Automated CT biomarkers for opportunistic prediction of future cardiovascular events and mortality in an asymptomatic screening population: a retrospective cohort study

Abstract

Background Body CT scans are frequently done for a wide range of clinical indications, but potentially valuable biometric information typically goes unused. We aimed to compare the prognostic ability of automated CT-based body composition biomarkers derived from previously developed deep-learning and feature-based algorithms with that of clinical parameters (Framingham risk score [FRS] and body-mass index [BMI]) for predicting major cardiovascular events and overall survival in an adult screening cohort.Methods In this retrospective cohort study, mature and fully automated CT-based algorithms with predefined metrics for quantifying aortic calcification, muscle density, ratio of visceral to subcutaneous fat, liver fat, and bone mineral density were applied to a generally healthy asymptomatic outpatient cohort of adults aged 18 years or older undergoing abdominal CT for routine colorectal cancer screening. To assess the association between the predictive measures (CT-based vs FRS and BMI) and downstream adverse events (death or myocardial infarction, cerebrovascular accident, or congestive heart failure subsequent to CT scanning), we used both an event-free survival analysis and logistic regression to compute receiver operating characteristic curves (ROCs) . Findings 9223 people (mean age 57•1 years [SD 7•8]; 5152 [56%] women and 4071 [44%] men) who underwent CT scans between April, 2004, and December, 2016, were included in this analysis. In the longitudinal clinical follow-up (median 8•8 years [IQR 5•1-11•6]), subsequent major cardiovascular events or death occurred in 1831 (20%) patients. Significant differences were observed for all five automated CT-based body composition measures according to adverse events (p<0•001). Univariate 5-year area under the ROC (AUROC) values for predicting death were 0•743 (95% CI 0•705-0•780) for aortic calcification, 0•721 (0•683-0•759) for muscle density, 0•661 (0•625-0•697) for ratio of visceral to subcutaneous fat, 0•619 (0•582-0•656) for liver density, and 0•646 (0•603-0•688) for vertebral density, compared with 0•499 (0•454-0•544) for BMI and 0•688 (0•650-0•727) for FRS.Univariate hazard ratios for highestrisk quartile versus others for these same CT measures were 4•53 (95% CI 3•82-5•37) for aortic calcification, 3•58 (3•02-4•23) for muscle density, 2•28 (1•92-2•71) for the ratio of visceral to subcutaneous fat, 1•82 (1•52-2•17) for liver density, and 2•73 (2•31-3•23) for vertebral density, compared with 1•36 (1•13-1•64) for BMI and 2•82 (2•36-3•37) for FRS. Multivariate combinations of CT biomarkers further improved prediction over clinical parameters (p<0•05 for AUROCs). For example, the 2-year AUROC from combining aortic calcification, muscle density, and liver density for predicting death was 0•811 (95% CI 0•761-0•860).Interpretation Fully automated quantitative tissue biomarkers derived from CT scans can outperform established clinical parameters for presymptomatic risk stratification for future serious adverse events and add opportunistic value to CT scans performed fo...

Assessing the Role of Pericardial Fat as a Biomarker Connected to Coronary Calcification—A Deep Learning Based Approach Using Fully Automated Body Composition Analysis

“…As Pickhardt et al point out, BCA can add great opportunistic value, and even outperform established clinical parameters, for pre-symptomatic risk analysis when deployed to extract individual biometric information from medical images for a variety of clinical indications [ 20 ]. The employed DL-based approach provided an efficient biomarker extraction of EAT, PAT and a variety of other tissue biomarkers on a large clinical cohort in a precise manner.…”

“…Artificial Intelligence is an emerging tool for biomarker extraction and precisely quantifying biomarkers in large-scale study cohorts [ 19 , 20 , 21 ]. Some deep learning-based (DL) approaches to EAT have already been demonstrated [ 16 , 21 ].…”

Muscle Loss Is Associated with Overall Survival in Patients with Metastatic Colorectal Cancer Independent of Tumor Mutational Status and Weight Loss

“…This study relies on an innovative method to obtain body composition data for translational research. We demonstrate that machine learning enables a fully automated workflow to analyze body composition on serial CT scans obtained as part of routine cancer care [17, 27–30]. Without segmentation tools, change in skeletal muscle and adipose tissue is difficult to appreciate as illustrated in Figure 2.…”

Opportunistic Assessment of Ischemic Heart Disease Risk Using Abdominopelvic Computed Tomography and Medical Record Data: a Multimodal Explainable Artificial Intelligence Approach

“…The use of BC biomarkers derived from abdominal CT imaging for cardiovascular risk assessment has been explored in the past. Pickhardt et al extracted univariate metrics from CT colonography such as liver and muscle radiodensity, abdominal aortic calcification, and VAT/SAT ratio combined with FRS in asymptomatic individuals and found an improvement in 2-year cardiovascular event prediction AUROC of .77 compared to .71 using FRS alone 46 . While highlighting the value of imaging biomarkers in cardiovascular risk assessment, their methods were developed using CT colonography, an imaging modality that remains underutilized 47 .…”