was significantly related to shoppers concern about the amount of salt in their diet and the belief that their health could improve by lowering salt intake. Approximately half of the sample was unable to accurately use labelled sodium information to pick low salt options. Raising consumer awareness of the health risks associated with high salt consumption may increase salt label usage and purchases of low salt foods. However, for food labels to be effective in helping consumers select low salt foods a more ‘user friendly’ labelling format is needed.

HOMA insulin sensitivity index and the risk of all-cause mortality and cardiovascular disease events in the general population : the Australian diabetes, obesity and lifestyle study (AusDiab) study

Aims/hypothesis We assessed whether the relationships between insulin sensitivity and all-cause mortality as well as fatal or non-fatal cardiovascular disease (CVD) events are independent of elevated blood glucose, high blood pressure, dyslipidaemia and body composition in individuals without diagnosed diabetes.
Methods Between 1999 and 2000, baseline fasting insulin, glucose and lipids, 2 h plasma glucose, HbA1c, anthropometrics, blood pressure, medication use, smoking and history of CVD were collected from 8,533 adults aged >35 years from the population-based Australian Diabetes, Obesity and Lifestyle study. Insulin sensitivity was estimated by HOMA of insulin sensitivity (HOMA-%S). Deaths and fatal or non-fatal CVD events were ascertained through linkage to the National Death Index and medical records adjudication.
Results After a median of 5.0 years there were 277 deaths and 225 CVD events. HOMA-%S was not associated with all-cause mortality. Compared with the most insulin-sensitive quintile, the combined fatal or non-fatal CVD HR (95% CI) for quintiles of decreasing HOMA-%S were 1.1 (0.6–1.9), 1.4 (0.9–2.3), 1.6 (1.0–2.5) and 2.0 (1.3–3.1), adjusting for age and sex. Smoking, CVD history, hypertension, lipid-lowering medication, total cholesterol and waist-to-hip ratio moderately attenuated this relationship. However, the association was rendered non-significant by adding HDL. Fasting plasma glucose, but not HOMA-%S significantly improved the prediction of CVD, beyond that seen with other risk factors.
Conclusions/interpretation In this cohort, HOMA-%S showed no association with all-cause mortality and only a modest association with CVD events, largely explained by its association with HDL. Fasting plasma glucose was a better predictor of CVD than HOMA-%S.

Psychological interventions for the prevention and management of lifestyle-related chronic disease

The Australian Government's current health reform agenda provides a timely opportunity to highlight the contribution of health psychology interventions in the prevention and management of chronic diseases associated with lifestyle risk factors. The World Health Organisation (2009) has identified the main risk factors responsible for deaths internationally as high blood pressure (responsible for 13% of deaths), tobacco use (9%), high blood sugar (6%), physical inactivity (6%), overweight and obesity (5%), high cholesterol (5%), unsafe sex (4%) and alcohol use (4%). A number of these factors also increase the risk of major chronic diseases - cardiovascular disease, diabetes and cancers. There is now a substantial evidence base for the effectiveness of health improvement interventions based on psychological theory, research and practice and hence they deserve a high level of recognition within systems for funding health. This article presents a summary of a systematic review of the evidence for the effectiveness of health psychology interventions in the prevention and treatment of chronic diseases associated with lifestyle risk factors.

The development of a national salt reduction strategy for Australia

Excess dietary salt is a well established cause of high blood pressure and vascular disease. National and international bodies recommend a significant reduction in population salt intakes on the basis of strong evidence for health gains that population salt reduction strategies could achieve. The Australian Division of World Action on Salt and Health (AWASH) coordinates the Drop the Salt! campaign in Australia. This aims to reduce the average amount of salt consumed by Australians to six grams per day over five years through three main implementation strategies targeting the food industry, the media and government. This strategy has the potential to achieve a rapid and significant reduction in dietary salt consumption in Australia. With industry and government engagement, this promises to be a highly effective, low cost option for preventing chronic disease.

Farming fit? Dispelling the Australian agrarian myth.

