Deep Learning-Based Assessment of Built Environment From Satellite Images and Cardiometabolic Disease Prevalence.

Importance: Built environment plays an important role in development of cardiovascular disease. Large scale, pragmatic evaluation of built environment has been limited owing to scarce data and inconsistent data quality. Objective: To investigate the association between image-based built environment and the prevalence of cardiometabolic disease in urban cities. Design, Setting, and Participants: This cross-sectional study used features extracted from Google satellite images (GSI) to measure the built environment and link them with prevalence of cardiometabolic disease. Convolutional neural networks, light gradient-boosting machines, and activation maps were used to assess the association with health outcomes and identify feature associations with coronary heart disease (CHD), stroke, and chronic kidney disease (CKD). The study obtained aerial images from GSI covering census tracts in 7 cities (Cleveland, Ohio; Fremont, California; Kansas City, Missouri; Detroit, Michigan; Bellevue, Washington; Brownsville, Texas; and Denver, Colorado). The study used census tract-level data from the US Centers for Disease Control and Prevention's 500 Cities project. The data were originally collected from the Behavioral Risk Factor Surveillance System that surveyed people 18 years and older across the country. Analyses were conducted from February to December 2022. Exposures: GSI images of built environment and cardiometabolic disease prevalence. Main Outcomes and Measures: Census tract-level estimated prevalence of CHD, stroke, and CKD based on image-based built environment features. Results: The study obtained 31 786 aerial images from GSI covering 789 census tracts. Built environment features extracted from GSI using machine learning were associated with prevalence of CHD (R2 = 0.60), stroke (R2 = 0.65), and CKD (R2 = 0.64). The model performed better at distinguishing differences between cardiometabolic prevalence between cities than within cities (eg, highest within-city R2 = 0.39 vs between-city R2 = 0.64 for CKD). Addition of GSI features both outperformed and improved the model that only included age, sex, race, income, education, and composite indices for social determinants of health (R2 = 0.83 vs R2 = 0.76 for CHD; P <.001). Activation maps from the features revealed certain health-related built environment such as roads, highways, and railroads and recreational facilities such as amusement parks, arenas, and baseball parks. Conclusions and Relevance: In this cross-sectional study, a significant portion of cardiometabolic disease prevalence was associated with GSI-based built environment using convolutional neural networks.

Quantifying lead-attributable cardiovascular disease burden in the United States.

Lead exposure has been linked to a myriad of cardiovascular diseases. Utilizing data from the 2019 Global Burden of Disease Study, we quantified age-standardized lead exposure-related mortality and disability-adjusted life years (DALYs) in the United States between 1990 and 2019. Our analysis revealed a substantial reduction in age-standardized cardiovascular disease (CVD) mortality attributable to lead exposure by 60 % (from 7.4 to 2.9 per 100,000), along with a concurrent decrease in age-standardized CVD DALYs by 66 % (from 143.2 to 48.7 per 100,000).

Influence of social vulnerability index on Medicare beneficiaries' expenditures upon discharge.

Medicare beneficiaries' healthcare spending varies across geographical regions, influenced by availability of medical resources and institutional efficiency. We aimed to evaluate whether social vulnerability influences healthcare costs among Medicare beneficiaries. Multivariable regression analyses were conducted to determine whether the social vulnerability index (SVI), released by the Centers for Disease Control and Prevention (CDC), was associated with average submitted covered charges, total payment amounts, or total covered days upon hospital discharge among Medicare beneficiaries. We used information from discharged Medicare beneficiaries from hospitals participating in the Inpatient Prospective Payment System. Covariate adjustment included demographic information consisting of age groups, race/ethnicity, and Hierarchical Condition Category risk score. The regressions were performed with weights proportioned to the number of discharges. Average submitted covered charges significantly correlated with SVI (ß = 0.50, p < 0.001) in the unadjusted model and remained significant in the covariates-adjusted model (ß = 0.25, p = 0.039). The SVI was not significantly associated with the total payment amounts (ß = -0.07, p = 0.238) or the total covered days (ß = 0.00, p = 0.953) in the adjusted model. Regional variations in Medicare beneficiaries' healthcare spending exist and are influenced by levels of social vulnerability. Further research is warranted to fully comprehend the impact of social determinants on healthcare costs.

Artificial intelligence-based assessment of built environment from Google Street View and coronary artery disease prevalence.

