Framingham risk scores for determination the 10-year risk of cardiovascular disease in participants with and without the metabolic syndrome: results of the Fasa Persian cohort study.

BACKGROUND: Metabolic syndrome (MetS) is a cluster of risk factors and the Framingham risk score (FRS) is a useful metric for measuring the 10-year cardiovascular disease (CVD) risk of the population. The present study aimed to determine the 10-year risk of cardiovascular disease using the Framingham risk score in people with and without MetS in a large Iranian cohort study. METHODS: This cross-sectional study was done using the Fasa cohort. Participants aged ≥ 35 years old were recruited to the study from 2015 to 2016. The FRS was calculated using age, sex, current smoking, diabetes, systolic blood pressure (SBP), total cholesterol, and high-density lipoprotein (HDL) cholesterol. MetS was defined as the presence of three or more of the MetS risk factors including triglyceride (TG) level ≥ 150 mg dl- 1, HDL level < 40 mg dl- 1 in men and < 50 mg dl- 1 in women, systolic/diastolic blood pressure ≥ 130/≥85 mmHg or using medicine for hypertension, fasting blood sugar (FBS) level ≥ 100 mg dl- 1 or using diabetes medication and abdominal obesity considered as waist circumference (WC) ≥ 88 cm for women and ≥ 102 cm for men. Multiple logistic regressions were applied to estimate the 10- year CVD risk among people with and without MetS. RESULTS: Of 8949 participants, 1928 people (21.6%) had MetS. The mean age of the participants with and without Mets was 50.4 ± 9.2 years and 46.9 ± 9.1 years respectively. In total 15.3% of participants with MetS and 8.0% of participants without MetS were in the high-risk category of 10-year CVD risk. Among participants with MetS gender, TG, SBP, FBS and in people without MetS gender, TG, SBP, FBS, and HDL showed strong associations with the predicted 10-year CVD risk. CONCLUSION: Male sex and increased SBP, TG, and FBS parameters were strongly associated with increased 10-year risk of CVD in people with and without MetS. In people without MetS, reduced HDL-cholestrol was strongly associated with increased 10-year risk of CVD. The recognition of participant's TG, blood pressure (BP), FBS and planning appropriate lifestyle interventions related to these characteristics is an important step towards prevention of CVD.

Association between dietary magnesium and 10-year risk of a first hard atherosclerotic cardiovascular disease event.

BACKGROUND: To test whether dietary magnesium is associated with 10-year risk of a first hard atherosclerotic cardiovascular disease event. METHODS: In this cross-sectional study, a total of 2980 participants, aged 40 to 79 years, from the National Health and Nutrition Examination Survey 1999-2018 were analyzed. The association between dietary magnesium and 10-year risk of a first hard atherosclerotic cardiovascular disease (ASCVD) event was assessed following adjustment for clinical risk factors, including sex, age, race, educational level, body mass index (BMI), alcohol drinking, smoking, systolic blood pressure (SBP), diastolic blood pressure (DBP), hypertension treated or not, diabetes and low density lipoprotein cholesterol (LDL-C), total energy and dietary fiber. We performed multivariate linear regression models and smooth curve fittings to evaluate the associations between dietary magnesium and 10-year risk of a first hard atherosclerotic cardiovascular disease event. RESULTS: We observed a significant inverse association between dietary magnesium and predicted 10-year risk of a first hard atherosclerotic cardiovascular disease event (ß=-0.01, [95% CI: -0.01, -0.00], P = 0.0256). We divided the 10-year risk into two categories, with a statistically significant reduction of ASCVD risk when the 10-year risk ≥7.5% (ß=-0.01, [95% CI: -0.01, -0.00], P = 0.0440). CONCLUSIONS: Dietary magnesium intake was inversely associated with the predicted 10-year risk of a first hard atherosclerotic cardiovascular disease event.

Dietary Saturated, Monounsaturated, or Polyunsaturated Fatty Acids and Estimated 10-Year Risk of a First Hard Cardiovascular Event.

