Absolute risk assessment for guiding cardiovascular risk management in a chest pain clinic

Evaluation of health-related quality of life changes in an Australian rapid access chest pain clinic

OBJECTIVE

To evaluate the impact of absolute cardiovascular risk counselling on quality-of-life indices within a chest pain clinic.

DATA SOURCES AND STUDY SETTING

Primary data was collected at the Royal Hobart Hospital, Australia, between 2014 and 2020.

STUDY DESIGN

Patients attending an Australian chest pain clinic were randomised into a prospective, open-label, blinded-endpoint study over a minimum 12-months follow-up.

DATA COLLECTION / EXTRACTION METHODS

The SF-36 questionnaire was completed at baseline/follow-up and SF-6D multi-attribute utility instrument's health state utilities (HSU) were generated using SF-36 responses and the SF-6D's Australian tariff. SF-6D minimal important difference was 0.04 points. Absolute cardiovascular risk was also stratified into high/intermediate/low-risk categories for exploratory analysis of summary HSUs and dimensional scores. ANZCTR registration number 12617000615381 (registered 28/4/17).

PRINCIPAL FINDINGS

Of n = 189 patients enrolled, HSUs were generated for 96% at baseline (intervention n = 93, usual care n = 88) and 61% at follow-up. There were no statistical differences in age, sex, absolute cardiovascular risk or mean HSU between groups at baseline. Summary HSUs improved more for the intervention group and the median between-group difference exceeded the minimal important difference threshold (intervention 0.16 utility points, control 0.10 utility points). For Intervention patients with high absolute risk (≥ 15%), HSU did not significantly change.

CONCLUSIONS

Absolute cardiovascular risk counselling in a chest pain clinic yielded clinically meaningful improvement in health-related quality of life.

Development of machine learning-based models to predict 10-year risk of cardiovascular disease: a prospective cohort study

BACKGROUND

Previous prediction algorithms for cardiovascular diseases (CVD) were established using risk factors retrieved largely based on empirical clinical knowledge. This study sought to identify predictors among a comprehensive variable space, and then employ machine learning (ML) algorithms to develop a novel CVD risk prediction model.

METHODS

From a longitudinal population-based cohort of UK Biobank, this study included 473 611 CVD-free participants aged between 37 and 73 years old. We implemented an ML-based data-driven pipeline to identify predictors from 645 candidate variables covering a comprehensive range of health-related factors and assessed multiple ML classifiers to establish a risk prediction model on 10-year incident CVD. The model was validated through a leave-one-center-out cross-validation.

RESULTS

During a median follow-up of 12.2 years, 31 466 participants developed CVD within 10 years after baseline visits. A novel UK Biobank CVD risk prediction (UKCRP) model was established that comprised 10 predictors including age, sex, medication of cholesterol and blood pressure, cholesterol ratio (total/high-density lipoprotein), systolic blood pressure, previous angina or heart disease, number of medications taken, cystatin C, chest pain and pack-years of smoking. Our model obtained satisfied discriminative performance with an area under the receiver operating characteristic curve (AUC) of 0.762±0.010 that outperformed multiple existing clinical models, and it was well-calibrated with a Brier Score of 0.057±0.006. Further, the UKCRP can obtain comparable performance for myocardial infarction (AUC 0.774±0.011) and ischaemic stroke (AUC 0.730±0.020), but inferior performance for haemorrhagic stroke (AUC 0.644±0.026).

CONCLUSION

ML-based classification models can learn expressive representations from potential high-risked CVD participants who may benefit from earlier clinical decisions.

Lifestyle changes and quality of life a year after attending Rapid Access Cardiology Clinics: an observational study

We examined behavioural risk factors and quality of life (QoL) in women and men, younger and older adults 12 months after a Rapid Access Cardiology Clinic (RACC) visit. Routine clinical care data were collected in person from three Sydney hospitals between 2017 and 2018 and followed up by questionnaire at 365 days. 1491 completed the baseline survey, at 1 year, 1092 provided follow-up data on lifestyle changes, and 811 completed the EQ-5D-5L (QoL) survey. 666 (44.7%) were women, and 416 (27.9%) were older than 60 years of age. Almost 50% of participants reported improving physical activity and diet a year after their RACC visit. These changes were less likely in women and older participants.

