Development and Validation of Multicenter Study on Novel Artificial Intelligence Based Cardiovascular Risk Score (AICVD)

2021 ◽  
Author(s):  
Shiv Kumar ◽  
Prashant Gupta ◽  
Andre L.A.J. Dekker ◽  
Inigo Bermejo ◽  
Sujoy Kar
Keyword(s):  
Artificial Intelligence ◽  
Risk Factors ◽  
Deep Learning ◽  
The Netherlands ◽  
Risk Score ◽  
Randomized Clinical Trials ◽  
Positive Likelihood Ratio ◽  
Hazard Model ◽  
Risk Scores ◽  
Cvd Risk

Abstract Cardiovascular diseases (CVD) are one of the most prevalent diseases in India amounting for nearly 30% of total deaths. A dearth of research on CVD risk scores in Indian population, limited performance of conventional risk scores and inability to reproduce the initial accuracies in randomized clinical trials – has led to this study on large-scale patient data. The objective is to develop an Artificial Intelligence based Risk Score (AICVD) to predict CVD Event (e.g. Acute MI / ACS) in next 10 years and compare the model with the Framingham Heart Risk Score (FHRS) and QRisk3.Our study included 31,599 participants aged 18-91 years from 2009 - 2018 in six Apollo Hospitals in India. A multi-step risk factors selection process using Spearman correlation coefficient and propensity score matching yielded 21 risk factors. A Deep Learning Hazard Model was built on risk factors to predict event occurrence (classification) and time to event (hazard model) using multi-layered neural network. Further, the model was validated with independent retrospective cohorts of participants from India and the Netherlands and compared with FHRS and QRisk3.The Deep Learning Hazard model had a good performance (AUC 0.853). Validation and comparative results showed AUCs between 0.84 to 0.92 with better Positive Likelihood Ratio (AICVD-6.16 to FHRS–2.24 and QRisk3–1.16) and Accuracy (AICVD– 80.15% to FHRS 59.71% and QRisk3 51.57%). In the Netherlands cohort, AICVD also outperformed the Framingham Heart Risk Model (AUC - 0.737 vs 0.707).This study concludes that the novel AI based CVD risk score has a higher predictive performance for cardiac events than conventional risk scores.

scholarly journals The Relationship between Cardiovascular Risk Scores and Several Markers of Subclinical Atherosclerosis in an Asymptomatic Population

2021 ◽  
Vol 10 (5) ◽  
pp. 955
Author(s):  
Ovidiu Mitu ◽  
Adrian Crisan ◽  
Simon Redwood ◽  
Ioan-Elian Cazacu-Davidescu ◽  
Ivona Mitu ◽  
...  
Keyword(s):  
Risk Score ◽  
Subclinical Atherosclerosis ◽  
Ankle Brachial Index ◽  
Intima Media Thickness ◽  
Carotid Intima Media Thickness ◽  
Risk Scores ◽  
Cvd Risk ◽  
Cross Sectional ◽  
Single Center Study ◽  
Asymptomatic Individuals

Background: The current cardiovascular disease (CVD) primary prevention guidelines prioritize risk stratification by using clinical risk scores. However, subclinical atherosclerosis may rest long term undetected. This study aimed to evaluate multiple subclinical atherosclerosis parameters in relation to several CV risk scores in asymptomatic individuals. Methods: A cross-sectional, single-center study included 120 asymptomatic CVD subjects. Four CVD risk scores were computed: SCORE, Framingham, QRISK, and PROCAM. Subclinical atherosclerosis has been determined by carotid intima-media thickness (cIMT), pulse wave velocity (PWV), aortic and brachial augmentation indexes (AIXAo, respectively AIXbr), aortic systolic blood pressure (SBPao), and ankle-brachial index (ABI). Results: The mean age was 52.01 ± 10.73 years. For cIMT—SCORE was more sensitive; for PWV—Framingham score was more sensitive; for AIXbr—QRISK and PROCAM were more sensitive while for AIXao—QRISK presented better results. As for SBPao—SCORE presented more sensitive results. However, ABI did not correlate with any CVD risk score. Conclusions: All four CV risk scores are associated with markers of subclinical atherosclerosis in asymptomatic population, except for ABI, with specific particularities for each CVD risk score. Moreover, we propose specific cut-off values of CV risk scores that may indicate the need for subclinical atherosclerosis assessment.