BACKGROUND AND AIMS: Built environment plays an important role in the development of cardiovascular disease. Tools to evaluate the built environment using machine vision and informatic approaches have been limited. This study aimed to investigate the association between machine vision-based built environment and prevalence of cardiometabolic disease in US cities. METHODS: This cross-sectional study used features extracted from Google Street View (GSV) images to measure the built environment and link them with prevalence of coronary heart disease (CHD). Convolutional neural networks, linear mixed-effects models, and activation maps were utilized to predict health outcomes and identify feature associations with CHD at the census tract level. The study obtained 0.53 million GSV images covering 789 census tracts in seven US cities (Cleveland, OH; Fremont, CA; Kansas City, MO; Detroit, MI; Bellevue, WA; Brownsville, TX; and Denver, CO). RESULTS: Built environment features extracted from GSV using deep learning predicted 63% of the census tract variation in CHD prevalence. The addition of GSV features improved a model that only included census tract-level age, sex, race, income, and education or composite indices of social determinant of health. Activation maps from the features revealed a set of neighbourhood features represented by buildings and roads associated with CHD prevalence. CONCLUSIONS: In this cross-sectional study, the prevalence of CHD was associated with built environment factors derived from GSV through deep learning analysis, independent of census tract demographics. Machine vision-enabled assessment of the built environment could potentially offer a more precise approach to identify at-risk neighbourhoods, thereby providing an efficient avenue to address and reduce cardiovascular health disparities in urban environments.

Sex-specific heart failure burden across the United States: Global burden of disease 1990-2019.

BACKGROUND: Heart failure (HF) has unique aspects that vary by biological sex. Thus, understanding sex-specific trends of HF in the US population is crucial to develop targeted interventions. We aimed to analyze the burden of HF in female and male patients across the US, from 1990 to 2019. METHODS: Using the Global Burden of Disease (GBD) study data from 2019, we performed an analysis of the burden of HF from 1990-2019, across US states and regions. The GBD defined HF through studies that used symptom-based criteria and expressed the burden of HF as the age-adjusted prevalence and years lived with disability (YLDs) rates per 100,000 individuals. RESULTS: The age-adjusted prevalence of HF for the US in 2019 was 926.2 (95% UI [799.6, 1,079.0]) for females and 1,291.2 (95% UI [1,104.1, 1,496.8]) for males. Notably, our findings also highlight cyclic fluctuations in HF prevalence over time, with peaks occurring in the mid-1990s and around 2010, while reaching their lowest points in around 2000 and 2018. Among individuals >70 years of age, the absolute number of individuals with HF was higher in females, and this age group doubled the absolute count between 1990 and 2019. Comparing 1990-1994 to 2015-2019, 10 states had increased female HF prevalence, while only 4 states increased male prevalence. Overall, Western states had the greatest relative decline in HF burden, in both sexes. CONCLUSION: The burden of HF in the US is high, although the magnitude of this burden varies according to age, sex, state, and region. There is a significant increase in the absolute number of individuals with HF, especially among women >70 years, expected to continue due to the aging population.

Coronary artery calcium scoring for cardiovascular risk assessment in patients with inflammatory bowel disease.

BACKGROUND: Inflammatory bowel disease (IBD) is associated with higher incidence of atherosclerotic cardiovascular disease (ASCVD). Data investigating the role of coronary artery calcium (CAC) scoring in identifying subclinical atherosclerotic disease in IBD patients is scarce. METHODS: Using data obtained from the CLARIFY registry, a prospective study of no-charge coronary artery calcium (CAC) testing at University Hospitals, we reviewed patients with ulcerative colitis (UC) or Crohn's disease (CD) who underwent CAC scoring from 2014 to 2020. We investigated the concordance between CAC risk and 10-year estimated ASCVD risk by AHA/ACC pooled cohort equation using pre-established thresholds for statin prescription (CAC≥100, 10-year ASCVD risk ≥7.5%). We additionally investigated the association between CAC, preventive therapy initiation and Major Adverse Cardiovascular Events (MACE). RESULTS: A total of 369 patients with IBD were included (174 UC, 195 CD), with median age of 60 years. The median CAC score was 14.9 with no significant difference between UC and CD (P = .76). Overall, 151 (41%) had CAC of 0, 108 (29%) had CAC 1-99, 61 (17%) had CAC 100 to 399, and 49 (13%) had CAC ≥400 with no difference in CAC distribution between CD and UC (P = .17). There was no difference in median CAC between IBD or age/sex-matched controls (P = .34). Approximately half of the patients (52%) with IBD had 10-year estimated ASCVD risk of 7.5% or higher. Among patients with ASCVD risk <7.5% (n = 163), 29 (18%) had CAC≥100 and among patients with ASCVD risk ≥7.5% (n = 178), 102 (57%) had CAC <100. There was no difference between CAC<100 vs CAC≥100 with respect to CRP, use of immunosuppressive or amino-salicylate therapy, IBD severity or complications. CAC score (AUROC 0.67 [0.56-0.78]), but not PCE ASCVD risk (AUROC 0.60 [0.48-0.73]), was predictive of MACE. The best cut-off for CAC score was 76 (sensitivity = 60%, specificity = 69%), and was associated with 4-fold increase in MACE (Hazard Ratio 4.0 [2.0-8.1], P < .001). CONCLUSION: Subclinical atherosclerosis, as evaluated by CAC scoring, is prevalent in patients with IBD, and is associated with cardiovascular events. Further studies are needed to understand underlying biological processes of increased atherosclerotic disease risk among adults with IBD.

