scholarly journals A Machine Learning-Based Prediction Model for Cardiovascular Risk in Women With Preeclampsia

2021 ◽  
Vol 8 ◽  
Author(s):  
Guan Wang ◽  
Yanbo Zhang ◽  
Sijin Li ◽  
Jun Zhang ◽  
Dongkui Jiang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Random Forest ◽  
Prediction Model ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Machine Learning Algorithms ◽  
Brier Score ◽  
Random Forest Algorithm

Objective: Preeclampsia affects 2–8% of women and doubles the risk of cardiovascular disease in women after preeclampsia. This study aimed to develop a model based on machine learning to predict postpartum cardiovascular risk in preeclamptic women.Methods: Collecting demographic characteristics and clinical serum markers associated with preeclampsia during pregnancy of 907 preeclamptic women retrospectively, we predicted the cardiovascular risk (ischemic heart disease, ischemic cerebrovascular disease, peripheral vascular disease, chronic kidney disease, metabolic system disease or arterial hypertension). The study samples were divided into training sets and test sets randomly in the ratio of 8:2. The prediction model was developed by 5 different machine learning algorithms, including Random Forest. 10-fold cross-validation was performed on the training set, and the performance of the model was evaluated on the test set.Results: Cardiovascular disease risk occurred in 186 (20.5%) of these women. By weighing area under the curve (AUC), the Random Forest algorithm presented the best performance (AUC = 0.711[95%CI: 0.697–0.726]) and was adopted in the feature selection and the establishment of the prediction model. The most important variables in Random Forest algorithm included the systolic blood pressure, Urea nitrogen, neutrophil count, glucose, and D-Dimer. Random Forest algorithm was well calibrated (Brier score = 0.133) in the test group, and obtained the highest net benefit in the decision curve analysis.Conclusion: Based on the general situation of patients and clinical variables, a new machine learning algorithm was developed and verified for the individualized prediction of cardiovascular risk in post-preeclamptic women.

scholarly journals Cardiovascular Disease Risk Factors: How Relevant in African Men With Prostate Cancer Receiving Androgen-Deprivation Therapy?

2017 ◽  
Vol 3 (1) ◽  
pp. 7-14
Author(s):  
Okon Ekwere Essien ◽  
Iya Eze Bassey ◽  
Rebecca Mtaku Gali ◽  
Alphonsus Ekpe Udoh ◽  
Uwem Okon Akpan ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Waist Circumference ◽  
Total Cholesterol ◽  
Ldl Cholesterol ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Treatment Naïve

Purpose Cardiovascular disease risk factors have been associated with androgen-deprivation therapy (ADT) in white and Hispanic populations. It is therefore relevant to determine if there exists a relationship between these parameters in the African population. Patients and Methods The design of the study was cross sectional. Prostate-specific antigen concentration, waist circumference, body mass index (BMI), lipid profile, glucose level, and insulin level were determined in 153 patients with prostate cancer and 80 controls. The patients with prostate cancer were divided into subgroups of treatment-naïve patients and those receiving ADT. Results Mean total cholesterol ( P = .010), LDL cholesterol ( P = .021), BMI ( P = .001), and waist circumference ( P = .029) values were significantly higher in patients treated with ADT when compared with treatment-naïve patients. In patients treated with ADT for up to 1 year, only mean BMI was significantly higher than in treatment-naïve patients, whereas those treated with ADT for more than 1 year had significantly higher mean BMI, waist circumference, total cholesterol, and LDL cholesterol values when compared with treatment-naïve patients. There were no significant differences in insulin or glucose levels. Those undergoing hormone manipulation after orchiectomy had fewer cardiovascular risk factors compared with those undergoing hormone manipulation alone. Conclusion This study shows that ADT results in elevated total cholesterol, LDL cholesterol, BMI, and waist circumference values, all of which are risk factors of cardiovascular disease. Screening for cardiovascular risk factors should be included in treatment plans for patients with prostate cancer.

