| 1. |
- Javeed, Ashir, 1989-, et al.
(författare)
-
Decision Support System for Predicting Mortality in Cardiac Patients Based on Machine Learning
- 2023
-
Ingår i: Applied Sciences. - : MDPI. - 2076-3417. ; 13:8
-
Tidskriftsartikel (refereegranskat)abstract
- Researchers have proposed several automated diagnostic systems based on machine learning and data mining techniques to predict heart failure. However, researchers have not paid close attention to predicting cardiac patient mortality. We developed a clinical decision support system for predicting mortality in cardiac patients to address this problem. The dataset collected for the experimental purposes of the proposed model consisted of 55 features with a total of 368 samples. We found that the classes in the dataset were highly imbalanced. To avoid the problem of bias in the machine learning model, we used the synthetic minority oversampling technique (SMOTE). After balancing the classes in the dataset, the newly proposed system employed a (Formula presented.) statistical model to rank the features from the dataset. The highest-ranked features were fed into an optimized random forest (RF) model for classification. The hyperparameters of the RF classifier were optimized using a grid search algorithm. The performance of the newly proposed model ((Formula presented.) _RF) was validated using several evaluation measures, including accuracy, sensitivity, specificity, F1 score, and a receiver operating characteristic (ROC) curve. With only 10 features from the dataset, the proposed model (Formula presented.) _RF achieved the highest accuracy of 94.59%. The proposed model (Formula presented.) _RF improved the performance of the standard RF model by 5.5%. Moreover, the proposed model (Formula presented.) _RF was compared with other state-of-the-art machine learning models. The experimental results show that the newly proposed decision support system outperforms the other machine learning systems using the same feature selection module ((Formula presented.)).
|
|
| 2. |
- Vuorinen, Miika, et al.
(författare)
-
Changes in vascular factors 28 years from midlife and late-life cortical thickness
- 2013
-
Ingår i: Neurobiology of Aging. - : Elsevier BV. - 0197-4580 .- 1558-1497. ; 34:1, s. 100-109
-
Tidskriftsartikel (refereegranskat)abstract
- We assessed midlife blood pressure (BP), body mass index, total cholesterol, and their changes over time in relation to cortical thickness on magnetic resonance imaging 28 years later in 63 elderly at risk of dementia. Participants in the population-based Cardiovascular Risk Factors, Aging, and Dementia study were first examined at midlife. A first follow-up was conducted after 21 years, and a second follow-up after an additional 7 years. Magnetic resonance images from the second follow-up were analyzed using algorithms developed at McGill University, Montreal, Canada. Midlife hypertension was related to thinner cortex in several brain areas, including insular, frontal, and temporal cortices. In elderly with thinner insular cortex, there was a continuous decline in systolic BP and an increase in pulse pressure after midlife, while in elderly with thicker insular cortex the decline in systolic BP started at older ages, paralleled by a decline in pulse pressure. No associations were found between body mass index, cholesterol, or apolipoprotein E ε4 allele and cortical thickness in this group of elderly at risk individuals.
|
|
| 3. |
- Heshmati, Amy Frances, et al.
(författare)
-
Childhood and adulthood socio-economic position and hypertensive disorders in pregnancy: the Uppsala Birth Cohort Multigenerational Study
- 2013
-
Ingår i: Journal of Epidemiology and Community Health. - : BMJ. - 0143-005X .- 1470-2738. ; 67:11, s. 939-946
-
Tidskriftsartikel (refereegranskat)abstract
- Background Childhood and adulthood socio-economic position (SEP) is associated with cardiovascular disease in later life, but associations with hypertensive disorders in pregnancy are not well established. Objective The aim of this study was to investigate the association of childhood and adulthood SEP with hypertensive disorders in pregnancy (chronic hypertension, gestational hypertension and pre-eclampsia/eclampsia). Method Study participants were Swedish women (n=9507) from generation 3 of the Uppsala Birth Cohort Multigenerational Study (UBCoS Multigen) who delivered a live singleton offspring between 1982 and 2008. Social and health data were obtained from routine Swedish registers. Associations of own education (adulthood SEP), and parental education and social class (childhood SEP) with hypertensive disorders were studied using logistic regression with adjustments for age, calendar period, parity, smoking and body mass index. Results Low own education was associated with chronic hypertension, but not with gestational hypertension or pre-eclampsia/eclampsia. Increased risk of chronic hypertension was seen in women whose mothers had medium education compared with women whose mothers had high education (OR 2.18, 95% CI 1.03 to 4.62). Women from a manual social class during childhood had twice the risk of chronic hypertension compared with those from non-manual backgrounds (OR 2.19, 95% CI 1.28 to 3.75). Childhood SEP was not associated with gestational hypertension or pre-eclampsia/eclampsia. Conclusions Childhood and adulthood SEP was associated with chronic hypertension in pregnancy. In contrast, no association with childhood or adulthood SEP was seen for gestational hypertension or pre-eclampsia/eclampsia.
|
|
| 4. |
- Matilla-Santander, Nuria, et al.