Alzheimer`s disease mortality in the United States: Cross-sectional analysis of county-level socio-environmental factors.

BACKGROUND: Geographical disparities in mortality among Alzheimer`s disease (AD) patients have been reported and complex sociodemographic and environmental determinants of health (SEDH) may be contributing to this variation. Therefore, we aimed to explore high-risk SEDH factors possibly associated with all-cause mortality in AD across US counties using machine learning (ML) methods. METHODS: We performed a cross-sectional analysis of individuals ≥65 years with any underlying cause of death but with AD in the multiple causes of death certificate (ICD-10,G30) between 2016 and 2020. Outcomes were defined as age-adjusted all-cause mortality rates (per 100,000 people). We analyzed 50 county-level SEDH and Classification and Regression Trees (CART) was used to identify specific county-level clusters. Random Forest, another ML technique, evaluated variable importance. CART`s performance was validated using a "hold-out" set of counties. RESULTS: Overall, 714,568 individuals with AD died due to any cause across 2,409 counties during 2016-2020. CART identified 9 county clusters associated with an 80.1% relative increase of mortality across the spectrum. Furthermore, 7 SEDH variables were identified by CART to drive the categorization of clusters, including High School Completion (%), annual Particulate Matter 2.5 Level in Air, live births with Low Birthweight (%), Population under 18 years (%), annual Median Household Income in US dollars ($), population with Food Insecurity (%), and houses with Severe Housing Cost Burden (%). CONCLUSION: ML can aid in the assimilation of intricate SEDH exposures associated with mortality among older population with AD, providing opportunities for optimized interventions and resource allocation to reduce mortality among this population.

Implementing a Sustainability Framework in Healthcare: A Three-Lens Framework.

The list of sustainability issues that can pose risks to people, society, and healthcare organizations (HCOs) has been steadily growing over the last decade. HCOs and related industries are responsible for greenhouse gas emissions, pollutants, and unsustainable practices with a substantial death and disability footprint. There is an urgent need for health care transformation that advances quality, safety and value in order to address the public health crisis arising from healthcare pollution and to the meet rapidly moving deadlines to avert climate change. Sustainability initiatives are yet further linked with diversity, equity, inclusion, and justice, with HCOs being asked to disclose their commitments to these as part of "good" environmental society and governance (ESG) practices. In this paper, we review approaches to embed sustainability as a core strategy in HCOs and discuss implementation from the standpoint of a three-lens political, strategic, and cultural framework. We discuss solutions to embed sustainability and to facilitate buy-in, and provide a pathway to operationalize sustainability initiatives.

Cardiovascular disease burden attributable to non-optimal temperature: analysis of the 1990-2019 global burden of disease.

