Association of Multiorgan Computed Tomographic Phenomap With Adverse Cardiovascular Health Outcomes: The Framingham Heart Study

Clinical-transcriptional prioritization of the circulating proteome in human heart failure

Given expanding studies in epidemiology and disease-oriented human studies offering hundreds of associations between the human "ome" and disease, prioritizing molecules relevant to disease mechanisms among this growing breadth is important. Here, we link the circulating proteome to human heart failure (HF) propensity (via echocardiographic phenotyping and clinical outcomes) across the lifespan, demonstrating key pathways of fibrosis, inflammation, metabolism, and hypertrophy. We observe a broad array of genes encoding proteins linked to HF phenotypes and outcomes in clinical populations dynamically expressed at a transcriptional level in human myocardium during HF and cardiac recovery (several in a cell-specific fashion). Many identified targets do not have wide precedent in large-scale genomic discovery or human studies, highlighting the complementary roles for proteomic and tissue transcriptomic discovery to focus epidemiological targets to those relevant in human myocardium for further interrogation.

Clusters of multidimensional exercise response patterns and estimated heart failure risk in the Framingham Heart Study

AIMS

New tools are needed to identify heart failure (HF) risk earlier in its course. We evaluated the association of multidimensional cardiopulmonary exercise testing (CPET) phenotypes with subclinical risk markers and predicted long-term HF risk in a large community-based cohort.

METHODS AND RESULTS

We studied 2532 Framingham Heart Study participants [age 53 ± 9 years, 52% women, body mass index (BMI) 28.0 ± 5.3 kg/m2, peak oxygen uptake (VO2) 21.1 ± 5.9 kg/m2 in women, 26.4 ± 6.7 kg/m2 in men] who underwent maximum effort CPET and were not taking atrioventricular nodal blocking agents. Higher peak VO2 was associated with a lower estimated HF risk score (Spearman correlation r: -0.60 in men and -0.55 in women, P < 0.0001), with an observed overlap of estimated risk across peak VO2 categories. Hierarchical clustering of 26 separate CPET phenotypes (values residualized on age, sex, and BMI to provide uniformity across these variables) identified three clusters with distinct exercise physiologies: Cluster 1-impaired oxygen kinetics; Cluster 2-impaired vascular; and Cluster 3-favourable exercise response. These clusters were similar in age, sex distribution, and BMI but displayed distinct associations with relevant subclinical phenotypes [Cluster 1-higher subcutaneous and visceral fat and lower pulmonary function; Cluster 2-higher carotid-femoral pulse wave velocity (CFPWV); and Cluster 3-lower CFPWV, C-reactive protein, fat volumes, and higher lung function; all false discovery rate < 5%]. Cluster membership provided incremental variance explained (adjusted R2 increment of 0.10 in women and men, P < 0.0001 for both) when compared with peak VO2 alone in association with predicted HF risk.

CONCLUSIONS

Integrated CPET response patterns identify physiologically relevant profiles with distinct associations to subclinical phenotypes that are largely independent of standard risk factor-based assessment, which may suggest alternate pathways for prevention.

Proteomics, Human Environmental Exposure, and Cardiometabolic Risk

BACKGROUND

The biological mechanisms linking environmental exposures with cardiovascular disease pathobiology are incompletely understood. We sought to identify circulating proteomic signatures of environmental exposures and examine their associations with cardiometabolic and respiratory disease in observational cohort studies.

METHODS

We tested the relations of >6500 circulating proteins with 29 environmental exposures across the built environment, green space, air pollution, temperature, and social vulnerability indicators in ≈3000 participants of the CARDIA study (Coronary Artery Risk Development in Young Adults) across 4 centers using penalized and ordinary linear regression. In >3500 participants from FHS (Framingham Heart Study) and JHS (Jackson Heart Study), we evaluated the prospective relations of proteomic signatures of the envirome with cardiovascular disease and mortality using Cox models.