scholarly journals Body Mass Index, Multi-Morbidity, and COVID-19 Risk Factors as Predictors of Severe COVID-19 Outcomes

2021 ◽  
Vol 12 ◽  
pp. 215013272110185
Author(s):  
Sanjeev Nanda ◽  
Audry S. Chacin Suarez ◽  
Loren Toussaint ◽  
Ann Vincent ◽  
Karen M. Fischer ◽  
...  
Keyword(s):  
Risk Factors ◽  
Body Mass Index ◽  
Hospital Admission ◽  
Body Mass ◽  
Risk Score ◽  
The Body ◽  
Risk Scores ◽  
Nasopharyngeal Swab ◽  
Morbidity Score ◽  
The Impact

Purpose The purpose of the present study was to investigate body mass index, multi-morbidity, and COVID-19 Risk Score as predictors of severe COVID-19 outcomes. Patients Patients from this study are from a well-characterized patient cohort collected at Mayo Clinic between January 1, 2020 and May 23, 2020; with confirmed COVID-19 diagnosis defined as a positive result on reverse-transcriptase-polymerase-chain-reaction (RT-PCR) assays from nasopharyngeal swab specimens. Measures Demographic and clinical data were extracted from the electronic medical record. The data included: date of birth, gender, ethnicity, race, marital status, medications (active COVID-19 agents), weight and height (from which the Body Mass Index (BMI) was calculated, history of smoking, and comorbid conditions to calculate the Charlson Comorbidity Index (CCI) and the U.S Department of Health and Human Services (DHHS) multi-morbidity score. An additional COVID-19 Risk Score was also included. Outcomes included hospital admission, ICU admission, and death. Results Cox proportional hazards models were used to determine the impact on mortality or hospital admission. Age, sex, and race (white/Latino, white/non-Latino, other, did not disclose) were adjusted for in the model. Patients with higher COVID-19 Risk Scores had a significantly higher likelihood of being at least admitted to the hospital (HR = 1.80; 95% CI = 1.30, 2.50; P < .001), or experiencing death or inpatient admission (includes ICU admissions) (HR = 1.20; 95% CI = 1.02, 1.42; P = .028). Age was the only statistically significant demographic predictor, but obesity was not a significant predictor of any of the outcomes. Conclusion Age and COVID-19 Risk Scores were significant predictors of severe COVID-19 outcomes. Further work should examine the properties of the COVID-19 Risk Factors Scale.

scholarly journals A Modified CAIDE Risk Score as a Screening Tool for Cognitive Impairment in Older Adults

2021 ◽  
pp. 1-14
Author(s):  
Magdalena I. Tolea ◽  
Jaeyeong Heo ◽  
Stephanie Chrisphonte ◽  
James E. Galvin
Keyword(s):  
Risk Factors ◽  
Older Adults ◽  
Cognitive Impairment ◽  
Risk Score ◽  
Clinical Sample ◽  
Community Sample ◽  
Community Dwelling ◽  
Cognitive Testing ◽  
Risk Scores ◽  
Predictive Values

Background: Although an efficacious dementia-risk score system, Cardiovascular Risk Factors, Aging, and Dementia (CAIDE) was derived using midlife risk factors in a population with low educational attainment that does not reflect today’s US population, and requires laboratory biomarkers, which are not always available. Objective: Develop and validate a modified CAIDE (mCAIDE) system and test its ability to predict presence, severity, and etiology of cognitive impairment in older adults. Methods: Population consisted of 449 participants in dementia research (N = 230; community sample; 67.9±10.0 years old, 29.6%male, 13.7±4.1 years education) or receiving dementia clinical services (N = 219; clinical sample; 74.3±9.8 years old, 50.2%male, 15.5±2.6 years education). The mCAIDE, which includes self-reported and performance-based rather than blood-derived measures, was developed in the community sample and tested in the independent clinical sample. Validity against Framingham, Hachinski, and CAIDE risk scores was assessed. Results: Higher mCAIDE quartiles were associated with lower performance on global and domain-specific cognitive tests. Each one-point increase in mCAIDE increased the odds of mild cognitive impairment (MCI) by up to 65%, those of AD by 69%, and those for non-AD dementia by >  85%, with highest scores in cases with vascular etiologies. Being in the highest mCAIDE risk group improved ability to discriminate dementia from MCI and controls and MCI from controls, with a cut-off of ≥7 points offering the highest sensitivity, specificity, and positive and negative predictive values. Conclusion: mCAIDE is a robust indicator of cognitive impairment in community-dwelling seniors, which can discriminate well between dementia severity including MCI versus controls. The mCAIDE may be a valuable tool for case ascertainment in research studies, helping flag primary care patients for cognitive testing, and identify those in need of lifestyle interventions for symptomatic control.