AIMS: Extreme temperatures are increasingly experienced as a result of climate change. Both high and low temperatures, impacted by climate change, have been linked with cardiovascular disease (CVD). Global estimates on non-optimal temperature-related CVD are not known. The authors investigated global trends of temperature-related CVD burden over the last three decades. METHODS AND RESULTS: The authors utilized the 1990-2019 global burden of disease methodology to investigate non-optimal temperature, low temperature- and high temperature-related CVD deaths, and disability-adjusted life years (DALYs) globally. Non-optimal temperatures were defined as above (high temperature) or below (low temperature) the location-specific theoretical minimum-risk exposure level or the temperature associated with the lowest mortality rates. Analyses were later stratified by sociodemographic index (SDI) and world regions. In 2019, non-optimal temperature contributed to 1 194 196 (95% uncertainty interval [UI]: 963 816-1 425 090) CVD deaths and 21 799 370 (95% UI: 17 395 761-25 947 499) DALYs. Low temperature contributed to 1 104 200 (95% UI: 897 783-1 326 965) CVD deaths and 19 768 986 (95% UI: 16 039 594-23 925 945) DALYs. High temperature contributed to 93 095 (95% UI: 10 827-158 386) CVD deaths and 2 098 989 (95% UI: 146 158-3 625 564) DALYs. Between 1990 and 2019, CVD deaths related to non-optimal temperature increased by 45% (95% UI: 32-63%), low temperature by 36% (95% UI: 25-48%), and high temperature by 600% (95% UI: -1879-2027%). Non-optimal temperature- and high temperature-related CVD deaths increased more in countries with low income than countries with high income. CONCLUSION: Non-optimal temperatures are significantly associated with global CVD deaths and DALYs, underscoring the significant impact of temperature on public health.

The paper discusses the relationship between non-optimal temperature and cardiovascular disease (CVD) and presents the first-to-date quantification of the global temperature-related CVD burden. Key findings include: Non-optimal temperatures were responsible for a significant proportion of global cardiovascular deaths between 1990 and 2019.People in lower socioeconomic regions were more vulnerable to the effects of non-optimal temperature on CVD than those in higher socioeconomic regions.

Disparities in statin prescription among patients with severe hypercholesterolemia in an integrated healthcare system.

Background: Severe hypercholesterolemia (SH), defined as a low-density lipoprotein cholesterol (LDL-C) level ≥ 190 mg/dl, is associated with an increased risk for premature atherosclerotic cardiovascular disease. Despite guideline recommendations, many patients with severe hypercholesterolemia remain untreated. We conducted an observational analysis of a large pool of SH patients, exploring demographic and social factors contributing to disparities in the prescription of statin and other lipid-lowering therapies. Methods: We included all adults (age 18 or older) in the University Hospitals Health Care System, with an LDL-C ≥ 190 mg/dl on a lipid profile drawn between January 2, 2014, and March 15, 2022. Variables were compared across relevant categories of age, gender, race and ethnicity, medical history, prescription medication status, insurance type, and provider referral type. We used the Fischer exact test and Pearson Chi-square (χ 2) for variable comparisons. Results: A total of 7,942 patients were included in the study. The median age was 57 [IQR 48-66] years with 64% female, and 17% Black patients. Only 58% of the total cohort was prescribed statin therapy. Higher age was independently associated with a higher likelihood of receiving a statin, with an odds ratio of 1.25 (95% CI [1.21 - 1.30] per 10 years, p<0.001). Additional factors that were associated with higher rates of statin prescription in patients with SH were Black race (OR 1.90, 95% CI [1.65 - 2.17], p<0.001), smoking (OR 2.42, 95% CI [2.17 -2.70], p<0.001), and presence of diabetes (OR 3.88, 95% CI [3.27 - 4.60], p<0.001). Similar trends were also seen with other lipid-lowering therapies such as ezetimibe and fibrates. Conclusions: In our Northeast Ohio healthcare system, less than two-thirds of patients with severe hypercholesterolemia are prescribed a statin. Statin prescription rates were highly dependent on age and the presence of additional ASCVD risk factors.

Coronary Artery Calcium Scoring for Risk Assessment in Patients With Severe Hypercholesterolemia.

The American College of Cardiology and the American Heart Association guidelines recommend treatment of patients with severe hypercholesterolemia (low-density lipoprotein cholesterol [LDL-C] ≥190 mg/100 ml) with a high-intensity statin. However, atherosclerotic cardiovascular disease (ASCVD) risk, even among those with severe hypercholesterolemia, is heterogeneous, and coronary artery calcium (CAC) scoring may be used to clarify risk. We sought to evaluate CAC in patients with severe hypercholesterolemia and measure its impact on real-world statin prescriptions. We identified patients with at least 1 LDL-C ≥190 mg100 ml who had a CAC scoring in the Community Benefit of No-Charge Calcium Score Screening Program (CLARIFY) study (NCT04075162) between 2014 and 2020. We explored the CAC distribution, factors associated with CAC >0, and ASCVD risk (myocardial infarction, stroke, revascularization, death). A total of 1,904 patients (1.257 women, aged 57.8 ± 9.3 years) with severe hypercholesterolemia were included. LDL-C ranged from 190 to 524 mg100 ml (mean 215.5 ± 27 mg100 ml). A total of 864 patients (45.4%) had CAC = 0 and 1,561 (82%) had CAC <100. In patients with LDL-C ≥250 mg100 ml, 67 (36.6%) had CAC = 0. Age, male gender, smoking, diabetes, systolic blood pressure, and obesity (ps ≤0.001) were associated with CAC >0. In patients with LDL-C ≥190 mg100 ml, CAC was associated with a higher risk for ASCVD events (CAC ≥100 vs CAC <100, hazard ratio 3.57 [1.81 to 7.04], p <0.001). A higher CAC category was associated with increased statin use after CAC scoring (p <0.001). In patients with severe hypercholesterolemia, 45% had CAC = 0, which was associated with a significantly lower ASCVD risk. CAC was associated with statin prescription and cholesterol lowering. In conclusion, CAC scoring may be used to clarify ASCVD risk in this heterogeneous population with severe hypercholesterolemia.