RESULTS

Proteomic signatures of the envirome identified novel/established cardiovascular disease-relevant pathways including DNA damage, fibrosis, inflammation, and mitochondrial function. The proteomic signatures of the envirome were broadly related to cardiometabolic disease and respiratory phenotypes (eg, body mass index, lipids, and left ventricular mass) in CARDIA, with replication in FHS/JHS. A proteomic signature of social vulnerability was associated with a composite of cardiovascular disease/mortality (1428 events; FHS: hazard ratio, 1.16 [95% CI, 1.08-1.24]; P=1.77×10-5; JHS: hazard ratio, 1.25 [95% CI, 1.14-1.38]; P=6.38×10-6; hazard ratio expressed as per 1 SD increase in proteomic signature), robust to adjustment for known clinical risk factors.

CONCLUSIONS

Environmental exposures are related to an inflammatory-metabolic proteome, which identifies individuals with cardiometabolic disease and respiratory phenotypes and outcomes. Future work examining the dynamic impact of the environment on human cardiometabolic health is warranted.

Exploring patient medication adherence and data mining methods in clinical big data: A contemporary review

BACKGROUND

Increasingly, patient medication adherence data are being consolidated from claims databases and electronic health records (EHRs). Such databases offer an indirect avenue to gauge medication adherence in our data-rich healthcare milieu. The surge in data accessibility, coupled with the pressing need for its conversion to actionable insights, has spotlighted data mining, with machine learning (ML) emerging as a pivotal technique. Nonadherence poses heightened health risks and escalates medical costs. This paper elucidates the synergistic interaction between medical database mining for medication adherence and the role of ML in fostering knowledge discovery.

METHODS

We conducted a comprehensive review of EHR applications in the realm of medication adherence, leveraging ML techniques. We expounded on the evolution and structure of medical databases pertinent to medication adherence and harnessed both supervised and unsupervised ML paradigms to delve into adherence and its ramifications.

RESULTS

Our study underscores the applications of medical databases and ML, encompassing both supervised and unsupervised learning, for medication adherence in clinical big data. Databases like SEER and NHANES, often underutilized due to their intricacies, have gained prominence. Employing ML to excavate patient medication logs from these databases facilitates adherence analysis. Such findings are pivotal for clinical decision-making, risk stratification, and scholarly pursuits, aiming to elevate healthcare quality.

CONCLUSION

Advanced data mining in the era of big data has revolutionized medication adherence research, thereby enhancing patient care. Emphasizing bespoke interventions and research could herald transformative shifts in therapeutic modalities.

Predicting adverse cardiac events in sarcoidosis: deep learning from automated characterization of regional myocardial remodeling

Recognizing early cardiac sarcoidosis (CS) imaging phenotypes can help identify opportunities for effective treatment before irreversible myocardial pathology occurs. We aimed to characterize regional CS myocardial remodeling features correlating with future adverse cardiac events by coupling automated image processing and data analysis on cardiac magnetic resonance (CMR) imaging datasets. A deep convolutional neural network (DCNN) was used to process a CMR database of a 10-year cohort of 117 consecutive biopsy-proven sarcoidosis patients. The maximum relevance - minimum redundancy method was used to select the best subset of all the features-24 (from manual processing) and 232 (from automated processing) left ventricular (LV) structural/functional features. Three machine learning (ML) algorithms, logistic regression (LogR), support vector machine (SVM) and multi-layer neural networks (MLP), were used to build classifiers to categorize endpoints. Over a median follow-up of 41.8 (inter-quartile range 20.4-60.5) months, 35 sarcoidosis patients experienced a total of 43 cardiac events. After manual processing, LV ejection fraction (LVEF), late gadolinium enhancement, abnormal segmental wall motion, LV mass (LVM), LVMI index (LVMI), septal wall thickness, lateral wall thickness, relative wall thickness, and wall thickness of 9 (out of 17) individual LV segments were significantly different between patients with and without endpoints. After automated processing, LVEF, end-diastolic volume, end-systolic volume, LV mass and wall thickness of 92 (out of 216) individual LV segments were significantly different between patients with and without endpoints. To achieve the best predictive performance, ML algorithms selected lateral wall thickness, abnormal segmental wall motion, septal wall thickness, and increased wall thickness of 3 individual segments after manual image processing, and selected end-diastolic volume and 7 individual segments after automated image processing. LogR, SVM and MLP based on automated image processing consistently showed better predictive accuracies than those based on manual image processing. Automated image processing with a DCNN improves data resolution and regional CS myocardial remodeling pattern recognition, suggesting that a framework coupling automated image processing with data analysis can help clinical risk stratification.