Abstract P375: Vascular Age Versus Calendar Age as Surrogate for Atherosclerotic Burden and Cardiovascular Disease Risk

Circulation ◽  
2013 ◽  
Vol 127 (suppl_12) ◽  
Author(s):  
Sanne A Peters ◽  
Karlijn A Groenewegen ◽  
Hester M den Ruijter ◽  
Michiel L Bots
Keyword(s):  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Disease Risk ◽  
Meta Analysis ◽  
Cardiovascular Disease Risk ◽  
Intima Media Thickness ◽  
Chronological Age ◽  
Specific Reference ◽  
Communication Tool ◽  
Vascular Age

Background Vascular age is the chronological age of an individual adjusted by their level of atherosclerosis. Vascular age can be used as understandable communication tool towards patients. It has been proposed that carotid intima-media thickness (CIMT) could be used to estimate the vascular age in individuals. The issue on how to best estimate vascular age remains an unanswered question and was evaluated in this study. Methods Data were used from the USE-IMT study collaboration, a global individual patient data meta-analysis including 14 population-based cohorts contributing data for 45 828 individuals. We used two methods to define vascular age. First, vascular age was the age at which a participant’s CIMT value would be at the 50th percentile of the age-and sex specific reference values of the healthy USE-IMT subpopulation (VA50). Second, vascular age was the age at which the estimated cardiovascular risk equals the risk of the observed CIMT value (VArisk). Results Mean (+/- standard deviation [SD]) chronological age, VA50, and VArisk were 58 (9), 63 (19), and 59 (7) years, respectively. VArisk was 0.24 yrs higher in women and 1.5 yrs higher in men than chronological age whereas VA50 was 4.4 yrs higher in women and 5.8 yrs higher in men than chronological age. After adjustment for traditional cardiovascular risk factors, a SD increase in VA50 and VArisk was associated with a 15% (95% confidence interval [CI]: 1.12; 1.19) and 22% (95% CI: 1.17; 1.28) higher risk of cardiovascular disease. For comparison, a SD increase in mean common CIMT increased the risk of cardiovascular disease with 15% (95% CI: 1.12; 1.19). Conclusion We presented two distinct measures a vascular age: VA50, and VArisk. VA50 is a straightforward translation of CIMT and is a measure of the age at which the average person would be expected to have a certain CIMT. In contrast, VArisk incorporates information about expected cardiovascular risk and is the chronological age of a person that conveys the same risk as the CIMT. VA50 and VArisk might provide a convenient transformation of CIMT to a scale that is more easily understood by patients and clinicians.

Thirty-year cardiovascular risk score in patients with newly diagnosed bipolar disorder and their unaffected first-degree relatives

2018 ◽  
Vol 53 (7) ◽  
pp. 651-662 ◽  
Author(s):  
Klara Coello ◽  
Hanne L Kjærstad ◽  
Sharleny Stanislaus ◽  
Sigurd Melbye ◽  
Maria Faurholt-Jepsen ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Bipolar Disorder ◽  
Cardiovascular Risk ◽  
Risk Score ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Newly Diagnosed ◽  
Healthy Individuals ◽  
First Degree Relatives ◽  
Age And Sex

Objectives: Bipolar disorder is associated with a decreased life expectancy of 8–12 years. Cardiovascular disease is the leading cause of excess mortality. For the first time, we investigated the Framingham 30-year risk score of cardiovascular disease in patients with newly diagnosed/first-episode bipolar disorder, their unaffected first-degree relatives and healthy individuals. Methods: In a cross-sectional study, we compared the Framingham 30-year risk score of cardiovascular disease in 221 patients with newly diagnosed/first-episode bipolar disorder, 50 of their unaffected first-degree relatives and 119 healthy age- and sex-matched individuals with no personal or first-degree family history of affective disorder. Among patients with bipolar disorder, we further investigated medication- and illness-related variables associated with cardiovascular risk. Results: The 30-year risk of cardiovascular disease was 98.5% higher in patients with bipolar disorder ( p = 0.017) and 85.4% higher in unaffected first-degree relatives ( p = 0.042) compared with healthy individuals in models adjusted for age and sex. When categorizing participants in low cardiovascular risk without considering age and sex distribution among participants, 81% of patients were at low risk, versus 92% of unaffected relatives and 89% of healthy individuals. Of the patients 209 (94.6%) were diagnosed within the preceding 2 years. Smoking was more prevalent among patients with bipolar disorder (45.2%) and their unaffected first-degree relatives (20.4%) compared with healthy individuals (12.8%). Similarly, dyslipidemia was more common among patients with bipolar disorder compared with healthy individuals. Treatment with psychotropic medication with metabolic adverse effects was associated with higher 30-year cardiovascular disease risk score, whereas we did not find illness-related variables associated with cardiovascular risk among patients with bipolar disorder. Conclusion: We found an enhanced cardiovascular disease risk score in patients with newly diagnosed bipolar disorder and their unaffected first-degree relatives, which points to a need for specific primary preventive interventions against smoking and dyslipidemia in these populations.