Rapid access chest pain clinics in Australia and New Zealand

Chest pain is the second most common reason for adult emergency department presentations. Most patients have low or intermediate risk chest pain, which historically has led to inpatient admission for further evaluation. Rapid access chest pain clinics represent an innovative outpatient pathway for these low and intermediate risk patients, and have been shown to be safe and reduce hospital costs. Despite variations in rapid access chest pain clinic models, there are limited data to determine the most effective approach. Developing a national framework could be beneficial to provide sites with evidence, possible models, and business cases. Multicentre data analysis could enhance understanding and monitoring of the service.

Integration of Risk Scores and Integration Capability in Electronic Patient Records

BACKGROUND

Digital availability of patient data is continuously improving with the increasing implementation of electronic patient records in physician practices. The emergence of digital health data defines new fields of application for data analytics applications, which in turn offer extensive options of using data. Common areas of data analytics applications include decision support, administration, and fraud detection. Risk scores play an important role in compiling algorithms that underlay tools for decision support.

OBJECTIVES

This study aims to identify the current state of risk score integration and integration capability in electronic patient records for cardiovascular disease and diabetes in German primary care practices.

METHODS

We developed an evaluation framework to determine the current state of risk score integration and future integration options for four cardiovascular disease risk scores (arriba, Pooled Cohort Equations, QRISK3, and Systematic Coronary Risk Evaluation) and two diabetes risk scores (Finnish Diabetes Risk Score and German Diabetes Risk Score). We then used this framework to evaluate the integration of risk scores in common practice software solutions by examining the software and inquiring the respective software contact person.

RESULTS

Our evaluation showed that the most widely integrated risk score is arriba, as recommended by German medical guidelines. Every software version in our sample provided either an interface to arriba or the option to implement one. Our assessment of integration capability revealed a more nuanced picture. Results on data availability were mixed. Each score contains at least one variable, which requires laboratory diagnostics. Our analysis of data standardization showed that only one score documented all variables in a standardized way.

CONCLUSION

Our assessment revealed that the current state of risk score integration in physician practice software is rather low. Integration capability currently faces some obstacles. Future research should develop a comprehensive framework that considers the reasonable integration of risk scores into practice workflows, disease prevention programs, and the awareness of physicians and patients.

Can existing electronic medical records be used to quantify cardiovascular risk at point of care?

BACKGROUND

Using electronic data for cardiovascular risk stratification could help in prioritising healthcare access and optimise cardiovascular prevention.

AIMS

To determine whether assessment of absolute cardiovascular risk (Australian Absolute Cardiovascular Disease Risk, ACVDR) and short-term ischaemic risk (HEART Score) are possible from available data in Electronic Medical Record (EMR) and My Health Record (MHR) of patients presenting with acute cardiac symptoms to a Rapid Access Cardiology Clinic (RACC).

METHODS

Audit of EMR and MHR on 200 randomly selected adults who presented to RACC between 1st of March 2017 and 4th February 2020. The main outcomes were the proportion of patients for which an ACVDR and HEART Score could be calculated.

RESULTS

Mean age was 55.2 ± 17.8 years and 43% were female. Most were referred from Emergency (85%) for chest pain (52%). 46% had hypertension, 35% obesity, 20% diabetes mellitus, 17% ischaemic heart disease, and 18% were current smokers. There was no significant difference in MHR accessibility with age, gender, and number of comorbidities. ACVDR could be estimated for 17.5% (EMR) and 0% (MHR) of patients. None had complete data to estimate HEART Score in either EMR or MHR. Most commonly missing variables for ACVDR were blood pressure (MHR) and HDL-C (EMR), and for HEART Score were body mass index and comorbidities (MHR and EMR).

CONCLUSIONS

Significant gaps are apparent in electronic medical data capture of key variables to perform cardiovascular risk assessment. Medical data capture should prioritise the collection of clinically important data to help address gaps in cardiovascular management. This article is protected by copyright. All rights reserved.