Implications of Cardiovascular Disease Risk Assessment Using the WHO/ISH Risk Prediction Charts in Rural India

Artificial intelligence in the risk prediction models of cardiovascular disease and development of an independent validation screening tool: a systematic review

BACKGROUND

A comprehensive overview of artificial intelligence (AI) for cardiovascular disease (CVD) prediction and a screening tool of AI models (AI-Ms) for independent external validation are lacking. This systematic review aims to identify, describe, and appraise AI-Ms of CVD prediction in the general and special populations and develop a new independent validation score (IVS) for AI-Ms replicability evaluation.

METHODS

PubMed, Web of Science, Embase, and IEEE library were searched up to July 2021. Data extraction and analysis were performed for the populations, distribution, predictors, algorithms, etc. The risk of bias was evaluated with the prediction risk of bias assessment tool (PROBAST). Subsequently, we designed IVS for model replicability evaluation with five steps in five items, including transparency of algorithms, performance of models, feasibility of reproduction, risk of reproduction, and clinical implication, respectively. The review is registered in PROSPERO (No. CRD42021271789).

RESULTS

In 20,887 screened references, 79 articles (82.5% in 2017-2021) were included, which contained 114 datasets (67 in Europe and North America, but 0 in Africa). We identified 486 AI-Ms, of which the majority were in development (n = 380), but none of them had undergone independent external validation. A total of 66 idiographic algorithms were found; however, 36.4% were used only once and only 39.4% over three times. A large number of different predictors (range 5-52,000, median 21) and large-span sample size (range 80-3,660,000, median 4466) were observed. All models were at high risk of bias according to PROBAST, primarily due to the incorrect use of statistical methods. IVS analysis confirmed only 10 models as "recommended"; however, 281 and 187 were "not recommended" and "warning," respectively.

CONCLUSION

AI has led the digital revolution in the field of CVD prediction, but is still in the early stage of development as the defects of research design, report, and evaluation systems. The IVS we developed may contribute to independent external validation and the development of this field.

Development and validation of multicentre study on novel Artificial Intelligence-based Cardiovascular Risk Score (AICVD)

OBJECTIVE

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 randomised 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 (eg, acute myocardial infarction/acute coronary syndrome) in the next 10 years and compare the model with the Framingham Heart Risk Score (FHRS) and QRisk3.

METHODS

Our study included 31 599 participants aged 18-91 years from 2009 to 2018 in six Apollo Hospitals in India. A multistep risk factors selection process using Spearman correlation coefficient and propensity score matching yielded 21 risk factors. A deep learning hazards model was built on risk factors to predict event occurrence (classification) and time to event (hazards model) using multilayered neural network. Further, the model was validated with independent retrospective cohorts of participants from India and the Netherlands and compared with FHRS and QRisk3.

RESULTS

The deep learning hazards model had a good performance (area under the curve (AUC) 0.853). Validation and comparative results showed AUCs between 0.84 and 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).

CONCLUSIONS

This study concludes that the novel AI-based CVD Risk Score has a higher predictive performance for cardiac events than conventional risk scores in Indian population.

TRIAL REGISTRATION NUMBER

CTRI/2019/07/020471.

Agreement between ten-years cardiovascular disease risk assessment tools: An application to Iranian population in Shahedieh Cohort Study

Background and aim

Cardiovascular risk-prediction models are efficient primary prevention tools to detect high-risk individuals. The study aims to use three tools to estimate the 10-year risk of developing cardiovascular disease (CVD) and investigate their agreement in an Iranian adult population.

Methods

The current cross-sectional study was carried out on 8569 adults between 35 and 70 who participated in the first phase of the Shahedieh cohort study in Yazd, Iran, and were free of CVDs (cardiac ischemia or myocardial infarction or stroke). World Health Organization/International Society of Hypertension (WHO/ISH) chart, Laboratory-Based (LB) and Non-Laboratory-Based (NLB) Framingham Risk Score (FRS) were used to predict the 10-year risk of developing CVD. The agreement across tools was determined by Kappa.