scholarly journals Habitual physical activity is not associated with lower cardiovascular risk profile or higher aerobic fitness

2020 ◽  
pp. 1-6
Author(s):  
Denis Fabrício Valério ◽  
Arthur Fernandes Gáspari ◽  
Giovana Vergínea de Souza ◽  
Cleiton Augusto Libardi ◽  
Claudia Regina Cavaglieri ◽  
...  
Keyword(s):  
Physical Activity ◽  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Aerobic Fitness ◽  
Physical Inactivity ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Risk Profile ◽  
Cardiovascular Risk Profile ◽  
Vo2 Max

Introduction: Physical inactivity is considered as one of the factors to increase the risk of developing cardiovascular diseases (CVDs) and decrease aerobic fitness mainly in middle-age. Increased habitual physical activity (HPA) is one of the strategies recommended to reduce physical inactivity. However, it is not known whether middle-age individuals who exclusively perform greater amount of HPA have greater aerobic fitness and / or a lower risk of CVDs. Objective: Verify the association between HPA with the risk of CVDs and aerobic fitness in individuals who only perform HPA. Method: We selected 89 male volunteers, age: 47.4 ± 5.06 years, who did not practice systemized physical training. Our measurements were: HPA by the International Physical Activity Questionnaire and Baecke questionnaires, the aerobic fitness by direct assessment of maximal oxygen consumption (VO2 máx) and the risk of developing cardiovascular disease by the score calculation of General Cardiovascular Risk Profile from Framingham Study. Results: There was no correlation of the HPA level with cardiovascular risk factors, general cardiovascular disease risk and VO2 máx. Moreover, no difference was found between the categorical groups of the IPAQ questionnaire and between the groups, “clusters”, calculated from the Baecke questionnaire scores for the variables of cardiovascular risk, general cardiovascular disease risk and VO2 máx. Conclusion: This study have found that the HPA level of middle-aged men is not associated with lower cardiovascular risk profile or higher aerobic fitness, suggesting that only increase HPA may not be enough to promote beneficial adaptations in aerobic fitness and improve risk profile for CVDs. These results may be related to low volume and intensity of HPA, which reinforces the importance of performing physical training with control of these variables for health promotion.

scholarly journals Impact of Elevated Cystatin C Level on Cardiovascular Disease Risk in Predominantly High Cardiovascular Risk Populations

2010 ◽  
Vol 3 (6) ◽  
pp. 675-683 ◽  
Author(s):  
Meng Lee ◽  
Jeffrey L. Saver ◽  
Wen-Hung Huang ◽  
Jessica Chow ◽  
Kuo-Hsuan Chang ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Cystatin C ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
High Cardiovascular Risk

scholarly journals Metabolic syndrome in Xinjiang Kazakhs and construction of a risk prediction model for cardiovascular disease risk

PLoS ONE ◽  
2018 ◽  
Vol 13 (9) ◽  
pp. e0202665 ◽  
Author(s):  
Lei Mao ◽  
Jia He ◽  
Xiang Gao ◽  
Heng Guo ◽  
Kui Wang ◽  
...  
Keyword(s):  
Cardiovascular Disease ◽  
Metabolic Syndrome ◽  
Prediction Model ◽  
Risk Prediction ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Risk Prediction Model

scholarly journals Prediction of novel mouse TLR9 agonists using a random forest approach

2019 ◽  
Vol 20 (S2) ◽  
Author(s):  
Varun Khanna ◽  
Lei Li ◽  
Johnson Fung ◽  
Shoba Ranganathan ◽  
Nikolai Petrovsky
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Correlation Coefficient ◽  
Matthews Correlation Coefficient ◽  
Learning Algorithms ◽  
Ensemble Classifier ◽  
Innate Immune ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Random Forest Algorithm