BACKGROUND: The effects of dietary saturated, monounsaturated, or polyunsaturated fatty acids on the risk of cardiovascular events remain controversial. METHODS: This cross-sectional study was performed in 4211 patients, aged 40 to 79 years, from the National Health and Nutrition Examination Survey between 1999 and 2018. The independent variables were saturated fatty acids, monounsaturated fatty acids, and polyunsaturated fatty acids. The dependent variable was the 10-year risk of a first hard atherosclerotic cardiovascular event. The other variables were considered as the potential confounding factors. Multivariate linear regression models and smooth curve fittings were used to evaluate the association between saturated fatty acids, polyunsaturated fatty acids, or monounsaturated fatty acids and the 10-year risk. RESULTS: There was no association between dietary saturated fatty acids and 10-year risk after adjusting for all the potential confounding factors; 10-year risk decreased by 0.022% each 1-g increase in monounsaturated fatty acids intake from 0 to 153.772 g, and 0.025% each 1-g increase in polyunsaturated fatty acids intake from 0 to 98.323 g, respectively. Moreover, subgroup analysis showed that monounsaturated fatty acids and polyunsaturated fatty acids were both negatively correlated to 10-year risk in nondiabetes and non-high-low-density lipoprotein patients; monounsaturated fatty acids were also negatively associated with 10-year risk in hypertensive patients. CONCLUSIONS: There was no association between dietary saturated fatty acids and 10-year risk. Increased dietary intake of monounsaturated fatty acids or polyunsaturated fatty acids decreased 10-year risk, particularly in nondiabetes, non-high-low density lipoprotein patients.

Associations of risk factor burden and genetic predisposition with the 10-year risk of atrial fibrillation: observations from a large prospective study of 348,904 participants.

BACKGROUND: Understanding the effects of risk factor burden and genetic predisposition on the long-term risk of atrial fibrillation (AF) is important to improve public health initiatives. However, the 10-year risk of AF considering risk factor burden and genetic predisposition is unknown. METHODS: A total of 348,904 genetically unrelated participants without AF at baseline from the UK were categorized into three groups: index ages 45 years (n = 84,206), 55 years (n=117,520), and 65 years (n=147,178). Optimal, borderline, or elevated risk factor burden was determined by body mass index, blood pressure, diabetes mellitus, alcohol consumption, smoking status, and history of myocardial infarction or heart failure. Genetic predisposition was estimated using the polygenic risk score (PRS), constructed using 165 predefined genetic risk variants. The combined effects of risk factor burden and PRS on the risk of incident AF in 10 years were estimated for each index age. Fine and Gray models were developed to predict the 10-year risk of AF. RESULTS: The overall 10-year risk of AF was 0.67% (95% CI: 0.61-0.73%) for index age 45 years, 2.05% (95% CI: 1.96-2.13%) for index age 55 years, and 6.34% (95% CI: 6.21-6.46%) for index age 65 years, respectively. An optimal risk factor burden was associated with later AF onset regardless of genetic predisposition and sex (P < 0.001). Significant synergistic interactions were observed for risk factor burden with PRS at each index age (P < 0.05). Participants with an elevated risk factor burden and high PRS had the highest 10-year risk of AF in reference to those who had both an optimal risk factor burden and a low PRS. At younger ages, optimal risk burden and high PRS might also lead to later onset of AF, compared to the joint effect of elevated risk burden and low/intermediate PRS. CONCLUSIONS: Risk factor burden together with a genetic predisposition is associated with the 10-year risk of AF. Our results may be helpful in selecting high-risk individuals for primary prevention of AF and facilitating subsequent health interventions.

The associations between uric acid with BMDs and risk of the 10-year probability of fractures in Chinese patients with T2DM stratified by age and gender.

PURPOSE: Accumulating evidence suggests that serum uric acid (SUA) plays a beneficial role in bone health in the general population through antioxidant mechanisms. However, there is controversy over the association between SUA and bone in patients with type 2 diabetes mellitus (T2DM). We aimed to investigate the association of serum UA with BMDs and future fracture risks and its potential influencing factors in those patients. METHOD: This was a cross-sectional study of 485 patients. BMDs at femoral neck (FN), Troch and the lumbar spine (LS) were measured by DXA. The 10-year probability of fracture risk was assessed using the fracture risk assessment tool (FRAX). SUA level and other biochemical indexes were measured. RESULTS: There were lower SUA concentrations in patients with osteoporosis/osteopenia compared with those in the normal group, which only existed in non-elderly men and elderly women with T2DM. After adjustment for potential confounders, SUA was positively associated with BMD and negatively with 10-year probability of fracture risk only in non-elderly men and elderly women with T2DM. Multiple stepwise regression analysis showed that SUA was an independent determinant of BMD and 10-year probability of fracture risk, which also occurred in the above patients. CONCLUSION: These results implied that relatively high SUA is a protective factor for bone in T2DM patients, but the osteoprotective effect of SUA was mediated by age and gender, and persisted only in non-elderly men and elderly women. Large intervention studies are needed to further confirm the outcomes and provide possible explanations.

Cardiovascular (Framingham) and type II diabetes (Finnish Diabetes) risk scores: a qualitative study of local knowledge of diet, physical activity and body measurements in rural Rakai, Uganda.