Results

WHO/ISH chart indicated the highest prevalence of low CVD risk for males (96.10%) and females (96.50%), while NLB Framingham had the highest prevalence of high CVD risk for males (19.40%) and females (5.30%). In total, there was substantial agreement between both FRS models (Kappa = o.70), while there was a slight agreement between WHO/ISH and both FRS tools. For under 60 years males and females, substantial agreements were observed between FRS methods (kappa = 0.73 and kappa = 0.68). For males and females over 60 years, this agreement was moderate and substantial, respectively (kappa = 0.54 and kappa = 0.64). WHO/ISH and LB Framingham model had substantial agreement for over 60 years females (kappa = 0.61).

Conclusions

Framingham models classified more participants in the high-risk category than WHO/ISH. Due to the lethality of CVDs, categorizing individuals based on FRS can ensure that most of the real high-risk people are detected. Remarkable agreement between FRS methods in all sex-age groups suggested using the NLB Framingham model as a primary screening tool, especially in a shortage of resources condition.

Machine learning identifies prominent factors associated with cardiovascular disease: findings from two million adults in the Kashgar Prospective Cohort Study (KPCS)

BACKGROUND

Identifying factors associated with cardiovascular disease (CVD) is critical for its prevention, but this topic is scarcely investigated in Kashgar prefecture, Xinjiang, northwestern China. We thus explored the CVD epidemiology and identified prominent factors associated with CVD in this region.

METHODS

A total of 1,887,710 adults at baseline (in 2017) of the Kashgar Prospective Cohort Study were included in the analysis. Sixteen candidate factors, including seven demographic factors, 4 lifestyle factors, and 5 clinical factors, were collected from a questionnaire and health examination records. CVD was defined according to International Clinical Diagnosis (ICD-10) codes. We first used logistic regression models to investigate the association between each of the candidate factors and CVD. Then, we employed 3 machine learning methods-Random Forest, Random Ferns, and Extreme Gradient Boosting-to rank and identify prominent factors associated with CVD. Stratification analyses by sex, ethnicity, education level, economic status, and residential setting were also performed to test the consistency of the ranking.

RESULTS

The prevalence of CVD in Kashgar prefecture was 8.1%. All the 16 candidate factors were confirmed to be significantly associated with CVD (odds ratios ranged from 1.03 to 2.99, all p values < 0.05) in logistic regression models. Further machine learning-based analysis suggested that age, occupation, hypertension, exercise frequency, and dietary pattern were the five most prominent factors associated with CVD. The ranking of relative importance for prominent factors in stratification analyses showed that the factor importance generally followed the same pattern as that in the overall sample.

CONCLUSIONS

CVD is a major public health concern in Kashgar prefecture. Age, occupation, hypertension, exercise frequency, and dietary pattern might be the prominent factors associated with CVD in this region.In the future, these factors should be given priority in preventing CVD in future.

Recalibrating the Non-Communicable Diseases risk prediction tools for the rural population of Western India

BACKGROUND

The aim of the present study was to recalibrate the effectiveness of Indian Diabetes Risk Score (IDRS) and Community-Based Assessment Checklist (CBAC) by opportunistic screening of Diabetes Mellitus (DM) and Hypertension (HT) among the people attending health centres, and estimating the risk of fatal and non-fatal Cardio-Vascular Diseases (CVDs) among them using WHO/ISH charts.

METHODS

All the people aged ≥ 30 years attending the health centers were screened for DM and HT. Weight, height, waist circumference, and hip circumferences were measured, and BMI and Waist-Hip Ratio (WHR) were calculated. Risk categorization of all participants was done using IDRS, CBAC, and WHO/ISH risk prediction charts. Individuals diagnosed with DM or HT were started on treatment. The data was recorded using Epicollect5 and was analyzed using SPSS v.23 and MedCalc v.19.8. ROC curves were plotted for DM and HT with the IDRS, CBAC score, and anthropometric parameters. Sensitivity (SN), specificity (SP), Positive Predictive Value (PPV), Negative Predictive Value (NPV), Accuracy and Youden's index were calculated for different cut-offs of IDRS and CBAC scores.

RESULTS

A total of 942 participants were included for the screening, out of them, 9.2% (95% CI: 7.45-11.31) were diagnosed with DM for the first time. Hypertension was detected among 25.7% (95% CI: 22.9-28.5) of the participants. A total of 447 (47.3%) participants were found with IDRS score ≥ 60, and 276 (29.3%) with CBAC score > 4. As much as 26.1% were at moderate to higher risk (≥ 10%) of developing CVDs. Area Under the Curve (AUC) for IDRS in predicting DM was 0.64 (0.58-0.70), with 67.1% SN and 55.2% SP (Youden's Index 0.22). While the AUC for CBAC was 0.59 (0.53-0.65). For hypertension both the AUCs were 0.66 (0.62-0.71) and 0.63 (0.59-0.67), respectively.