scholarly journals Risk score to stratify miscarriage risk levels in preconception women

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Xin Hui Choo ◽  
Chee Wai Ku ◽  
Yin Bun Cheung ◽  
Keith M. Godfrey ◽  
Yap-Seng Chong ◽  
...  
Keyword(s):  
Risk Factors ◽  
Risk Score ◽  
Smoking Status ◽  
Characteristic Curve ◽  
Lifestyle Changes ◽  
Risk Scores ◽  
Risk Level ◽  
Multivariable Logistic Regression Model ◽  
Spontaneous Miscarriage ◽  
Risk Levels

AbstractSpontaneous miscarriage is one of the most common complications of pregnancy. Even though some risk factors are well documented, there is a paucity of risk scoring tools during preconception. In the S-PRESTO cohort study, Asian women attempting to conceive, aged 18-45 years, were recruited. Multivariable logistic regression model coefficients were used to determine risk estimates for age, ethnicity, history of pregnancy loss, body mass index, smoking status, alcohol intake and dietary supplement intake; from these we derived a risk score ranging from 0 to 17. Miscarriage before 16 weeks of gestation, determined clinically or via ultrasound. Among 465 included women, 59 had miscarriages and 406 had pregnancy ≥ 16 weeks of gestation. Higher rates of miscarriage were observed at higher risk scores (5.3% at score ≤ 3, 17.0% at score 4–6, 40.0% at score 7–8 and 46.2% at score ≥ 9). Women with scores ≤ 3 were defined as low-risk level (< 10% miscarriage); scores 4–6 as intermediate-risk level (10% to < 40% miscarriage); scores ≥ 7 as high-risk level (≥ 40% miscarriage). The risk score yielded an area under the receiver-operating-characteristic curve of 0.74 (95% confidence interval 0.67, 0.81; p < 0.001). This novel scoring tool allows women to self-evaluate their miscarriage risk level, which facilitates lifestyle changes to optimize modifiable risk factors in the preconception period and reduces risk of spontaneous miscarriage.

scholarly journals Limited Utility of Cardiovascular Risk Scores for People Living with HIV in Malawi

2020 ◽  
Author(s):  
Chia Goh ◽  
Henry Mwandumba ◽  
Alicja Rapala ◽  
Willard Tingao ◽  
Irene Sheha ◽  
...  
Keyword(s):  
Risk Score ◽  
Low Income ◽  
Intima Media Thickness ◽  
Risk Groups ◽  
Carotid Intima Media Thickness ◽  
Endothelial Damage ◽  
Risk Scores ◽  
People Living With Hiv ◽  
Cvd Risk ◽  
Living With Hiv

HIV is associated with increased cardiovascular disease (CVD) risk. Despite the high prevalence of HIV in low income subSaharan Africa, there are few data on the assessment of CVD risk in the region. In this study, we aimed to compare the utility of existing CVD risk scores in a cohort of Malawian adults, and assess to what extent they correlate with established markers of endothelial damage: carotid intima media thickness (IMT) and pulse wave velocity (PWV). WHO/ISH, SCORE, FRS, ASCVD, QRISK2 and D:A:D scores were calculated for 279 Malawian adults presenting with HIV and low CD4. Correlation of the calculated 10year CVD risk score with IMT and PWV was assessed using Spearmans rho. The median (IQR) age of patients was 37 (31 to 43) years and 122 (44%) were female. Median (IQR) blood pressure was 120/73mmHg (108/68 to 128/80) and 88 (32%) study participants had a new diagnosis of hypertension. The FRS and QRISK2 scores included the largest number of participants in this cohort (96% and 100% respectively). D:A:D, a risk score specific for people living with HIV, identified more patients in moderate and high risk groups. Although all scores correlated well with physiological markers of endothelial damage, FRS and QRISK2 correlated most closely with both IMT [r2 0.51, p<0.0001 and r2 0.47, p<0.0001 respectively] and PWV [r2 0.47, p<0.0001 and r2 0.5, p<0.0001 respectively]. Larger cohort studies are required to adapt and validate risk prediction scores in this region, so that limited healthcare resources can be effectively targeted.