BACKGROUND: Non-communicable diseases such as cardiovascular conditions and diabetes are rising in sub-Saharan Africa. Prevention strategies to mitigate non-communicable diseases include improving diet, physical activity, early diagnosis, and long-term management. Early identification of individuals at risk based on risk-score models - such as the Framingham Risk Score (FRS) for 10-year risk of cardiovascular disease and the Finnish type 2 Diabetes risk score (FINDRISC) for type 2 diabetes which are used in high-income settings - have not been well assessed in sub-Saharan Africa. The purpose of this study was to qualitatively assess local knowledge of components of these risk scores in a rural Ugandan setting. METHODS: Semi-structured qualitative in-depth interviews were conducted with a purposively selected sample of 15 participants who had responded to the FRS and FINDRISC questionnaires and procedures embedded in the Rakai Community Cohort Study. Data were summarized and categorized using content analysis, with support of Atlas.ti. RESULTS: Participants described local terms for hypertension ("pulessa") and type 2 diabetes ("sukaali"). Most participants understood physical activity as leisure physical activity, but when probed would also include physical activity linked to routine farm work. Vegetables were typically described as "plants", "leafy greens", and "side dish". Vegetable and fruit consumption was described as varying seasonally, with peak availability in December after the rainy season. Participants perceived themselves to have good knowledge about their family members' history of type 2 diabetes and hypertension. CONCLUSIONS: While most items of the FRS and FINDRISC were generally well understood, physical activity needs further clarification. It is important to consider the seasonality of fruits and vegetables, especially in rural resource-poor settings. Current risk scores will need to be locally adapted to estimate the 10-year risk of cardiovascular diseases and type 2 diabetes in this setting.

Association between plaque localization in proximal coronary segments and MACE outcomes in patients with mild CAC: Results from the EISNER study.

Objective: Coronary artery calcium score (CAC) is a validated tool to predict and reclassify cardiovascular risk. Additional metrics such as regional distribution and extent of CAC over Agatston CAC score may allow further risk stratification. In this study, we evaluate the prognostic significance of proximal CAC involvement in asymptomatic population from the prospective EISNER (Early-Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) registry, focusing on patients with mild CAC (score 1-99). Methods: This study included a total of 2,047 adult asymptomatic subject who underwent baseline CAC scan and 14-year follow-up for MACE, defined as myocardial infarction, late revascularization, or cardiac death. Proximal involvement was defined as presence of CAC in the LM, proximal LAD, LCX or RCA. CAC was categorized as 0, 1-99, and ≥100. Results: 1,090 (53.2%) subjects had no CAC, 576 (28.1%) had CAC 1-99, and 381 (18.7%) had CAC ≥100. Proximal involvement was seen in 67.2% of subjects with CAC 1-99 and 97.3% of subjects with CAC ≥100. In the CAC 1-99 category, the presence of proximal CAC was associated with increased MACE risk after adjustment for CAC score, CAC extent and conventional risk factors compared to those without proximal CAC (HR: 2.84 95% CI: 1.29-6.25, p=0.009). Conclusion: In asymptomatic subjects with CAC scores of 1-99, the presence and extent of proximal CAC plaques provides strong independent prognostic information in predicting MACE.

The Association Between Remnant Cholesterol and the Estimated 10-Year Risk of a First Hard Cardiovascular Event.

Background: Remnant cholesterol (Remnant-C), rather than TG, is believed to increase the risk of atherosclerotic cardiovascular disease. We evaluated whether Remnant-C is associated with an estimated 10-year risk of a first hard atherosclerotic cardiovascular disease event. Methods: This cross-sectional study was performed on 2,048 participants (1,130 men and 918 women), aged 40 to 79 years, from the National Health and Nutrition Examination Survey (NHANES) between 1999 and 2018. The independent variable was Remnant-C; the dependent variable was the 10-year risk of a first hard atherosclerotic cardiovascular disease event (defined as non-fatal myocardial infarction, coronary heart disease death, or stroke, over a 10-year period among people free from atherosclerotic cardiovascular disease at the beginning of the period). The other variables, such as smoking behavior, hypertension, diabetes etc., were considered as the potential effect modifiers. Multivariate linear regression models and smooth curve fittings were used to evaluate the association between Remnant-C and the 10-year risk of a first hard atherosclerotic cardiovascular disease event. Subgroup analyses stratified by gender and race were also performed. Results: A positive association between Remnant-C and the 10-year risk of a first hard atherosclerotic cardiovascular disease event was demonstrated in the fully adjusted model (ß = 0.078, [95%CI: 0.061-0.094], P < 0.001). The 10-year risk was increased by 0.078% for each 1 mg/dl increase in Remnant-C. In the subgroup analysis for gender, this association remained in both men (ß = 0.128, [95%CI: 0.108-0.148], P < 0.001) and women (ß = 0.043, [95%CI: 0.016-0.070], P = 0.00179). However, in the subgroup analysis for race, the association between Remnant-C and the 10-year risk reached an inflection point at remnant-C 38 mg/dL, where a positive association was not as obvious for the non-Hispanic Black population as for other racial groups. Conclusions: Remnant-C positively correlates with a 10-year risk of a first hard atherosclerotic cardiovascular disease event.