CONCLUSIONS

IDRS was found to have the maximum AUC and sensitivity thereby demonstrating its usefulness as compared to other tools for screening of both diabetes and hypertension. It thus has the potential to expose the hidden NCD iceberg. Hence, we propose IDRS as a useful tool in screening of Diabetes and Hypertension in rural India.

Validation of the World Health Organization/ International Society of Hypertension (WHO/ISH) cardiovascular risk predictions in Sri Lankans based on findings from a prospective cohort study

Introduction and objectives

There are no cardiovascular (CV) risk prediction models for Sri Lankans. Different risk prediction models not validated for Sri Lankans are being used to predict CV risk of Sri Lankans. We validated the WHO/ISH (SEAR-B) risk prediction charts prospectively in a population-based cohort of Sri Lankans.

Method

We selected 40–64 year-old participants from the Ragama Medical Officer of Health (MOH) area in 2007 by stratified random sampling and followed them up for 10 years. Ten-year risk predictions of a fatal/non-fatal cardiovascular event (CVE) in 2007 were calculated using WHO/ISH (SEAR-B) charts with and without cholesterol. The CVEs that occurred from 2007–2017 were ascertained. Risk predictions in 2007 were validated against observed CVEs in 2017.

Results

Of 2517 participants, the mean age was 53.7 year (SD: 6.7) and 1132 (45%) were males. Using WHO/ISH chart with cholesterol, the percentages of subjects with a 10-year CV risk <10%, 10–19%, 20%-29%, 30–39%, ≥40% were 80.7%, 9.9%, 3.8%, 2.5% and 3.1%, respectively. 142 non-fatal and 73 fatal CVEs were observed during follow-up. Among the cohort, 9.4% were predicted of having a CV risk ≥20% and 8.6% CVEs were observed in the risk category. CVEs were within the predictions of WHO/ISH charts with and without cholesterol in both high (≥20%) and low(<20%) risk males, but only in low(<20%) risk females. The predictions of WHO/ISH charts, with-and without-cholesterol were in agreement in 81% of subjects (ĸ = 0.429; p<0.001).

Conclusions

WHO/ISH (SEAR B) risk prediction charts with-and without-cholesterol may be used in Sri Lanka. Risk charts are more predictive in males than in females and for lower-risk categories. The predictions when stratifying into 2 categories, low risk (<20%) and high risk (≥20%), are more appropriate in clinical practice.

Cardiovascular Risk Scores in Women Undergoing Stress Myocardial Perfusion Scan and Comparison with Scan-Predicted Risk

Background:

Death due to cardiovascular disease is a major concern in the field of noncommunicable disease. Assessment of cardiovascular risk score using Framingham score and WHO/ISH score is a noninvasive, easier method of predicting the adverse cardiovascular event in the general population.

Aims and Objectives:

The aim of the study was to assess the cardiovascular risk using Framingham score and WHO/ISH in women undergoing stress myocardial perfusion imaging (MPI) and comparison with scan-predicted risk.

Materials and Methods:

Adult females with suspected coronary artery disease referred to the department of nuclear medicine for 2 months were included in the study. Data pertaining to the risk score assessment were collected, and the risk scores were calculated. Subsequently, the patients underwent scheduled Tc-99m methoxy-isobutyl-isonitrile myocardial stress imaging, and scan-predicted risks were calculated. Then, the risk score of Framingham and WHO/ISH methods were compared with stress myocardial perfusion score using Cohen's kappa statistic.

Results:

The mean age of the sample was 52 years (standard deviation: 11). Framingham and WHO/ISH risk scores predicted low, intermediate, and high risk in 62.2%, 28.9%, and 8.9% and 68.9%, 22.1%, and 8.89% of the population. The two scoring methods showed moderate agreement (κ =0.59). However, the scores showed only slight and fair agreement, respectively, with risk predicted by stress MPI.