Burden of cardiovascular disease attributable to particulate matter pollution in the eastern Mediterranean region: analysis of the 1990-2019 global burden of disease.

AIMS: Particulate matter pollution is the most important environmental mediator of global cardiovascular morbidity and mortality. Air pollution evidence from the Eastern Mediterranean Region (EMR) is limited, owing to scarce local studies, and the omission from multinational studies. We sought to investigate trends of particulate matter (PM2.5)-related cardiovascular disease (CVD) burden in the EMR from 1990 to 2019. METHODS AND RESULTS: We used the 1990-2019 global burden of disease methodology to investigate total PM2.5, ambient PM2.5, and household PM2.5-related CVD deaths and disability-adjusted life years (DALYs) and cause-specific CVD mortality in the EMR. The average annual population-weighted PM2.5 exposure in EMR region was 50.3 µg/m3 [95% confidence interval (CI):42.7-59.0] in 2019, which was comparable with 199 048.1 µg/m3 (95% CI: 36.5-65.3). This was despite an 80% reduction in household air pollution (HAP) sources since 1990. In 2019, particulate matter pollution contributed to 25.67% (95% CI: 23.55-27.90%) of total CVD deaths and 28.10% (95% CI: 25.75-30.37%) of DALYs in the region, most of which were due to ischaemic heart disease and stroke. We estimated that 353 071 (95% CI: 304 299-404 591) CVD deaths in EMR were attributable to particulate matter in 2019, including 264 877 (95% CI: 218 472-314 057) and 88 194.07 (95% CI: 60 149-119 949) CVD deaths from ambient PM2.5 pollution and HAP from solid fuels, respectively. DALY's in 2019 from CVD attributable to particulate matter was 28.1% when compared with 26.69% in 1990. The age-standardized death and DALY rates attributable to air pollution was 2122 per 100 000 in EMR in 2019 and was higher in males (2340 per 100 000) than in females (1882 per 100 000). CONCLUSION: The EMR region experiences high PM2.5 levels with high regional heterogeneity and attributable burden of CVD due to air pollution. Despite significant reductions of overall HAP in the past 3 decades, there is continued HAP exposure in this region with rising trend in CVD mortality and DALYs attributable to ambient sources. Given the substantial contrast in disease burden, exposures, socio-economic and geo-political constraints in the EMR region, our analysis suggests substantial opportunities for PM2.5 attributable CVD burden mitigation.

Machine learning derived ECG risk score improves cardiovascular risk assessment in conjunction with coronary artery calcium scoring.

