Advanced cardiovascular risk prediction in the emergency department: updating a clinical prediction model – a large database study protocol

Background Patients presenting with chest pain represent a large proportion of attendances to emergency departments. In these patients clinicians often consider the diagnosis of acute myocardial infarction (AMI), the timely recognition and treatment of which is clinically important. Clinical prediction models (CPMs) have been used to enhance early diagnosis of AMI. The Troponin-only Manchester Acute Coronary Syndromes (T-MACS) decision aid is currently in clinical use across Greater Manchester. CPMs have been shown to deteriorate over time through calibration drift. We aim to assess potential calibration drift with T-MACS and compare methods for updating the model. Methods We will use routinely collected electronic data from patients who were treated using TMACS at two large NHS hospitals. This is estimated to include approximately 14,000 patient episodes spanning June 2016 to October 2020. The primary outcome of acute myocardial infarction will be sourced from NHS Digital’s admitted patient care dataset. We will assess the calibration drift of the existing model and the benefit of updating the CPM by model recalibration, model extension and dynamic updating. These models will be validated by bootstrapping and one step ahead prequential testing. We will evaluate predictive performance using calibrations plots and c-statistics. We will also examine the reclassification of predicted probability with the updated TMACS model. Discussion CPMs are widely used in modern medicine, but are vulnerable to deteriorating calibration over time. Ongoing refinement using routinely collected electronic data will inevitably be more efficient than deriving and validating new models. In this analysis we will seek to exemplify methods for updating CPMs to protect the initial investment of time and effort. If successful, the updating methods could be used to continually refine the algorithm used within TMACS, maintaining or even improving predictive performance over time. Trial registration ISRCTN number: ISRCTN41008456

Cardiovascular risk prediction in type 2 diabetes: a comparison of 22 risk scores in primary care setting

People with type 2 diabetes (T2DM) remain at high risk for cardiovascular disease (CVD) CVD treatment initiation and intensification are guided by risk prediction algorithms. The majority of CVD risk prediction tools have not been validated in T2DM. We compared the performance of general and diabetes specific cardiovascular risk prediction scores for cardiovascular disease (CVD ie coronary heart disease and stroke), CVD+ (including atrial fibrillation and heart failure), and their individual components, in type 2 diabetes patients (T2DM). Scores were identified through a systematic review and included irrespective of the type of predicted CVD, or inclusion of T2DM patients. Performance was assessed in a contemporary sample of 203,172 UK T2DM. We identified 22 scores: 11 derived in the general population, 9 in T2DM patients, and 2 excluded T2DM patients. Over 10 years follow-up, 63,000 events occurred. The RECODE score, derived in people with T2DM, performed best for both CVD (c-statistic 0.731 (0.728,0.734), and CVD+ (0.732 (0.729,0.735)). Calibration slopes (1 indicates perfect calibration) ranged from 0.38 (95% CI 0.37; 0.39) to 1.05 (95% CI 1.03; 1.07). A simple, population specific recalibration process considerably improved performance, now ranging between 0.98 and 1.03. Risk scores performed badly in people with pre-existing CVD (c-statistic ∼0.55). CVD risk prediction scores performed worse in T2DM than in the general population, irrespective of derivation population, and of original predicted outcome. Scores performed especially poorly in patients with established CVD. A simple population specific recalibration markedly improved score performance and is recommended for future use. FUNDunding Acknowledgement Type of funding sources: Public grant(s) – EU funding. Main funding source(s): NPIF programme

Machine learning approaches as an alternative to traditional statistical methods in cardiovascular risk prediction

Machine Learning (ML) algorithms have proven promising methodologies in improving Cardiovascular (CV) risk predictors based on traditional statistics. In the present work, two case studies are reported: CV risk prediction in patients affected by Inflammatory Arthritis (IA), with attention to Psoriatic Arthritis (PsA), and patients who experienced Acute Coronary Syndrome (ACS).

Emerging techniques in atherosclerosis imaging

Atherosclerosis is a chronic immunomodulated disease that affects multiple vascular beds and results in a significant worldwide disease burden. Conventional imaging modalities focus on the morphological features of atherosclerotic disease such as the degree of stenosis caused by a lesion. Modern CT, MR and positron emission tomography scanners have seen significant improvements in the rapidity of image acquisition and spatial resolution. This has increased the scope for the clinical application of these modalities. Multimodality imaging can improve cardiovascular risk prediction by informing on the constituency and metabolic processes within the vessel wall. Specific disease processes can be targeted using novel biological tracers and smart contrast agents. These approaches have the potential to inform clinicians of the metabolic state of atherosclerotic plaque. This review will provide an overview of current imaging techniques for the imaging of atherosclerosis and how various modalities can provide information that enhances the depiction of basic morphology. This publication is the reprint with Russian translation from original: Syed MBJ, Fletcher AJ, Forsythe RO, Kaczynski J, Newby DE, Dweck MR, et al. Emerging techniques in atherosclerosis imaging. Br J Radiol 2019; 92: 20180309. DOI: https://doi.org/10.1259/bjr.20180309