Conclusion:

Although the risk scores have been shown to benefit in screening general population, they may not perform well in symptomatic patients with suspected angina. Out of the two methods, WHO/ISH fares better than Framingham score in this population.

Development of an Efficient, Non-Invasive Method for Cardiovascular Disease Risk Stratification in a Resource-Limited Setting

BACKGROUND

Augmentation Index (AIx) is considered as an important predictor of cardiovascular disease. So, quantification of AIx may provide a rapid cost-effective and non-invasive means of cardiovascular risk stratification. At present, WHO/ISH risk prediction charts are used to predict 10-year risk of a fatal or nonfatal major cardiovascular event, an assessment which requires laboratory support for blood chemistry and thus making it ill-suited for resource-limited settings.

OBJECTIVES

In this study, we examined the association of AIx with cardiovascular risk as determined by the WHO/ISH chart and identified AIx cut-offs to stratify patients into different risk categories.

METHODS

A case-control study with 162 cases and 61 controls was conducted in a tertiary care hospital in eastern India. Data were obtained for demographic, anthropometric, cardiovascular, and biochemical parameters. Cardiovascular risk assessment was carried out by WHO/ISH risk model in R. Statistical analysis was done for examining the association of AIx with WHO/ISH cardiovascular risk and for identifying AIx cut-offs to stratify patients into different risk categories.

RESULTS

Box and whisker plots for assessing the correlation between AIx and WHO/ISH cardiovascular risk showed an increase in the median value of AIx with increasing risk in both cases and controls. Heart rate corrected AIx showed a steady increase with increasing risk in males. AIx cutoffs showed good sensitivity and specificity for each risk category.

CONCLUSION

AIx is remarkably associated with cardiovascular risk as assessed by the WHO/ISH chart and the AIx cut-offs obtained in the study can be used as an efficient, non-invasive surrogate biomarker of cardiovascular risk even in resource-limited settings.

Critical appraisal of a mHealth-assisted community-based cardiovascular disease risk screening program in rural Kenya: an operational research study

Community health workers (CHWs) can participate in the cascade of hypertension and diabetes management in low and middle-income countries (LMICs). Their services may be enhanced with mobile health (mHealth) tools. In this operational research study, we describe the AFYACHAT mHealth-assisted cardiovascular health screening program in rural Kenya. In this study, A CHW screened a convenience sample of adults ≥ 40 years old in rural Kenya for cardiovascular disease (CVD) risk using the two-way AFYACHAT mHealth instrument. AFYACHAT analyzes a patient's age, sex, smoking, diabetes and systolic blood pressure and provides a four-tiered 10-year CVD risk score. User acceptability was assessed by an end-of-study interview with the CWH. Automated error logs were analyzed. Patient satisfaction was measured with a six-question satisfaction questionnaire. Screened participants with high CVD risk were followed-up via telephone to explore any actions taken following screening. In 24 months, one CHW screened 1650 participants using AFYACHAT. The 10-year risk of CVD was <10% for 1611 (98%) patients, 10 to <20% for 26 (1.6%), 20 to <30% in 12 (0.7%), and ≥30% for 1 (0.1%). The point prevalence of hypertension and diabetes was 27% and 1.9%, respectively. Seventy-five percent of participants with elevated CVD risk sought further medical care. There was high acceptability, a 15% miscode error rate, and high participant satisfaction with the screening program. Our operational research outlines how AFYACHAT mHealth tool can assist CHW perform rapid CVD screening; this provides a model framework for non-communicable disease screening in LMICs.

Cardiovascular risk using WHO-ISH chart among Diabetes and Hypertensive patients in a remote rural area of South India

INTRODUCTION

Cardiovascular diseases (CVDs) are major problems in India and many other developing and developed countries. As India is committed to provide universal health care for the population, there is a need to find out the prevalence and determinants of CVD risk among high-risk individuals (Diabetes and Hypertensive patients) in the remote rural area of India to deliver appropriate services, as they are considered as neglected population.

METHODS

We screened high-risk individuals (Hypertension and Diabetes patients) for CVD risk using WHO/ISH chart, in a remote rural area of south India, covering ten villages surrounding the Rural Health Training Centre (RHTC), in August-September 2017. After line-listing the participants from the electronic database of RHTC, screening with questionnaire and biochemical tests was done at village level as the first step. Thereafter, the participants were invited to the hospital on a particular day where electrocardiography (ECG) and echocardiography (ECHO) were done with special consultation.