Unsupervised Learning for Automated Detection of Coronary Artery Disease Subgroups

Background The promise of precision population health includes the ability to use robust patient data to tailor prevention and care to specific groups. Advanced analytics may allow for automated detection of clinically informative subgroups that account for clinical, genetic, and environmental variability. This study sought to evaluate whether unsupervised machine learning approaches could interpret heterogeneous and missing clinical data to discover clinically important coronary artery disease subgroups. Methods and Results The Genetic Determinants of Peripheral Arterial Disease study is a prospective cohort that includes individuals with newly diagnosed and/or symptomatic coronary artery disease. We applied generalized low rank modeling and K-means cluster analysis using 155 phenotypic and genetic variables from 1329 participants. Cox proportional hazard models were used to examine associations between clusters and major adverse cardiovascular and cerebrovascular events and all-cause mortality. We then compared performance of risk stratification based on clusters and the American College of Cardiology/American Heart Association pooled cohort equations. Unsupervised analysis identified 4 phenotypically and prognostically distinct clusters. All-cause mortality was highest in cluster 1 (oldest/most comorbid; 26%), whereas major adverse cardiovascular and cerebrovascular event rates were highest in cluster 2 (youngest/multiethnic; 41%). Cluster 4 (middle-aged/healthiest behaviors) experienced more incident major adverse cardiovascular and cerebrovascular events (30%) than cluster 3 (middle-aged/lowest medication adherence; 23%), despite apparently similar risk factor and lifestyle profiles. In comparison with the pooled cohort equations, cluster membership was more informative for risk assessment of myocardial infarction, stroke, and mortality. Conclusions Unsupervised clustering identified 4 unique coronary artery disease subgroups with distinct clinical trajectories. Flexible unsupervised machine learning algorithms offer the ability to meaningfully process heterogeneous patient data and provide sharper insights into disease characterization and risk assessment. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT00380185.

Artificial intelligence in medical imaging: A radiomic guide to precision phenotyping of cardiovascular disease

ABSTRACT

Rapid technological advances in non-invasive imaging, coupled with the availability of large data sets and the expansion of computational models and power, have revolutionized the role of imaging in medicine. Non-invasive imaging is the pillar of modern cardiovascular diagnostics, with modalities such as cardiac computed tomography (CT) now recognized as first-line options for cardiovascular risk stratification and the assessment of stable or even unstable patients. To date, cardiovascular imaging has lagged behind other fields, such as oncology, in the clinical translational of artificial intelligence (AI)-based approaches. We hereby review the current status of AI in non-invasive cardiovascular imaging, using cardiac CT as a running example of how novel machine learning (ML)-based radiomic approaches can improve clinical care. The integration of ML, deep learning, and radiomic methods has revealed direct links between tissue imaging phenotyping and tissue biology, with important clinical implications. More specifically, we discuss the current evidence, strengths, limitations, and future directions for AI in cardiac imaging and CT, as well as lessons that can be learned from other areas. Finally, we propose a scientific framework in order to ensure the clinical and scientific validity of future studies in this novel, yet highly promising field. Still in its infancy, AI-based cardiovascular imaging has a lot to offer to both the patients and their doctors as it catalyzes the transition towards a more precise phenotyping of cardiovascular disease.