Background: Rural Australians face a higher mental health and lifestyle disease burden (obesity, diabetes and
cardiovascular disease) than their urban counterparts. Our ongoing research reveals that the Australian farming
community has even poorer physical and mental health outcomes than rural averages. In particular, farm men and
women have high rates of overweightness, obesity, abdominal adiposity, high blood pressure and psychological
distress when compared against Australian averages. Within our farming cohort we observed a significant
association between psychological distress and obesity, abdominal adiposity and body fat percentage in the
farming population.
Presentation of hypothesis: This paper presents a hypothesis based on preliminary data obtained from an
ongoing study that could potentially explain the complex correlation between obesity, psychological distress and
physical activity among a farming population. We posit that spasmodic physical activity, changing farm practices
and climate variability induce prolonged stress in farmers. This increases systemic cortisol that, in turn, promotes
abdominal adiposity and weight gain.
Testing the hypothesis: The hypothesis will be tested by anthropometric, biochemical and psychological analysis
matched against systemic cortisol levels and the physical activity of the subjects.
Implications of the hypothesis tested: Previous studies indicate that farming populations have elevated rates of
psychological distress and high rates of suicide. Australian farmers have recently experienced challenging climatic
conditions including prolonged drought, floods and cyclones. Through our interactions and through the media it is
not uncommon for farmers to describe the effect of this long-term stress with feelings of ‘defeat’. By gaining a
greater understanding of the role cortisol and physical activity have on mental and physical health we may
positively impact the current rates of psychological distress in farmers.

Behavioural and physical characteristics associated with vitamin D status in women

For most people in Australia, the primary source of vitamin D is casual exposure to sunlight. Hypovitaminosis D has been reported for high-risk populations, but little has been documented for women of all ages living in the community. Using cross-sectional data, we aimed to describe physical and behavioural characteristics associated with serum 25-hydroxyvitamin D (25OHD) for such women and to determine the association of serum 25OHD with hypertension and bone health. Serum 25OHD, parathyroid hormone (PTH), blood pressure, bone mineral density (BMD) and anthropometry were measured in a random sample of 861 women aged 20–92 years enrolled in the Geelong Osteoporosis Study, set in a temperate region at latitude 38–39°S. Lifestyle factors (including diet, smoking, medication use, socio-economic status, residence, education, occupation, and physical activity) were documented by questionnaire. In season-adjusted models for women aged 20–54 years, physical activity and living with a partner were independently and positively associated with serum 25OHD; associations with weight and waist–hip ratio were negative. Among older women, physical activity, vitamin D intake and urban dwelling were positively associated with serum 25OHD; age, weight and smoking were negative. Compared with the lowest tertile, those in the highest serum 25OHD tertile were less likely to have elevated serum PTH (adjusted OR = 0.25, 95% CI 0.16–0.41) and high blood pressure (adjusted OR = 0.40, 95% CI 0.22–0.72), and more likely to have normal hip and spine BMD (adjusted OR = 1.65, 95% CI 1.08–2.52). In multivariable models adjusting for season, age, weight (and height), BMD was associated with serum 25OHD at the spine, hip and whole body; no associations were detected at the forearm and no other characteristics were identified as confounders. Factors associated with high vitamin D status generally reflected healthy body habitus and active lifestyles. In contrast, excessive weight and smoking were associated with poorer vitamin D status. Women with high vitamin D were less likely to have elevated PTH, hypertension or bone deficits than women with poor levels.

Improving the cost-effectiveness of cardiovascular disease prevention in Australia : a modelling study

Background : Cardiovascular disease is the leading cause of death worldwide. Like many countries, Australia is currently changing its guidelines for cardiovascular disease prevention from drug treatment for everyone with 'high blood pressure' or 'high cholesterol', to prevention based on a patient's absolute risk. In this research, we model cost-effectiveness of cardiovascular disease prevention with blood pressure and lipid drugs in Australia under three different scenarios: (1) the true current practice in Australia; (2) prevention as intended under the current guidelines; and (3) prevention according to proposed absolute risk levels. We consider the implications of changing to absolute risk-based cardiovascular disease prevention, for the health of the Australian people and for Government health sector expenditure over the long term.

Methods : We evaluate cost-effectiveness of statins, diuretics, ACE inhibitors, calcium channel blockers and beta-blockers, for Australian men and women, aged 35 to 84 years, who have never experienced a heart disease or stroke event. Epidemiological changes and health care costs are simulated by age and sex in a discrete time Markov model, to determine total impacts on population health and health sector costs over the lifetime, from which we derive cost-effectiveness ratios in 2008 Australian dollars per quality-adjusted life year.

Results : Cardiovascular disease prevention based on absolute risk is more cost-effective than prevention under the current guidelines based on single risk factor thresholds, and is more cost-effective than the current practice, which does not follow current clinical guidelines. Recommending blood pressure-lowering drugs to everyone with at least 5% absolute risk and statin drugs to everyone with at least 10% absolute risk, can achieve current levels of population health, while saving $5.4 billion for the Australian Government over the lifetime of the population. But savings could be as high as $7.1 billion if Australia could match the cheaper price of statin drugs in New Zealand.

Conclusions : Changing to absolute risk-based cardiovascular disease prevention is highly recommended for reducing health sector spending, but the Australian Government must also consider measures to reduce the cost of statin drugs, over and above the legislated price cuts of November 2010.