Abstract 15997: Pooled Cohort Risk Equations: A Comparison of Their Predictions With Five Other Cardiovascular Risk Scores in Five Peruvian Sites

Circulation ◽  
2014 ◽  
Vol 130 (suppl_2) ◽  
Author(s):  
Juan Bazo-Alvarez ◽  
Frank Peralta-Alvarez ◽  
Renato Quispe ◽  
Julio Poterico ◽  
Giancarlo Valle ◽  
...  
Keyword(s):  
Risk Score ◽  
Disease Risk ◽  
Heart Association ◽  
Population Based ◽  
Continuous Variable ◽  
World Health ◽  
Risk Scores ◽  
Cvd Risk ◽  
Low Middle Income Countries ◽  
Predicted Risk

Introduction: Cardiovascular disease (CVD) risk scores are used to estimate an individual’s risk of developing a disease or death from a cardiovascular event. Recently, the American College of Cardiology/American Heart Association (ACC/AHA) introduced the Pooled Cohort risk equations (ACC/AHA model). It is important to know how comparable CVD risk predictions are in low-middle income countries (LMIC). Hypothesis: ACC/AHA model has a poor concordance with any other CVD risk score. Methods: We used secondary data from two Peruvian, age and sex-matched, population-based studies across five geographical sites. The ACC/AHA model was compared to five other CVD risk prediction tools: two versions of the Framingham Risk Score (FRS-Lipids and FRS-BMI), Reynolds Risk Score (RRS), four versions of the Systematic Coronary Risk Evaluation (SCORE 1-4), World Health Organization risk chart (WHO), and Lancet Chronic Disease risk chart (LCD). We calculated predicted risk as a continuous variable and used Lin’s concordance correlation coefficient (CCC). We also compared the high predicted risk prevalence between all the scores using the cut-off levels suggested by each score’s guidelines. Results: We included 2183 subjects in the risk scores age range of 45-65 years (mean age 54.3 (SD±5.6) years). CCC agreement values found in this study were generally poor. The highest concordance was observed between the ACC/AHA model and the risk scores derived from the Framingham Study (40% with FRS-BMI and 44% with FRS-Lipids). ACC/AHA model depicted the highest proportion of people with predicted high-risk of 10-year CVD, at 29.0% (95%CI 26.9-31.0%) and the same tendency was observed in all study sites. Conclusions: In Peruvian population-based samples, agreement between ACC/AHA model and five other CVD risk scores was generally poor. There is an urgent need to use an appropriate risk score for CVD in LMIC. In an ideal scenario, it would be significant to have a proper CVD risk score for LMIC.

Abstract 31: Prediction of coronary artery and abdominal aortic calcium in middle-aged adults using the Pathobiological Determinants of Atherosclerosis in Youth (PDAY) risk score: the CARDIA study

Circulation ◽  
2014 ◽  
Vol 129 (suppl_1) ◽  
Author(s):  
Christopher Prendergast ◽  
Jamal S Rana ◽  
Alex McMahan ◽  
Henry McGill ◽  
Jeff Carr ◽  
...  
Keyword(s):  
Risk Factors ◽  
Young Adults ◽  
Coronary Artery ◽  
Risk Score ◽  
Model Performance ◽  
Baseline Risk ◽  
Risk Scores ◽  
Abdominal Aortic ◽  
Point Increase ◽  
Better Than