(författare)
-
Trajectories of precarious employment and the risk of myocardial infarction and stroke among middle-aged workers in Sweden : A register-based cohort study
- 2022
-
Ingår i: The Lancet Regional Health. - : Elsevier BV. - 2666-7762. ; 15
-
Tidskriftsartikel (refereegranskat)abstract
- Background The aim is to identify trajectories of precarious employment (PE) over time in Sweden to examine associations of these with the subsequent risk of myocardial infarction (MI) and stroke.Methods This is a nation-wide register-based cohort study of 1,583,957 individuals aged 40 to 61 years old residing in Sweden between 2003-2007. Trajectories of PE as a multidimensional construct and single PE components (contractual employment relationship, temporariness, income levels, multiple job holding, probability of coverage by collective agreements) were identified for 2003-2007 by means of group-based model trajectories. Risk Ratios (RR) for MI and stroke according to PE trajectories were calculated by means of generalized linear models with binomial family.Findings Adjusted estimates showed that constant PE and borderline PE trajectories increased the risk of MI (RR: 1.08, CI95%:1.05-1.11 and RR:1.13, CI95%: 1.07-1.20 respectively) and stroke (RR:1.14, CI95%: 1.10-1.18 and HR:1.24, CI95%: 1.16-1.33 respectively) among men. A higher risk of stroke in men was found for the following unidimensional trajectories: former agency employees (RR:1.32, CI95%:1.04-1.68); moving from high to a low probability of having collective agreements (RR: 1.10, CI95%:1.01-1.20). Having constant low or very low income was associated to an increased risk of MI and Stroke for both men and women.Interpretation The study findings provide evidence that PE increases the risk of stroke and possibly MI. It highlights the importance of being covered by collective bargaining agreements, being directly employed and having sufficient income levels over time.
|
|
| 5. |
- Lindberg, Terese, et al.
(författare)
-
Prevalence and Incidence of Atrial Fibrillation and Other Arrhythmias in the General Older Population : Findings From the Swedish National Study on Aging and Care
- 2019
-
Ingår i: Gerontology and geriatric medicine. - : SAGE PUBLICATIONS INC. - 2333-7214. ; 5
-
Tidskriftsartikel (refereegranskat)abstract
- Aim: To study the prevalence and cumulative incidence of arrhythmias in the general population of adults aged 60 and older over a 6-year period. Study Design and Setting: Data were taken from the Swedish National Study on Aging and Care (SNAC), a national, longitudinal, multidisciplinary study of the general elderly population (defined as 60 years of age or older). A 12-lead resting electrocardiography (ECG) was performed at baseline and 6-year follow-up. Results: The baseline prevalence of atrial fibrillation (AF) was 4.9% (95% confidence interval [CI] = [4.5%, 5.5%]), and other arrhythmias including ventricular premature complexes (VPCs), supraventricular tachycardia (SVT), and supraventricular extrasystole (SVES) were seen in 8.4% (7.7%, 9.0%) of the population. A first- or second-degree atrioventricular (AV) block was found in 7.1% of the population (95% CI = [6.5%, 7.7%]), and there were no significant differences between men and women in baseline arrhythmia prevalence. The 6-year cumulative incidence of AF was 4.1% (95% CI = [3.5%, 4.9%]), or 6.9/1,000 person-years (py; 95% CI = [5.7, 8.0]). The incidence of AF, other arrhythmias, AV block, and pacemaker-induced rhythm was significantly higher in men in all cohorts except for the oldest. Conclusion: Our data highlight the prevalence and incidence of arrhythmias, which rapidly increase with advancing age in the general population.
|
|
| 6. |
- Ervasti, Jenni, et al.
