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

Abstract

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 (CVRC ML ) and compares against statistically derived CVRC (CVRC Stat ) 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 CVRC Stat (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 CVRC Stat , the patients were again risk-stratified using CVRC ML 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 CVRC Stat 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), FRS cardio (AUC 0.67, P<0.01), FRS stroke (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 CVRC ML with integrated risk factors (AUC 0.88, P<0.001), a 42% increase in performance. The overall risk-stratification accuracy for the CVRC ML with integrated risk factors was 92.52% which was higher compared all the other CVRC Stat.

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

“…Such types of composite EEGS have been evaluated in our previous studies. [19][20][21]23,24,42 Results Figure SM2A and Figure SM2B). Similarly, the distributions of PA for left CB and right CB have a broad spread with participants with having higher PA compared to left and right CCA (see supplementary Figure SM2C and SM2D of the supplementary material).…”

“…The performance of risk stratification using the AECRS2.0 was evaluated using the area under the curve and "atherosclerosis aggregation factor" against an event-equivalence gold standard (EEGS), which was a combination of glycated hemoglobin (HbA 1c ), estimated glomerular filtration rate (eGFR), and carotid plaque area. 24,[42][43][44][45] A similar type of EEGS has been used as a surrogate marker of CVD/stroke in our previous studies. 20,21,23,24,42 The expansions of all the abbreviations used in this study are presented in Appendix A Table 1.…”

“…24,[42][43][44][45] A similar type of EEGS has been used as a surrogate marker of CVD/stroke in our previous studies. 20,21,23,24,42 The expansions of all the abbreviations used in this study are presented in Appendix A Table 1.…”

Morphological Carotid Plaque Area Is Associated With Glomerular Filtration Rate: A Study of South Asian Indian Patients With Diabetes and Chronic Kidney Disease

“…65,108 Total plaque area is one of the key features which can be amalgamated with grayscale plaque features for the online risk stratification using the machine learning paradigm. 109 –111 Big data framework can be adapted with all CUSIP features inclusive of TPA and cIMT (ie, cIMTave, cIMTmax, cIMTmin, IMTV, and TPA) along with grayscale features (with different characteristics having different order statistics) 112,113 in machine/deep learning framework. 114 Lastly, multimodality registrations can be carried out, which combines ultrasound with MRI for superior plaque component analysis and feature extraction, 113,115 leading to stronger risk assessment.…”

A Novel Block Imaging Technique Using Nine Artificial Intelligence Models for COVID-19 Disease Classification, Characterization and Severity Measurement in Lung Computed Tomography Scans on an Italian Cohort

“…We follow the standardized protocol for estimating the total samples needed for a certain threshold of the margin of error. The standardized protocol consisted of choosing the right parameters while applying the “power analysis” [ 63 – 66 ]. Adapting the margin of error (MoE) to be 3% , the confidence interval (CI) to be 97%, the resultant sample size (n) was computed using the following equation: where z∗ represents the z-score value ( 2.17 ) from the table of probabilities of the standard normal distribution for the desired CI, and p̂ represents the data proportion (705/(705 + 990) = 0.41 ).…”