Machine learning for automated abdominal aortic calcification scoring of DXA vertebral fracture assessment images: A pilot study

BACKGROUND

Abdominal aortic calcification (AAC) identified on dual-energy x-ray absorptiometry (DXA) vertebral fracture assessment (VFA) lateral spine images is predictive of cardiovascular outcomes, but is time-consuming to perform manually. Whether this procedure can be automated using convolutional neural networks (CNNs), a class of machine learning algorithms used for image processing, has not been widely investigated.

METHODS

Using the Province of Manitoba Bone Density Program DXA database, we selected a random sample of 1100 VFA images from individuals qualifying for VFA as part of their osteoporosis assessment. For each scan, AAC was manually scored using the 24-point semi-quantitative scale and categorized as low (score < 2), moderate (score 2 to <6), or high (score ≥ 6). An ensemble consisting of two CNNs was developed, by training and evaluating separately on single-energy and dual-energy images. AAC prediction was performed using the mean AAC score of the two models.

RESULTS

Mean (SD) age of the cohort was 75.5 (6.7) years, 95.5% were female. Training (N = 770, 70%), validation (N = 110, 10%) and test sets (N = 220, 20%) were well-balanced with respect to baseline characteristics and AAC scores. For the test set, the Pearson correlation between the CNN-predicted and human-labelled scores was 0.93 with intraclass correlation coefficient for absolute agreement 0.91 (95% CI 0.89-0.93). Kappa for AAC category agreement (prevalence- and bias-adjusted, ordinal scale) was 0.71 (95% CI 0.65-0.78). There was complete separation of the low and high categories, without any low AAC score scans predicted to be high and vice versa.

CONCLUSIONS

CNNs are capable of detecting AAC in VFA images, with high correlation between the human and predicted scores. These preliminary results suggest CNNs are a promising method for automatically detecting and quantifying AAC.

Abdominal periaortic and renal sinus fat attenuation indices measured on computed tomography are associated with metabolic syndrome

OBJECTIVES

To investigate the association between abdominal periaortic (APA) and renal sinus (RS) fat attenuation index (FAI) measured on MDCT and metabolic syndrome in non-obese and obese individuals.

METHODS

Visceral, subcutaneous, RS, and APA adipose tissue were measured in preoperative abdominal CT scans of individuals who underwent donor nephrectomy (n = 84) or bariatric surgery (n = 155). FAI was defined as the mean attenuation of measured fat volume. Participants were categorized into four groups: non-obese without metabolic syndrome (n = 64), non-obese with metabolic syndrome (n = 25), obese without metabolic syndrome (n = 21), and obese with metabolic syndrome (n = 129). The volume and FAI of each fat segment were compared among the groups. Receiver operator characteristics curve analysis was used to assess the association between the FAIs and metabolic syndrome.

RESULTS

FAIs of all abdominal fat segments were significantly lower in the obese group than in the non-obese group (p < 0.001). RS, APA, and the visceral adipose tissue FAIs were significantly lower in participants with metabolic syndrome than in those without metabolic syndrome in the non-obese group (p < 0.001, p = 0.006, and p < 0.001, respectively). The area under the curve for predicting metabolic syndrome was significantly higher for APA FAI (0.790) than subcutaneous, visceral, and RS FAI in all groups (0.649, 0.647, and 0.655, respectively).

CONCLUSION

Both metabolic syndrome and obesity were associated with lower RS and APA adipose tissue FAI, and APA FAI performed best for predicting metabolic syndrome.

KEY POINTS

• The volume and FAI of RS, APA, and visceral adipose tissue showed opposite trends with regard to metabolic syndrome or obesity. • Both metabolic syndrome and obesity were associated with lower RS FAI and APA FAI. • APA FAI performed best for predicting metabolic syndrome among FAIs of abdominal fat segments.

Automated Muscle Measurement on Chest CT Predicts All-Cause Mortality in Older Adults From the National Lung Screening Trial

BACKGROUND

Muscle metrics derived from computed tomography (CT) are associated with adverse health events in older persons, but obtaining these metrics using current methods is not practical for large datasets. We developed a fully automated method for muscle measurement on CT images. This study aimed to determine the relationship between muscle measurements on CT with survival in a large multicenter trial of older adults.