(författare)
-
Long working hours and risk of 50 health conditions and mortality outcomes : a multicohort study in four European countries
- 2021
-
Ingår i: The Lancet Regional Health. - : Elsevier BV. - 2666-7762. ; 11
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Studies on the association between long working hours and health have captured only a narrow range of outcomes (mainly cardiometabolic diseases and depression) and no outcome-wide studies on this topic are available. To achieve wider scope of potential harm, we examined long working hours as a risk factor for a wide range of disease and mortality endpoints.Methods: The data of this multicohort study were from two population cohorts from Finland (primary analysis, n=59 599) and nine cohorts (replication analysis, n=44 262) from Sweden, Denmark, and the UK, all part of the Individual-participant Meta-analysis in Working Populations (IPD-Work) consortium. Baseline-assessed long working hours (≥55 hours per week) were compared to standard working hours (35-40 h). Outcome measures with follow-up until age 65 years were 46 diseases that required hospital treatment or continuous pharmacotherapy, all-cause, and three cause-specific mortality endpoints, ascertained via linkage to national health and mortality registers.Findings: 2747 (4·6%) participants in the primary cohorts and 3027 (6·8%) in the replication cohorts worked long hours. After adjustment for age, sex, and socioeconomic status, working long hours was associated with increased risk of cardiovascular death (hazard ratio 1·68; 95% confidence interval 1·08-2·61 in primary analysis and 1·52; 0·90-2·58 in replication analysis), infections (1·37; 1·13-1·67 and 1·45; 1·13-1·87), diabetes (1·18; 1·01-1·38 and 1·41; 0·98-2·02), injuries (1·22; 1·00-1·50 and 1·18; 0·98-1·18) and musculoskeletal disorders (1·15; 1·06-1·26 and 1·13; 1·00-1·27). Working long hours was not associated with all-cause mortality.Interpretation: Follow-up of 50 health outcomes in four European countries suggests that working long hours is associated with an elevated risk of early cardiovascular death and hospital-treated infections before age 65. Associations, albeit weak, were also observed with diabetes, musculoskeletal disorders and injuries. In these data working long hours was not related to elevated overall mortality.
|
|
| 7. |
- Kivimäki, Mika, et al.
(författare)
-
Long working hours as a risk factor for atrial fibrillation : a multi-cohort study
- 2017
-
Ingår i: European Heart Journal. - : Oxford University Press. - 0195-668X .- 1522-9645. ; 38:34, s. 2621-2628
-
Tidskriftsartikel (refereegranskat)abstract
- Aims Studies suggest that people who work long hours are at increased risk of stroke, but the association of long working hours with atrial fibrillation, the most common cardiac arrhythmia and a risk factor for stroke, is unknown. We examined the risk of atrial fibrillation in individuals working long hours (>= 55 per week) and those working standard 35-40 h/week. Methods and results In this prospective multi-cohort study from the Individual-Participant-Data Meta-analysis in Working Populations (IPD-Work) Consortium, the study population was 85 494 working men and women (mean age 43.4 years) with no recorded atrial fibrillation. Working hours were assessed at study baseline (1991-2004). Mean follow-up for incident atrial fibrillation was 10 years and cases were defined using data on electrocardiograms, hospital records, drug reimbursement registers, and death certificates. We identified 1061 new cases of atrial fibrillation (10-year cumulative incidence 12.4 per 1000). After adjustment for age, sex and socioeconomic status, individuals working long hours had a 1.4-fold increased risk of atrial fibrillation compared with those working standard hours (hazard ratio = 1.42, 95% CI= 1.13-1.80, P= 0.003). There was no significant heterogeneity between the cohort-specific effect estimates (I-2= 0%, P = 0.66) and the finding remained after excluding participants with coronary heart disease or stroke at baseline or during the follow-up (N= 2006, hazard ratio= 1.36, 95% CI= 1.05-1.76, P = 0.0180). Adjustment for potential confounding factors, such as obesity, risky alcohol use and high blood pressure, had little impact on this association. Conclusion Individuals who worked long hours were more likely to develop atrial fibrillation than those working standard hours.
|
|
| 8. |
- Fransson, Eleonor I., et al.
(författare)
-
The Association between Job Strain and Atrial Fibrillation : Results from the Swedish WOLF Study
- 2015
-
Ingår i: BioMed Research International. - : Hindawi Publishing Corporation. - 2314-6133 .- 2314-6141.