Association between dietary fiber intake and atherosclerotic cardiovascular disease risk in adults: a cross-sectional study of 14,947 population based on the National Health and Nutrition Examination Surveys.

BACKGROUND: This study aimed to investigate the association between dietary fiber intake and long-term cardiovascular disease (CVD) risk based on the National Health and Nutrition Examination Survey (NHANES) database. METHODS: A total of 14,947 participants aged 20-79 from the NHANES database were included in this study between 2009 and 2018. The atherosclerotic cardiovascular disease (ASCVD) score was utilized to predict the 10-year risk of CVD in individuals (low, borderline, intermediate, and high risk). Weighted univariate and multinomial multivariate logistic regression analyses were used to analyze the association between dietary fiber intake and long-term CVD risk. RESULTS: Higher dietary fiber density may be associated with a reduced ASCVD risk in participants with intermediate risk [odds ratio (OR) = 0.76; 95% confidence interval (CI), 0.61-0.94] and high risk (OR = 0.60; 95%CI, 0.45-0.81) compared with those in the group with low risk. Higher total dietary fiber intake may also reduce ASCVD risk in participants with high risk (OR = 0.84; 95%CI, 0.75-0.95). Subgroup analyses showed that higher dietary fiber density may be related to reduced ASCVD risk in intermediate-risk participants aged 20-39 (OR = 0.62; 95%CI, 0.43-0.89) and 40-59 (OR = 0.67; 95%CI, 0.49-0.94). In high-risk participants, higher dietary fiber density may reduce ASCVD risk in 20-39-year-old (OR = 0.38; 95%CI, 0.19-0.77), 40-59-year-old (OR = 0.37; 95%CI, 0.20-0.70), male (OR = 0.47; 95%CI, 0.23-0.97) and female (OR = 0.57; 95%CI, 0.38-0.86) participants. CONCLUSION: Higher dietary fiber density and total dietary fiber intake were associated with a lower long-term CVD risk, especially in the 20-39 and 40-59 age groups, where the reduction was most significant.

Cardiovascular Risk Prediction by the American Diabetes Association Risk-Assessment Tool and Novel and Traditional Cardiovascular Risk Factors in Young Adults With Type 1 Diabetes.

INTRODUCTION: Cardiovascular disease is an important cause of morbidity and mortality in individuals with type 1 diabetes (T1D). The American Diabetes Association (ADA) has the ADA risk-assessment tool for cardiovascular risk (CVR) prediction in individuals with T1D. This study aims to evaluate the prevalence of novel and traditional cardiovascular risk factors (CVRF) and the CVR by the ADA risk-assessment tool: 10-year risk for diabetes complications in young adults with T1D. METHODS: Cross-sectional observational study of T1D individuals aged 18-40 years and T1D duration ≥1 year. The ADA risk-assessment tool was applied to predict CVR. RESULTS: 75 individuals, 61.3% male, with a median age of 30 (26.0-36.0) and 13.0 (6.0-20.0) years of T1D duration. Hypertension was found in 16% of individuals and dyslipidemia in 75.0%. 21.3% were active smokers, 30.7% sedentary, and 42.7% were at least overweight. Most individuals had a 10-year risk <1% for all complications except myocardial infarction (MI). In individuals who were outside the honeymoon period (T1D duration ≥ 5 years), most had a 10-year risk <1% for all complications except MI and amputation. Non-traditional CVRF homocysteine, apolipoprotein B, apolipoprotein B/apolipoprotein A1 ratio, magnesium, and vitamin D correlated with the ADA risk-assessment tool. 10-year risk for MI ≥1% was significantly more frequent in men. CONCLUSION: To our knowledge, this is the first study to apply the ADA risk-assessment tool: 10-year risk for diabetes complications in T1D. Young adults with T1D have a worrying prevalence of CVRF and show suboptimal control. Most individuals with T1D duration ≥1 year have an estimated 10-year risk <1% for all complications, except for MI.