RESULTS

Among the total of 303 individuals screened at the village level, 64 [21%(CI 17-25)] had a higher risk for CVD. 235 people attended the special consultation; among them, 212 underwent ECG and 88 underwent ECHO. Among those screened with ECHO, 18 had some cardiac pathologies. The relationship between CVD risk and other factors is shown in. After final adjustment, illiteracy [adjusted prevalence ratio (aPR) 1.8 (0.1-3.1)], anemia [aPR 1.8 (1-3.6)], and chronic renal diseases [aPR 1.8 (1.0-3.4)] were found to be associated with high risk for CVD among hypertension and diabetes groups.

CONCLUSION

Cardiovascular disease risk assessment using WHO/ISH chart showed an association with poor education, anemia, and chronic kidney disease.

Assessment of cardiovascular disease risk in Northern China: a cross-sectional study

Cardiovascular disease (CVD) is a life-threatening chronic illness. CVD risk may be influenced by environment and lifestyle. People in northern China usually consume high-fat, high-salt diets and alcohol and live in a cold climate over long periods. However, there are limited studies on CVD risk among people in northern China. In the present study, we sought to estimate the CVD risk profile among residents of northern China. Using the Programme of Screening and Intervention Subjects with High Risk Cardiovascular Diseases, we collected data from residents in six cities from September 2015 to June 2017. In total, 56,716 participants aged 40 years and above were finally included in the CVD risk assessment. To assess the 10-year risk of CVD among participants, we used World Health Organisation/International Society of Hypertension risk prediction charts. Among the study participants, 22.7% had a high 10-year risk of CVD. We identified differences in the 10-year CVD risk according to sex, socioeconomic status, and marital status. We conclude that individuals with high socioeconomic status should be encouraged to change their lifestyle habits, and greater medical resources should be invested for individuals residing in rural areas and those with low education levels.

CARDIOVASCULAR RISK ASSESSMENT IN THE ADULT (AGED 40-79 YEARS) ROMANIAN POPULATION

Atherosclerotic Cardiovascular Diseases are the leading cause of death worldwide.

Aim

To estimate the prevalence of cardiovascular risk (CVR) categories in the adult population (aged 40-79 years) of Romania.

Design

The present study was part of the epidemiological, cross-sectional PREDATORR study (PREvalence of DiAbeTes mellitus, prediabetes, overweight, Obesity, dyslipidemia, hyperuricemia and chronic kidney disease in Romania).

Subjects and Methods

Exclusion criteria: age <40/or>79 years old and diagnosis of ischemic vascular disease. The CVR was evaluated using charts developed by the World Health Organization/ International Society of Hypertension (WHO/ISH) available for Europe B (epidemiological sub-region where Romania was included). The CVR was divided into 5 categories: <10%, 10-20%, 20-30%, 30-40%, > 40%.

Results

A total of 1631 subjects (57.0±10.7 years, 45.1% males) were included in the present study.The age and sex-adjusted prevalence of CVR >40% was 2.9% (95%CI 2.8-3.1%), CVR 30-40% was 1.85% (95%CI 1.8-1.9%), CVR 20-30% was 5.8% (95%CI 5.6-6.0%) and 13.0% (95%CI 12.8-13.3%) of the adult Romanian population has a 10-20% CVR, these CVR categories being more frequent in male and older age. Diabetes, overweight/obesity and smoking were associated with high CVR categories.

Conclusion

Romania is one of the countries with high CVR, requiring CVD prevention measures.

whoishRisk - an R package to calculate WHO/ISH cardiovascular risk scores for all epidemiological subregions of the world

The World Health Organisation and International Society of Hypertension (WHO/ISH) cardiovascular disease (CVD) risk assessment charts have been implemented in many low- and middle-income countries as part of the WHO Package of Essential Non-Communicable Disease (PEN) Interventions for Primary Health Care in Low-Resource settings. Evaluation of the WHO/ISH cardiovascular risk charts and their use is a key priority and since they only existed in paper or PDF formats, we developed an R implementation of the charts for all epidemiological subregions of the world. The main strengths of this implementation are that it is built in a free, open-source, coding language with simple syntax, can be downloaded from github as a package (“whoishRisk”), and can be used with a standard computer.