Background: Risk scores to predict coronary and abdominal atherosclerosis have been developed from autopsy specimens from the right coronary artery and descending aorta and risk factors measured post-mortem in the Pathobiological Determinants of Atherosclerosis in Youth Study (PDAY), cohort aged 15-34 years. While the PDAY risk score predicts coronary artery calcium (CAC) up to 15 years before its assessment in Coronary Artery Risk Development in Young Adults (CARDIA), the clinical validity at 25 years follow up and of the abdominal score to predict abdominal aortic calcium (AAC) has not been tested. Objectives: To test the hypotheses: 1) PDAY risk scores at CARDIA baseline (cohort aged 18-30 years) predict CAC and abdominal aortic calcium (AAC) at year 25 better than PDAY risk scores measured at subsequent time points. 2) Change in risk over time will improve associations in Aim 1. Methods: The CARDIA study assessed CAC and AAC by computed tomography in young adults participating at year 25. The PDAY risk score was calculated from risk factors measured at the CARDIA examinations at years 0 (cohort aged 18-30 years), 5, 10, 15 and 25 (age 43-55 years). Results: Age and gender independent PDAY risk scores increased from CARDIA year 0 to year 25 (coronary from 1.80 to 4.95, abdomen from 1.88 to 3.18). Prevalence of any CAC was 28% and AAC was 53%. For a one point increase in risk score, baseline risk predicted CAC and AAC better than year 25 risk; change in risk improved the prediction further (Table). C-statistics for CAC prediction were higher at year 0 but similar at years 0 and 25 for AAC. Further analyses using PDAY scores calculated at 5 year intervals prior to the CT scan confirmed that CAC at baseline and AAC at year 5 had the highest Odds Ratios for a one point increase in score (AAC year 5 Odds Ratio 1.35 (1.30-1.41)). Conclusions: PDAY risk scores, applied to living adults in the CARDIA study, predicted CAC and AAC in 43-55 year old adults; including change in risk slightly improves model performance.

The Extent of Subclinical Atherosclerosis Is Partially Predicted by the Inflammatory Load: A Prospective Study over 5 Years in Patients with Rheumatoid Arthritis and Matched Controls

2015 ◽  
Vol 42 (6) ◽  
pp. 935-942 ◽  
Author(s):  
Anna Södergren ◽  
Kjell Karp ◽  
Christine Bengtsson ◽  
Bozena Möller ◽  
Solbritt Rantapää-Dahlqvist ◽  
...  
Keyword(s):  
Rheumatoid Arthritis ◽  
Risk Factors ◽  
Linear Regression ◽  
Prospective Study ◽  
Risk Score ◽  
Subclinical Atherosclerosis ◽  
Cvd Risk Factors ◽  
Cvd Risk ◽  
A Prospective Study ◽  
Reynolds Risk Score

Objective.This prospective followup study investigated subclinical atherosclerosis in relation to traditional cardiovascular disease (CVD) risk factors and inflammation in patients with rheumatoid arthritis (RA) recruited at diagnosis compared with controls.Methods.Patients diagnosed with early RA were consecutively recruited into a prospective study. From these, a subgroup aged ≤ 60 years (n = 71) was consecutively included for ultrasound measurement of intima-media thickness (IMT) and flow-mediated dilation (FMD) at inclusion (T0) and after 5 years (T5). Age- and sex-matched controls (n = 40) were also included.Results.In the Wilcoxon signed-rank test, both IMT and FMD were significantly aggravated at T5 compared to baseline in patients with RA, whereas only IMT was significantly increased in controls. In univariate linear regression analyses among patients with RA, the IMT at T5 was significantly associated with age, systolic blood pressure (BP), cholesterol, triglycerides, Systematic Coronary Risk Evaluation (SCORE), and Reynolds Risk Score at baseline (p < 0.05). Similarly, FMD at T5 was significantly inversely associated with age, smoking, systolic BP, SCORE, and Reynolds Risk Score (p < 0.05). A model with standardized predictive value from multiple linear regression models including age, smoking, BP, and blood lipids at baseline significantly predicted the observed value of IMT after 5 years. When also including the area under the curve for the 28-joint Disease Activity Score over 5 years, the observed value of IMT was predicted to a large extent.Conclusion.This prospective study identified an increased subclinical atherosclerosis in patients with RA. In the patients with RA, several traditional CVD risk factors at baseline significantly predicted the extent of subclinical atherosclerosis 5 years later. The inflammatory load over time augmented this prediction.