Serum Level of Lactate Dehydrogenase is Associated with Cardiovascular Disease Risk as Determined by the Framingham Risk Score and Arterial Stiffness in a Health-Examined Population in China.

INTRODUCTION: Lactate dehydrogenase (LDH) is an important oxidoreductase in the anaerobic metabolic pathway. The role of LDH in arterial stiffness (AS) and 10-year cardiovascular disease (CVD10) risk has not been established. METHODS: This retrospective, cross-sectional, and observational study evaluated the relationships between the LDH level and AS and CVD10 risk in 12,597 health-examined people (6988 men and 5609 women; mean age, 49.49 years) in China. Brachial-ankle pulse wave velocity (baPWV) was used to estimate AS. The Framingham CVD 10-year risk prediction model was used to calculate the CVD10 risk score. RESULTS: In both sexes, an increased LDH level was associated with increased AS and CVD10 (men: ß = 0.032, P < 0.001; women: ß = 0.025, P < 0.001). Half of the population with a high LDH level ( ≥ 172 U/L) showed significantly increased AS and CVD10 risk score. Men and women with baPWV ≥1400 cm/s had a higher LDH level, and the latter was significantly different from that of the group with baPWV <1400 cm/s (men: 176.93±30.99 vs 173.00±33.36, P < 0.001; women: 189.10±34.20 vs 171.39±31.08, P < 0.001). In both sexes, a higher level of LDH was noted in groups with higher CVD10 risk score (men: 176.65±32.51 vs 172.94±32.46, P < 0.001; women: 202.51±44.05 vs 175.73±32.39, P < 0.001). DISCUSSION: An increased LDH level may be associated with AS and CVD10 risk. The LDH level could be a new predictor of AS and CVD10 risk in health-examined populations.

Triglyceride-glucose index and estimated 10-year risk of a first hard cardiovascular event.

Background: Whether Triglyceride-glucose (TyG) index is associated with 10-year risk of a first hard atherosclerotic cardiovascular disease (ASCVD) event in the United States remains unclear. Methods: In this cross-sectional study, the participants, ranged from 40 to 79 years old, were from the National Health and Nutrition Examination Survey (NHANES) between 1999 and 2018. TyG index was the independent variable and 10-year risk of a first hard ASCVD was the dependent variable. The other variables, such as age, gender, race, body mass index (BMI), hypertension treatment states, smoking states and low-density lipoprotein cholesterol (LDL-C) et al. were considered as the potential confounding factors. Multivariate linear regression models and smooth curve fittings were used to evaluate the association between TyG index and 10-year risk of a first hard ASCVD event. Results: A total of 2,142 participants were included in the analysis. The results showed that TyG index was associated with an increased 10-year risk of a first hard ASCVD event [ß = 2.208, 95% (1.716, 2.700), P < 0.00001]. The association had statistical significance in both men [ß = 3.862 95% CI (3.274, 4.450), P < 0.00001] and women [ß = 1.067, 95% CI (0.286, 1.849), P = 0.00756)] according to subgroup analysis. Smooth curve fittings revealed that TyG index was linearly associated with 10-year risk of ASCVD in both male and female. Conclusion: Triglyceride-glucose index was associated with an increased 10-year risk of a first hard ASCVD event in the United States, suggesting it is necessary to monitor and control an appropriate range of TyG index.

Cardiovascular Risk Awareness and Calculated 10-Year Risk Among Female Employees at Taibah University 2019.