METHOD

The relationship between baseline paraspinous skeletal muscle area (SMA) and skeletal muscle density (SMD) and survival over 6 years was determined in 6,803 men and 4,558 women (baseline age: 60-69 years) in the National Lung Screening Trial (NLST). The automated machine learning pipeline selected appropriate CT series, chose a single image at T12, and segmented left paraspinous muscle, recording cross-sectional area and density. Associations between SMA and SMD with all-cause mortality were determined using sex-stratified Cox proportional hazards models, adjusted for age, race, height, weight, pack-years of smoking, and presence of diabetes, chronic lung disease, cardiovascular disease, and cancer at enrollment.

RESULTS

After a mean 6.44 ± 1.06 years of follow-up, 635 (9.33%) men and 265 (5.81%) women died. In men, higher SMA and SMD were associated with a lower risk of all-cause mortality, in fully adjusted models. A one-unit standard deviation increase was associated with a hazard ratio (HR) = 0.85 (95% confidence interval [CI] = 0.79, 0.91; p < .001) for SMA and HR = 0.91 (95% CI = 0.84, 0.98; p = .012) for SMD. In women, the associations did not reach significance.

CONCLUSION

Higher paraspinous SMA and SMD, automatically derived from CT exams, were associated with better survival in a large multicenter cohort of community-dwelling older men.

Comprehensive Metabolic Phenotyping Refines Cardiovascular Risk in Young Adults

BACKGROUND

Whereas cardiovascular disease (CVD) metrics define risk in individuals >40 years of age, the earliest lesions of CVD appear well before this age. Despite the role of metabolism in CVD antecedents, studies in younger, biracial populations to define precise metabolic risk phenotypes are lacking.

METHODS

We studied 2330 White and Black young adults (mean age, 32 years; 45% Black) in the CARDIA study (Coronary Artery Risk Development in Young Adults) to identify metabolite profiles associated with an adverse CVD phenome (myocardial structure/function, fitness, vascular calcification), mechanisms, and outcomes over 2 decades. Statistical learning methods (elastic nets/principal components analysis) and Cox regression generated parsimonious, metabolite-based risk scores validated in >1800 individuals in the Framingham Heart Study.

RESULTS

In the CARDIA study, metabolite profiles quantified in early adulthood were associated with subclinical CVD development over 20 years, specifying known and novel pathways of CVD (eg, transcriptional regulation, brain-derived neurotrophic factor, nitric oxide, renin-angiotensin). We found 2 multiparametric, metabolite-based scores linked independently to vascular and myocardial health, with metabolites included in each score specifying microbial metabolism, hepatic steatosis, oxidative stress, nitric oxide modulation, and collagen metabolism. The metabolite-based vascular scores were lower in men, and myocardial scores were lower in Black participants. Over a nearly 25-year median follow-up in CARDIA, the metabolite-based vascular score (hazard ratio, 0.68 per SD [95% CI, 0.50-0.92]; P=0.01) and myocardial score (hazard ratio, 0.60 per SD [95% CI, 0.45-0.80]; P=0.0005) in the third and fourth decades of life were associated with clinical CVD with a synergistic association with outcome (Pinteraction=0.009). We replicated these findings in 1898 individuals in the Framingham Heart Study over 2 decades, with a similar association with outcome (including interaction), reclassification, and discrimination. In the Framingham Heart Study, the metabolite scores exhibited an age interaction (P=0.0004 for a combined myocardial-vascular score with incident CVD), such that young adults with poorer metabolite-based health scores had highest hazard of future CVD.

CONCLUSIONS

Metabolic signatures of myocardial and vascular health in young adulthood specify known/novel pathways of metabolic dysfunction relevant to CVD, associated with outcome in 2 independent cohorts. Efforts to include precision measures of metabolic health in risk stratification to interrupt CVD at its earliest stage are warranted.