scholarly journals Global cardiovascular risk assessment: a national training course for General Practitioners

2019 ◽  
Vol 29 (Supplement_4) ◽  
Author(s):  
L Palmieri ◽  
B Unim ◽  
E Mattei ◽  
M Tijhuis ◽  
A Fehr ◽  
...  
Keyword(s):  
Risk Factors ◽  
Risk Assessment ◽  
High Risk ◽  
General Practitioners ◽  
Risk Score ◽  
Preventive Action ◽  
Clinical Practices ◽  
Cvd Risk ◽  
Training Course ◽  
National Training

Abstract Background Identification of high risk individuals is one of the main goals of the primary prevention of cardiovascular disease (CVD) and constitutes the basis for implementing actions aiming at reducing modifiable risk factors at individual level through changing life styles or drug interventions. The most appropriate method for identifying high risk individuals is the absolute risk assessment, a probability indicator of incidence, predictable on the basis of risk factors levels. Objectives The CUORE project score of the National Institute of Health-ISS is adopted in Italy; since 2007 ISS has implemented a national training course for General Practitioners-GPs with the aim of supporting and facilitating the use of CVD risk assessment in clinical practice as a preventive action in the general population. Results The training course is based on five sequential packages linked to educational credits: packages 1-2 facilitate the adoption of standardised methodologies for the assessment of CVD risk score; in package 3 patients are invited by GPs to assess the risk score; packages 4-5 evaluate and discuss data collected with GPs and stakeholders. A cascade training was implemented: ISS personnel provided training to local GPs who in turn provided the same training to other GPs. Two manuals for the training course were published. Since 2007 about 4,300 GPs were trained; about 320,000 10-year CVD risk assessments were performed in 260,000 men and women aged 35-69 years. Feedback was provided to all GPs participating to the 4th-5th packages of the training courses. Conclusions Implementation of the training course for the use of CVD risk assessment in the population represents a primary preventive action according to the recommendation of the EU Guideline on CVD prevention. The collected data may play an important role in the identification of strengths and weaknesses of preventive actions and represents the first step to improve good clinical practices standards.

scholarly journals Assessment of medium-term cardiovascular disease risk after Japan’s 2011 Fukushima Daiichi nuclear accident: a retrospective analysis

BMJ Open ◽  
2017 ◽  
Vol 7 (12) ◽  
pp. e018502 ◽  
Author(s):  
Haruka Toda ◽  
Shuhei Nomura ◽  
Stuart Gilmour ◽  
Masaharu Tsubokura ◽  
Tomoyoshi Oikawa ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cardiovascular Disease ◽  
Risk Score ◽  
Disease Risk ◽  
Cardiovascular Disease Risk ◽  
Multivariate Regression Analysis ◽  
Nuclear Accident ◽  
Medium Term ◽  
Cvd Risk ◽  
Fukushima Daiichi

ObjectiveTo assess the medium-term indirect impact of the 2011 Fukushima Daiichi nuclear accident on cardiovascular disease (CVD) risks and to identify whether risk factors for CVD changed after the accident.ParticipantsResidents aged 40 years and over participating in annual public health check-ups from 2009 to 2012, administered by Minamisoma city, located about 10 to 40 km from the Fukushima Daiichi nuclear plant.MethodsThe sex-specific Framingham CVD risk score was considered as the outcome measure and was compared before (2009–2010) and after the accident (2011–2012). A multivariate regression analysis was employed to evaluate risk factors for CVD.ResultsData from 563 individuals (60.2% women) aged 40 to 74 years who participated in the check-ups throughout the study period was analysed. After adjusting for covariates, no statistically significant change was identified in the CVD risk score postaccident in both sexes, which may suggest no obvious medium-term health impact of the Fukushima nuclear accident on CVD risk. The risk factors for CVD and their magnitude and direction (positive/negative) did not change after the accident.ConclusionsThere was no obvious increase in CVD risks in Minamisoma city, which may indicate successful management of health risks associated with CVD in the study sample.

Sign in / Sign up

Export Citation Format

Share Document