Cardiovascular diseases (CVD) are the most common cause of death and disability worldwide. Saudi Arabia, one of the middle-income countries has a proportional CVD mortality rate of 37%. Knowledge about CVD and its modifiable risk factors is a vital pre-requisite to change the health attitudes, behaviors, and lifestyle practices of individuals. Therefore, we intended to assess the employee knowledge about risk of CVD, symptoms of heart attacks, and stroke, and to calculate their future 10-years CVD risk. An epidemiological, cross-sectional, community-facility based study was conducted. The women aged ≥40 years who are employees of Taibah University, Al-Madinah Al-Munawarah were recruited. A screening self-administrative questionnaire was distributed to the women to exclude those who are not eligible. In total, 222 women met the inclusion criteria and were invited for the next step for the determination of CVD risk factors by using WHO STEPS questionnaire: It is used for the surveillance of non-communicable disease risk factor, such as CVD. In addition, the anthropometric measurements and biochemical measurements were done. Based on the identified atherosclerotic cardiovascular disease (ASCVD) risk factors and laboratory testing results, risk calculated used the Framingham Study Cardiovascular Disease (10-year) Risk Assessment. Data were analyzed using GraphPad Prism 7 software (GraphPad Software, CA, USA). The result showed the mean age of study sample was 55.6 ± 9.0 years. There was elevated percentage of obesity and rise in abdominal circumference among the women. Hypertension (HTN) was a considerable chronic disease among the participants where more than half of the sample had it, i.e., 53%. According to the ASCVD risk estimator, the study participants were distributed into four groups: 63.1% at low risk, 20.2% at borderline risk, 13.5% at intermediate risk, and 3.2% at high risk. A comparison between these categories based on the CVD 10-year risk estimator indicated that there were significant variations between the low-risk group and the intermediate and high-risk groups (P = 0.02 and P = 0.001, respectively). The multivariate analysis detected factors related to CVD risk for women who have an intermediate or high risk of CVD, such as age, smoking, body mass index (BMI), unhealthy diet, blood pressure (BP) measurements, and family history of CVD (P < 0.05). The present study reports limited knowledge and awareness of CVD was 8.6 that is considered as low knowledge. In conclusion, the present study among the university sample in Madinah reported limited knowledge and awareness of CVD risk. These findings support the need for an educational program to enhance the awareness of risk factors and prevention of CVD.

Artificial intelligence framework for predictive cardiovascular and stroke risk assessment models: A narrative review of integrated approaches using carotid ultrasound.

RECENT FINDINGS: Cardiovascular disease (CVD) is the leading cause of mortality and poses challenges for healthcare providers globally. Risk-based approaches for the management of CVD are becoming popular for recommending treatment plans for asymptomatic individuals. Several conventional predictive CVD risk models based do not provide an accurate CVD risk assessment for patients with different baseline risk profiles. Artificial intelligence (AI) algorithms have changed the landscape of CVD risk assessment and demonstrated a better performance when compared against conventional models, mainly due to its ability to handle the input nonlinear variations. Further, it has the flexibility to add risk factors derived from medical imaging modalities that image the morphology of the plaque. The integration of noninvasive carotid ultrasound image-based phenotypes with conventional risk factors in the AI framework has further provided stronger power for CVD risk prediction, so-called "integrated predictive CVD risk models." PURPOSE: of the review: The objective of this review is (i) to understand several aspects in the development of predictive CVD risk models, (ii) to explore current conventional predictive risk models and their successes and challenges, and (iii) to refine the search for predictive CVD risk models using noninvasive carotid ultrasound as an exemplar in the artificial intelligence-based framework. CONCLUSION: Conventional predictive CVD risk models are suboptimal and could be improved. This review examines the potential to include more noninvasive image-based phenotypes in the CVD risk assessment using powerful AI-based strategies.

Cardiovascular/stroke risk predictive calculators: a comparison between statistical and machine learning models.

BACKGROUND: Statistically derived cardiovascular risk calculators (CVRC) that use conventional risk factors, generally underestimate or overestimate the risk of cardiovascular disease (CVD) or stroke events primarily due to lack of integration of plaque burden. This study investigates the role of machine learning (ML)-based CVD/stroke risk calculators (CVRCML) and compares against statistically derived CVRC (CVRCStat) based on (I) conventional factors or (II) combined conventional with plaque burden (integrated factors). METHODS: The proposed study is divided into 3 parts: (I) statistical calculator: initially, the 10-year CVD/stroke risk was computed using 13 types of CVRCStat (without and with plaque burden) and binary risk stratification of the patients was performed using the predefined thresholds and risk classes; (II) ML calculator: using the same risk factors (without and with plaque burden), as adopted in 13 different CVRCStat, the patients were again risk-stratified using CVRCML based on support vector machine (SVM) and finally; (III) both types of calculators were evaluated using AUC based on ROC analysis, which was computed using combination of predicted class and endpoint equivalent to CVD/stroke events. RESULTS: An Institutional Review Board approved 202 patients (156 males and 46 females) of Japanese ethnicity were recruited for this study with a mean age of 69±11 years. The AUC for 13 different types of CVRCStat calculators were: AECRS2.0 (AUC 0.83, P<0.001), QRISK3 (AUC 0.72, P<0.001), WHO (AUC 0.70, P<0.001), ASCVD (AUC 0.67, P<0.001), FRScardio (AUC 0.67, P<0.01), FRSstroke (AUC 0.64, P<0.001), MSRC (AUC 0.63, P=0.03), UKPDS56 (AUC 0.63, P<0.001), NIPPON (AUC 0.63, P<0.001), PROCAM (AUC 0.59, P<0.001), RRS (AUC 0.57, P<0.001), UKPDS60 (AUC 0.53, P<0.001), and SCORE (AUC 0.45, P<0.001), while the AUC for the CVRCML with integrated risk factors (AUC 0.88, P<0.001), a 42% increase in performance. The overall risk-stratification accuracy for the CVRCML with integrated risk factors was 92.52% which was higher compared all the other CVRCStat. CONCLUSIONS: ML-based CVD/stroke risk calculator provided a higher predictive ability of 10-year CVD/stroke compared to the 13 different types of statistically derived risk calculators including integrated model AECRS 2.0.