-
Tidskriftsartikel (refereegranskat)abstract
- Introduction: Atrial fibrillation (AF) is a common heart rhythmdisorder. Several life-style factors have been identified as risk factors for AF, but less is known about the impact of work-related stress. This study aims to evaluate the association between work-related stress, defined as job strain, and risk of AF. Methods: Data from the Swedish WOLF study was used, comprising 10,121 working men and women. Job strain was measured by the demand-control model. Information on incident AF was derived from national registers. Cox proportional hazard regression was used to estimate hazard ratios (HR) and 95% confidence intervals (CI) for the association between job strain and AF risk. Results: In total, 253 incident AF cases were identified during a total follow-up time of 132,387 person-years. Job strain was associated with AF risk in a time-dependent manner, with stronger association after 10.7 years of follow-up (HR 1.93, 95% CI 1.10-3.36 after 10.7 years, versus HR 1.11, 95% CI 0.67-1.83 before 10.7 years). The results pointed towards a dose-response relationship when taking accumulated exposure to job strain over time into account. Conclusion: This study provides support to the hypothesis that work-related stress defined as job strain is linked to an increased risk of AF.
|
|
| 9. |
- Virtanen, Marianna, et al.
(författare)
-
Perceived job insecurity as a risk factor for incident coronary heart disease : systematic review and meta-analysis
- 2013
-
Ingår i: The BMJ. - : BMJ. - 1756-1833. ; 347
-
Tidskriftsartikel (refereegranskat)abstract
- Objective To determine the association between self reported job insecurity and incident coronary heart disease.Design A meta-analysis combining individual level data from a collaborative consortium and published studies identified by a systematic review.Data sources We obtained individual level data from 13 cohort studies participating in the Individual-Participant-Data Meta-analysis in Working Populations Consortium. Four published prospective cohort studies were identified by searches of Medline (to August 2012) and Embase databases (to October 2012), supplemented by manual searches.Review methods Prospective cohort studies that reported risk estimates for clinically verified incident coronary heart disease by the level of self reported job insecurity. Two independent reviewers extracted published data. Summary estimates of association were obtained using random effects models.Results The literature search yielded four cohort studies. Together with 13 cohort studies with individual participant data, the meta-analysis comprised up to 174 438 participants with a mean follow-up of 9.7 years and 1892 incident cases of coronary heart disease. Age adjusted relative risk of high versus low job insecurity was 1.32 (95% confidence interval 1.09 to 1.59). The relative risk of job insecurity adjusted for sociodemographic and risk factors was 1.19 (1.00 to 1.42). There was no evidence of significant differences in this association by sex, age (<50 v >= 50 years), national unemployment rate, welfare regime, or job insecurity measure.Conclusions The modest association between perceived job insecurity and incident coronary heart disease is partly attributable to poorer socioeconomic circumstances and less favourable risk factor profiles among people with job insecurity.
|
|
| 10. |
- Heiland, Emerald G, et al.
(författare)
-
Cardiovascular Risk Burden and Future Risk of Walking Speed Limitation in Older Adults
- 2017
-
Ingår i: Journal of The American Geriatrics Society. - : Wiley. - 0002-8614 .- 1532-5415. ; 65:11, s. 2418-2424
-
Tidskriftsartikel (refereegranskat)abstract
- OBJECTIVES: To explore the association between cardiovascular risk factor (CRF) burden and limitation in walking speed, balance, and chair stand and to verify whether these associations vary according to age and cognitive status.DESIGN: Longitudinal population-based study.SETTING: Urban area of Stockholm, Sweden.PARTICIPANTS: Individuals aged 60 and older who participated in the Swedish National Study on Aging and Care in Kungsholmen and were free of limitations in walking speed (n = 1,441), balance (n = 1,154), or chair stands (n = 1,496) at baseline (2001-04).MEASUREMENTS: At baseline, data on demographic characteristics, CRFs, other lifestyle factors, C-reactive protein, and cognitive function were collected. CRF burden was measured using the Framingham general cardiovascular risk score (FRS). Limitations in walking speed (<0.8 m/s), balance (<5 seconds), and chair stand (inability to rise 5 times) were determined at 3-, 6-, and 9-year follow-up. Data were analyzed using Cox proportional hazards models stratified according to age (<78, >= 78).RESULTS: During follow-up, 326 persons developed limitations in walking speed, 303 in balance, and 374 in chair stands. An association between the FRS and walking speed limitation was evident only in adults younger than 78 (for each 1-point increase in FRS: hazard ratio (HR) = 1.09, 95% confidence interval (CI) = 1.02-1.17) after controlling for potential confounders including cognitive function (correspondingly, in adults aged >= 78: HR = 0.98, 95% CI = 0.92-1.03). Also, higher FRS was significantly associated with faster decline in walking speed (P<.001).CONCLUSION: A higher FRS is associated with greater risk of subsequent development of walking speed limitation in adults younger than 78, independent of cognitive function. Interventions targeting multiple CRFs in younger-old people may help in maintaining mobility function.
|
|