Abstract Background Toll-like receptor 9 is a key innate immune receptor involved in detecting infectious diseases and cancer. TLR9 activates the innate immune system following the recognition of single-stranded DNA oligonucleotides (ODN) containing unmethylated cytosine-guanine (CpG) motifs. Due to the considerable number of rotatable bonds in ODNs, high-throughput in silico screening for potential TLR9 activity via traditional structure-based virtual screening approaches of CpG ODNs is challenging. In the current study, we present a machine learning based method for predicting novel mouse TLR9 (mTLR9) agonists based on features including count and position of motifs, the distance between the motifs and graphically derived features such as the radius of gyration and moment of Inertia. We employed an in-house experimentally validated dataset of 396 single-stranded synthetic ODNs, to compare the results of five machine learning algorithms. Since the dataset was highly imbalanced, we used an ensemble learning approach based on repeated random down-sampling. Results Using in-house experimental TLR9 activity data we found that random forest algorithm outperformed other algorithms for our dataset for TLR9 activity prediction. Therefore, we developed a cross-validated ensemble classifier of 20 random forest models. The average Matthews correlation coefficient and balanced accuracy of our ensemble classifier in test samples was 0.61 and 80.0%, respectively, with the maximum balanced accuracy and Matthews correlation coefficient of 87.0% and 0.75, respectively. We confirmed common sequence motifs including ‘CC’, ‘GG’,‘AG’, ‘CCCG’ and ‘CGGC’ were overrepresented in mTLR9 agonists. Predictions on 6000 randomly generated ODNs were ranked and the top 100 ODNs were synthesized and experimentally tested for activity in a mTLR9 reporter cell assay, with 91 of the 100 selected ODNs showing high activity, confirming the accuracy of the model in predicting mTLR9 activity. Conclusion We combined repeated random down-sampling with random forest to overcome the class imbalance problem and achieved promising results. Overall, we showed that the random forest algorithm outperformed other machine learning algorithms including support vector machines, shrinkage discriminant analysis, gradient boosting machine and neural networks. Due to its predictive performance and simplicity, the random forest technique is a useful method for prediction of mTLR9 ODN agonists.

scholarly journals Novel Cardiovascular Biomarkers Associated with Increased Cardiovascular Risk in Women With Prior Preeclampsia/HELLP Syndrome: A Narrative Review

2021 ◽  
Vol 16 ◽  
Author(s):  
Esmee ME Bovee ◽  
Martha Gulati ◽  
Angela HEM Maas
Keyword(s):  
Cardiovascular Disease ◽  
Cardiovascular Risk ◽  
Hellp Syndrome ◽  
Troponin I ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Narrative Review ◽  
Elevated Liver Enzymes ◽  
Increased Risk ◽  
Cardiovascular Biomarkers

Evidence has shown that women with a history of preeclampsia or haemolysis, elevated liver enzymes and low platelets (HELLP) syndrome have an increased risk of cardiovascular disease later in life. Recommendations for screening, prevention and management after such pregnancies are not yet defined. The identification of promising non-traditional cardiovascular biomarkers might be useful to predict which women are at greatest risk. Many studies are inconsistent and an overview of the most promising biomarkers is currently lacking. This narrative review provides an update of the current literature on circulating cardiovascular biomarkers that may be associated with an increased cardiovascular disease risk in women after previous preeclampsia/HELLP syndrome. Fifty-six studies on 53 biomarkers were included. From the summary of evidence, soluble fms-like tyrosine kinase-1, placental growth factor, interleukin (IL)-6, IL-6/IL-10 ratio, high-sensitivity cardiac troponin I, activin A, soluble human leukocyte antigen G, pregnancy-associated plasma protein A and norepinephrine show potential and are interesting candidate biomarkers to further explore. These biomarkers might be potentially eligible for cardiovascular risk stratification after preeclampsia/HELLP syndrome and may contribute to the development of adequate strategies for prevention of hypertension and adverse events in this population.

Sign in / Sign up

Export Citation Format

Share Document