HCV co-infection among people living with HIV Is associated with Higher fracture risk.

INTRODUCTION: The purpose of this study was to predict the 10-year risk of fracture among people living with HIV (PLWH) using FRAX™, and to determine the risk factors related to a high probability of fractures. METHODOLOGY: This study consisted of 288 subjects aged 40 years and above. The ten-year probability of major osteoporotic fractures (MOF) and hip fractures was assessed using the FRAX™ algorithm with bone mineral density (BMD) data. A logistic regression was used to determine risk factors related to a high probability of major osteoporotic fracture and hip fracture. RESULTS: The median 10-year probability of fracture was 3.7% (IQR 2.2-6.2) for MOF and 0.8% (IQR 0.3-2.5) for hip fractures. In addition to old age, previous fracture history, and low T-scores, HCV co-infection was associated with a higher risk of hip fractures in PLWH (AOR: 4.3, 95% CI: 1.29-14.33). Old age and low T-scores were also associated with a high probability of MOF. CONCLUSIONS: HCV co-infection among PLWH is associated with a higher risk of hip fracture. Sustained efforts in terms of pharmacologic and non-pharmacologic interventions in PLWH are necessary to prevent osteoporotic fractures, especially in those with HCV co-infections.

Does the Carotid Bulb Offer a Better 10-Year CVD/Stroke Risk Assessment Compared to the Common Carotid Artery? A 1516 Ultrasound Scan Study.

The objectives of this study are to (1) examine the "10-year cardiovascular risk" in the common carotid artery (CCA) versus carotid bulb using an integrated calculator called "AtheroEdge Composite Risk Score 2.0" (AECRS2.0) and (2) evaluate the performance of AECRS2.0 against "conventional cardiovascular risk calculators." These objectives are met by measuring (1) image-based phenotypes and AECRS2.0 score computation and (2) performance evaluation of AECRS2.0 against 12 conventional cardiovascular risk calculators. The Asian-Indian cohort (n = 379) with type 2 diabetes mellitus (T2DM), chronic kidney disease (CKD), or hypertension were retrospectively analyzed by acquiring the 1516 carotid ultrasound scans (mean age: 55 ± 10.1 years, 67% males, ∼92% with T2DM, ∼83% with CKD [stage 1-5], and 87.5% with hypertension [stage 1-2]). The carotid bulb showed a higher 10-year cardiovascular risk compared to the CCA by 18% (P < .0001). Patients with T2DM and/or CKD also followed a similar trend. The carotid bulb demonstrated a superior risk assessment compared to CCA in patients with T2DM and/or CKD by showing: (1) ∼13% better than CCA (0.93 vs 0.82, P = .0001) and (2) ∼29% better compared with 12 types of risk conventional calculators (0.93 vs 0.72, P = .06).

A low-cost machine learning-based cardiovascular/stroke risk assessment system: integration of conventional factors with image phenotypes.

BACKGROUND: Most cardiovascular (CV)/stroke risk calculators using the integration of carotid ultrasound image-based phenotypes (CUSIP) with conventional risk factors (CRF) have shown improved risk stratification compared with either method. However such approaches have not yet leveraged the potential of machine learning (ML). Most intelligent ML strategies use follow-ups for the endpoints but are costly and time-intensive. We introduce an integrated ML system using stenosis as an endpoint for training and determine whether such a system can lead to superior performance compared with the conventional ML system. METHODS: The ML-based algorithm consists of an offline and online system. The offline system extracts 47 features which comprised of 13 CRF and 34 CUSIP. Principal component analysis (PCA) was used to select the most significant features. These offline features were then trained using the event-equivalent gold standard (consisting of percentage stenosis) using a random forest (RF) classifier framework to generate training coefficients. The online system then transforms the PCA-based test features using offline trained coefficients to predict the risk labels on test subjects. The above ML system determines the area under the curve (AUC) using a 10-fold cross-validation paradigm. The above system so-called "AtheroRisk-Integrated" was compared against "AtheroRisk-Conventional", where only 13 CRF were considered in a feature set. RESULTS: Left and right common carotid arteries of 202 Japanese patients (Toho University, Japan) were retrospectively examined to obtain 395 ultrasound scans. AtheroRisk-Integrated system [AUC =0.80, P<0.0001, 95% confidence interval (CI): 0.77 to 0.84] showed an improvement of ~18% against AtheroRisk-Conventional ML (AUC =0.68, P<0.0001, 95% CI: 0.64 to 0.72). CONCLUSIONS: ML-based integrated model with the event-equivalent gold standard as percentage stenosis is powerful and offers low cost and high performance CV/stroke risk assessment.