Utilizing Fully Automated Abdominal CT-Based Biomarkers for Opportunistic Screening for Metabolic Syndrome in Adults Without Symptoms

OBJECTIVE

Metabolic syndrome describes a constellation of reversible cardiometabolic abnormalities associated with cardiovascular risk and diabetes. The present study investigates the use of fully automated abdominal CT-based biometric measures for opportunistic identification of metabolic syndrome in adults without symptoms.

MATERIALS AND METHODS

International Diabetes Federation criteria were applied to a cohort of 9223 adults without symptoms who underwent unenhanced abdominal CT. After patients with insufficient clinical data for diagnosis were excluded, the final cohort consisted of 7785 adults (mean age, 57.0 years; 4361 women and 3424 men). Previously validated and fully automated CT-based algorithms for quantifying muscle, visceral and subcutaneous fat, liver fat, and abdominal aortic calcification were applied to this final cohort.

RESULTS

A total of 738 subjects (9.5% of all subjects; mean age, 56.7 years; 372 women and 366 men) met the clinical criteria for metabolic syndrome. Subsequent major cardiovascular events occurred more frequently in the cohort with metabolic syndrome (p < 0.001). Significant differences were observed between the two groups for all CT-based biomarkers (p < 0.001). Univariate L1-level total abdominal fat (area under the ROC curve [AUROC] = 0.909; odds ratio [OR] = 27.2), L3-level skeletal muscle index (AUROC = 0.776; OR = 5.8), and volumetric liver attenuation (AUROC = 0.738; OR = 5.1) performed well when compared with abdominal aortic calcification scoring (AUROC = 0.578; OR = 1.6). An L1-level total abdominal fat threshold of 460.6 cm² was 80.1% sensitive and 85.4% specific for metabolic syndrome. For women, the AUROC was 0.930 when fat and muscle measures were combined.

CONCLUSION

Fully automated quantitative tissue measures of fat, muscle, and liver derived from abdominal CT scans can help identify individuals who are at risk for metabolic syndrome. These visceral measures can be opportunistically applied to CT scans obtained for other clinical indications, and they may ultimately provide a more direct and useful definition of metabolic syndrome.

Gustatory Function and the Uremic Toxin, Phosphate, Are Modulators of the Risk of Vascular Calcification among Patients with Chronic Kidney Disease: A Pilot Study

Patients with chronic kidney disease (CKD) have an increased risk of vascular calcification (VC), including aortic arch calcification (AAC). Few investigated the influence of gustatory function on the probability of having VC. We examined whether gustatory function results modulated the probability of having VC in patients with CKD. We prospectively enrolled adults with CKD (estimated glomerular filtration rate <60 mL/min/1.73 m²), with their AAC rated semi-quantitatively and gustatory function assessed by objective and subjective approaches. Multiple logistic regression was used to analyze the relationship between gustatory function results and AAC. Those with AAC had significantly better objective gustatory function in aggregate scores (p = 0.039) and categories (p = 0.022) and less defective bitter taste (p = 0.045) and scores (p = 0.037) than those without. Multiple regression analyses showed that higher aggregate scores (odds ratio (OR) 1.288, p = 0.032), or better gustatory function, and higher bitter taste scores (OR 2.558, p = 0.019) were each associated with a higher probability of having AAC among CKD patients; such an association was modulated by serum phosphate levels. In conclusion, better gustatory function was independently correlated with having AAC among CKD patients. A follow-up of VC severity may be an underrecognized component of care for CKD patients with a preserved gustatory function.

Unsupervised Cluster Analysis of Patients With Aortic Stenosis Reveals Distinct Population With Different Phenotypes and Outcomes

BACKGROUND

There is a lack of studies investigating the heterogeneity of patients with aortic stenosis (AS). We explored whether cluster analysis identifies distinct subgroups with different prognostic significances in AS.