Background: Precision estimation of cardiovascular risk remains the cornerstone of atherosclerotic cardiovascular disease (ASCVD) prevention. While coronary artery calcium (CAC) scoring is the best available non-invasive quantitative modality to evaluate risk of ASCVD, it excludes risk related to prior myocardial infarction, cardiomyopathy, and arrhythmia which are implicated in ASCVD. The high-dimensional and inter-correlated nature of ECG data makes it a good candidate for analysis using machine learning techniques and may provide additional prognostic information not captured by CAC. In this study, we aimed to develop a quantitative ECG risk score (eRiS) to predict major adverse cardiovascular events (MACE) alone, or when added to CAC. Further, we aimed to construct and validate a novel nomogram incorporating ECG, CAC and clinical factors for ASCVD. Methods: We analyzed 5,864 patients with at least 1 cardiovascular risk factor who underwent CAC scoring and a standard ECG as part of the CLARIFY study (ClinicalTrials.gov Identifier: NCT04075162). Events were defined as myocardial infarction, coronary revascularization, stroke or death. A total of 649 ECG features, consisting of measurements such as amplitude and interval measurements from all deflections in the ECG waveform (53 per lead and 13 overall) were automatically extracted using a clinical software (GE Muse™ Cardiology Information System, GE Healthcare). The data was split into 4 training (Str) and internal validation (Sv) sets [Str (1): Sv (1): 50:50; Str (2): Sv (2): 60:40; Str (3): Sv (3): 70:30; Str (4): Sv (4): 80:20], and the results were compared across all the subsets. We used the ECG features derived from Str to develop eRiS. A least absolute shrinkage and selection operator-Cox (LASSO-Cox) regularization model was used for data dimension reduction, feature selection, and eRiS construction. A Cox-proportional hazards model was used to assess the benefit of using an eRiS alone (Mecg), CAC alone (Mcac) and a combination of eRiS and CAC (Mecg+cac) for MACE prediction. A nomogram (Mnom) was further constructed by integrating eRiS with CAC and demographics (age and sex). The primary endpoint of the study was the assessment of the performance of Mecg, Mcac, Mecg+cac and Mnom in predicting CV disease-free survival in ASCVD. Findings: Over a median follow-up of 14 months, 494 patients had MACE. The feature selection strategy preserved only about 18% of the features that were consistent across the various strata (Str). The Mecg model, comprising of eRiS alone was found to be significantly associated with MACE and had good discrimination of MACE (C-Index: 0.7, p = <2e-16). eRiS could predict time-to MACE (C-Index: 0.6, p = <2e-16 across all Sv). The Mecg+cac model was associated with MACE (C-index: 0.71). Model comparison showed that Mecg+cac was superior to Mecg (p = 1.8e-10) or Mcac (p < 2.2e-16) alone. The Mnom, comprising of eRiS, CAC, age and sex was associated with MACE (C-index 0.71). eRiS had the most significant contribution, followed by CAC score and other clinical variables. Further, Mnom was able to identify unique patient risk-groups based on eRiS, CAC and clinical variables. Conclusion: The use of ECG features in conjunction with CAC may allow for improved prognostication and identification of populations at risk. Future directions will involve prospective validation of the risk score and the nomogram across diverse populations with a heterogeneity of treatment effects.

Deep-learning-based hepatic fat assessment (DeHFt) on non-contrast chest CT and its association with disease severity in COVID-19 infections: A multi-site retrospective study.

BACKGROUND: Hepatic steatosis (HS) identified on CT may provide an integrated cardiometabolic and COVID-19 risk assessment. This study presents a deep-learning-based hepatic fat assessment (DeHFt) pipeline for (a) more standardised measurements and (b) investigating the association between HS (liver-to-spleen attenuation ratio <1 in CT) and COVID-19 infections severity, wherein severity is defined as requiring invasive mechanical ventilation, extracorporeal membrane oxygenation, death. METHODS: DeHFt comprises two steps. First, a deep-learning-based segmentation model (3D residual-UNet) is trained (N.ß=.ß80) to segment the liver and spleen. Second, CT attenuation is estimated using slice-based and volumetric-based methods. DeHFt-based mean liver and liver-to-spleen attenuation are compared with an expert's ROI-based measurements. We further obtained the liver-to-spleen attenuation ratio in a large multi-site cohort of patients with COVID-19 infections (D1, N.ß=.ß805; D2, N.ß=.ß1917; D3, N.ß=.ß169) using the DeHFt pipeline and investigated the association between HS and COVID-19 infections severity. FINDINGS: The DeHFt pipeline achieved a dice coefficient of 0.95, 95% CI [0.93...0.96] on the independent validation cohort (N.ß=.ß49). The automated slice-based and volumetric-based liver and liver-to-spleen attenuation estimations strongly correlated with expert's measurement. In the COVID-19 cohorts, severe infections had a higher proportion of patients with HS than non-severe infections (pooled OR.ß=.ß1.50, 95% CI [1.20...1.88], P.ß<.ß.001). INTERPRETATION: The DeHFt pipeline enabled accurate segmentation of liver and spleen on non-contrast CTs and automated estimation of liver and liver-to-spleen attenuation ratio. In three cohorts of patients with COVID-19 infections (N.ß=.ß2891), HS was associated with disease severity. Pending validation, DeHFt provides an automated CT-based metabolic risk assessment. FUNDING: For a full list of funding bodies, please see the Acknowledgements.