Effect of carotid image-based phenotypes on cardiovascular risk calculator: AECRS1.0.

Today, the 10-year cardiovascular risk largely relies on conventional cardiovascular risk factors (CCVRFs) and suffers from the effect of atherosclerotic wall changes. In this study, we present a novel risk calculator AtheroEdge Composite Risk Score (AECRS1.0), designed by fusing CCVRF with ultrasound image-based phenotypes. Ten-year risk was computed using the Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study 56 (UKPDS56), UKPDS60, Reynolds Risk Score (RRS), and pooled composite risk (PCR) score. AECRS1.0 was computed by measuring the 10-year five carotid phenotypes such as IMT (ave., max., min.), IMT variability, and total plaque area (TPA) by fusing eight CCVRFs and then compositing them. AECRS1.0 was then benchmarked against the five conventional cardiovascular risk calculators by computing the receiver operating characteristics (ROC) and area under curve (AUC) values with a 95% CI. Two hundred four IRB-approved Japanese patients' left/right common carotid arteries (407 ultrasound scans) were collected with a mean age of 69 ± 11 years. The calculators gave the following AUC: FRS, 0.615; UKPDS56, 0.576; UKPDS60, 0.580; RRS, 0.590; PCRS, 0.613; and AECRS1.0, 0.990. When fusing CCVRF, TPA reported the highest AUC of 0.81. The patients were risk-stratified into low, moderate, and high risk using the standardized thresholds. The AECRS1.0 demonstrated the best performance on a Japanese diabetes cohort when compared with five conventional calculators. Graphical abstract AECRS1.0: Carotid ultrasound image phenotype-based 10-year cardiovascular risk calculator. The figure provides brief overview of the proposed carotid image phenotype-based 10-year cardiovascular risk calculator called AECRS1.0. AECRS1.0 was also benchmarked against five conventional cardiovascular risk calculators (Framingham Risk Score (FRS), United Kingdom Prospective Diabetes Study 56 (UKPDS56), UKPDS60, Reynolds Risk Score (RRS), and pooled composite risk (PCR) score).

Nonlinear model for the carotid artery disease 10-year risk prediction by fusing conventional cardiovascular factors to carotid ultrasound image phenotypes: A Japanese diabetes cohort study.

MOTIVATION: This study presents a novel nonlinear model which can predict 10-year carotid ultrasound image-based phenotypes by fusing nine traditional cardiovascular risk factors (ethnicity, gender, age, artery type, body mass index, hemoglobin A1c, hypertension, low-density lipoprotein, and smoking) with five types of carotid automated image phenotypes (three types of carotid intima-media thickness (IMT), wall variability, and total plaque area). METHODOLOGY: Two-step process was adapted: First, five baseline carotid image-based phenotypes were automatically measured using AtheroEdge™ (AtheroPoint™ , CA, USA) system by two operators (novice and experienced) and an expert. Second, based on the annual progression rates of cIMT due to nine traditional cardiovascular risk factors, a novel nonlinear model was adapted for 10-year predictions of carotid phenotypes. RESULTS: Institute review board (IRB) approved 204 Japanese patients' left/right common carotid artery (407 ultrasound scans) was collected with a mean age of 69 ± 11 years. Age and hemoglobin were reported to have a high influence on the 10-year carotid phenotypes. Mean correlation coefficient (CC) between 10-year carotid image-based phenotype and age was improved by 39.35% in males and 25.38% in females. The area under the curves for the 10-year measurements of five phenotypes IMTave10yr , IMTmax10yr , IMTmin10yr , IMTV10yr , and TPA10yr were 0.96, 0.94, 0.90, 1.0, and 1.0. Inter-operator variability between two operators showed significant CC (P < 0.0001). CONCLUSIONS: A nonlinear model was developed and validated by fusing nine conventional CV risk factors with current carotid image-based phenotypes for predicting the 10-year carotid ultrasound image-based phenotypes which may be used risk assessment.