METHODS

Newly diagnosed patients with moderate or severe AS were prospectively enrolled between 2013 and 2016 (n=398, mean 71 years, 55% male). Among demographics, laboratory, and echocardiography parameters (n=32), 11 variables were selected through dimension reduction and used for unsupervised clustering. Phenotypes and causes of mortality were compared between the clusters.

RESULTS

Three clusters with markedly different features were identified. Cluster 1 (n=60) was predominantly associated with cardiac dysfunction, cluster 2 (n=86) consisted of elderly with comorbidities, especially end-stage renal disease, whereas cluster 3 (n=252) demonstrated neither cardiac dysfunction nor comorbidities. Although AS severity did not differ, there was a significant difference in adverse outcomes between the clusters during a median 2.4 years follow-up (mortality rate, 13.3% versus 19.8% versus 6.0% for cluster 1, 2, and 3, P<0.001). Particularly, compared with cluster 3, cluster 1 was associated with only cardiac mortality (adjusted hazard ratio, 7.37 [95% CI, 2.00-27.13]; P=0.003), whereas cluster 2 was associated with higher noncardiac mortality (adjusted hazard ratio, 3.35 [95% CI, 1.26-8.90]; P=0.015). Phenotypes and association of clusters with specific outcomes were reproduced in an independent validation cohort (n=262).

CONCLUSIONS

Unsupervised cluster analysis of patients with AS revealed 3 distinct groups with different causes of death. This provides a new perspective in the categorization of patients with AS that takes into account comorbidities and extravalvular cardiac dysfunction.

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

Background

Body CT scans are frequently performed for a wide variety of clinical indications, but potentially valuable biometric information typically goes unused. We investigated the prognostic ability of automated CT-based body composition biomarkers derived from previously-developed deep-learning and feature-based algorithms for predicting major cardiovascular events and overall survival in an adult screening cohort, compared with clinical parameters.

Methods

Mature and fully-automated CT-based algorithms with pre-defined metrics for quantifying aortic calcification, muscle density, visceral/subcutaneous fat, liver fat, and bone mineral density (BMD) were applied to a generally-healthy asymptomatic outpatient cohort of 9223 adults (mean age, 57.1 years; 5152 women) undergoing abdominal CT for routine colorectal cancer screening. Longitudinal clinical follow-up (median, 8.8 years; IQR, 5.1-11.6 years) documented subsequent major cardiovascular events or death in 19.7% (n=1831). Predictive ability of CT-based biomarkers was compared against the Framingham Risk Score (FRS) and body mass index (BMI).

Findings

Significant differences were observed for all five automated CT-based body composition measures according to adverse events (p<0.001). Univariate 5-year AUROC (with 95% CI) for automated CT-based aortic calcification, muscle density, visceral/subcutaneous fat ratio, liver density, and vertebral density for predicting death were 0.743(0.705-0.780)/0.721(0.683-0.759)/0.661(0.625-0.697)/0.619 (0.582-0.656)/0.646(0.603-0.688), respectively, compared with 0.499(0.454-0.544) for BMI and 0.688(0.650-0.727) for FRS (p<0.05 for aortic calcification vs. FRS and BMI); all trends were similar for 2-year and 10-year ROC analyses. Univariate hazard ratios (with 95% CIs) for highest-risk quartile versus others for these same CT measures were 4.53(3.82-5.37) /3.58(3.02-4.23)/2.28(1.92-2.71)/1.82(1.52-2.17)/2.73(2.31-3.23), compared with 1.36(1.13-1.64) and 2.82(2.36-3.37) for BMI and FRS, respectively. Similar significant trends were observed for cardiovascular events. Multivariate combinations of CT biomarkers further improved prediction over clinical parameters (p<0.05 for AUROCs). For example, by combining aortic calcification, muscle density, and liver density, the 2-year AUROC for predicting overall survival was 0.811 (0.761-0.860).

Interpretation

Fully-automated quantitative tissue biomarkers derived from CT scans can outperform established clinical parameters for pre-symptomatic risk stratification for future serious adverse events, and add opportunistic value to CT scans performed for other indications.