Deep Learning to Estimate Cardiovascular Risk From Chest Radiographs : A Risk Prediction Study.

BACKGROUND: Guidelines for primary prevention of atherosclerotic cardiovascular disease (ASCVD) recommend a risk calculator (ASCVD risk score) to estimate 10-year risk for major adverse cardiovascular events (MACE). Because the necessary inputs are often missing, complementary approaches for opportunistic risk assessment are desirable. OBJECTIVE: To develop and test a deep-learning model (CXR CVD-Risk) that estimates 10-year risk for MACE from a routine chest radiograph (CXR) and compare its performance with that of the traditional ASCVD risk score for implications for statin eligibility. DESIGN: Risk prediction study. SETTING: Outpatients potentially eligible for primary cardiovascular prevention. PARTICIPANTS: The CXR CVD-Risk model was developed using data from a cancer screening trial. It was externally validated in 8869 outpatients with unknown ASCVD risk because of missing inputs to calculate the ASCVD risk score and in 2132 outpatients with known risk whose ASCVD risk score could be calculated. MEASUREMENTS: 10-year MACE predicted by CXR CVD-Risk versus the ASCVD risk score. RESULTS: Among 8869 outpatients with unknown ASCVD risk, those with a risk of 7.5% or higher as predicted by CXR CVD-Risk had higher 10-year risk for MACE after adjustment for risk factors (adjusted hazard ratio [HR], 1.73 [95% CI, 1.47 to 2.03]). In the additional 2132 outpatients with known ASCVD risk, CXR CVD-Risk predicted MACE beyond the traditional ASCVD risk score (adjusted HR, 1.88 [CI, 1.24 to 2.85]). LIMITATION: Retrospective study design using electronic medical records. CONCLUSION: On the basis of a single CXR, CXR CVD-Risk predicts 10-year MACE beyond the clinical standard and may help identify individuals at high risk whose ASCVD risk score cannot be calculated because of missing data. PRIMARY FUNDING SOURCE: None.

Deep Learning of the Retina Enables Phenome- and Genome-Wide Analyses of the Microvasculature.

BACKGROUND: The microvasculature, the smallest blood vessels in the body, has key roles in maintenance of organ health and tumorigenesis. The retinal fundus is a window for human in vivo noninvasive assessment of the microvasculature. Large-scale complementary machine learning-based assessment of the retinal vasculature with phenome-wide and genome-wide analyses may yield new insights into human health and disease. METHODS: We used 97 895 retinal fundus images from 54 813 UK Biobank participants. Using convolutional neural networks to segment the retinal microvasculature, we calculated vascular density and fractal dimension as a measure of vascular branching complexity. We associated these indices with 1866 incident International Classification of Diseases-based conditions (median 10-year follow-up) and 88 quantitative traits, adjusting for age, sex, smoking status, and ethnicity. RESULTS: Low retinal vascular fractal dimension and density were significantly associated with higher risks for incident mortality, hypertension, congestive heart failure, renal failure, type 2 diabetes, sleep apnea, anemia, and multiple ocular conditions, as well as corresponding quantitative traits. Genome-wide association of vascular fractal dimension and density identified 7 and 13 novel loci, respectively, that were enriched for pathways linked to angiogenesis (eg, vascular endothelial growth factor, platelet-derived growth factor receptor, angiopoietin, and WNT signaling pathways) and inflammation (eg, interleukin, cytokine signaling). CONCLUSIONS: Our results indicate that the retinal vasculature may serve as a biomarker for future cardiometabolic and ocular disease and provide insights into genes and biological pathways influencing microvascular indices. Moreover, such a framework highlights how deep learning of images can quantify an interpretable phenotype for integration with electronic health record, biomarker, and genetic data to inform risk prediction and risk modification.

Deep Learning Analysis of Chest Radiographs to Triage Patients with Acute Chest Pain Syndrome.

Background Patients presenting to the emergency department (ED) with acute chest pain (ACP) syndrome undergo additional testing to exclude acute coronary syndrome (ACS), pulmonary embolism (PE), or aortic dissection (AD), often yielding negative results. Purpose To assess whether deep learning (DL) analysis of the initial chest radiograph may help triage patients with ACP syndrome more efficiently. Materials and Methods This retrospective study used electronic health records of patients with ACP syndrome at presentation who underwent a combination of chest radiography and additional cardiovascular or pulmonary imaging or stress tests at two hospitals (Massachusetts General Hospital [MGH], Brigham and Women's Hospital [BWH]) between January 2005 and December 2015. A DL model was trained on 23 005 patients from MGH to predict a 30-day composite end point of ACS, PE, AD, and all-cause mortality based on chest radiographs. Area under the receiver operating characteristic curve (AUC) was used to compare performance between models (model 1: age + sex; model 2: model 1 + conventional troponin or d-dimer positivity; model 3: model 2 + DL predictions) in internal and external test sets from MGH and BWH, respectively. Results At MGH, 5750 patients (mean age, 59 years ± 17 [SD]; 3329 men, 2421 women) were evaluated. Model 3, which included DL predictions, significantly improved discrimination of those with the composite outcome compared with models 2 and 1 (AUC, 0.85 [95% CI: 0.84, 0.86] vs 0.76 [95% CI: 0.74, 0.77] vs 0.62 [95% CI: 0.60 0.64], respectively; P < .001 for all). When using a sensitivity threshold of 99%, 14% (813 of 5750) of patients could be deferred from cardiovascular or pulmonary testing for differential diagnosis of ACP syndrome using model 3 compared with 2% (98 of 5750) of patients using model 2 (P < .001). Model 3 maintained its diagnostic performance in different age, sex, race, and ethnicity groups. In external validation at BWH (22 764 patients; mean age, 57 years ± 17; 11 470 women), trends were similar and improved after fine tuning. Conclusion Deep learning analysis of chest radiographs may facilitate more efficient triage of patients with acute chest pain syndrome in the emergency department. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Goo in this issue.

Deep Learning to Optimize Candidate Selection for Lung Cancer CT Screening: Advancing the 2021 USPSTF Recommendations.

Background A deep learning (DL) model to identify lung cancer screening candidates based on their chest radiographs requires external validation with a recent real-world non-U.S. sample. Purpose To validate the DL model and identify added benefits to the 2021 U.S. Preventive Services Task Force (USPSTF) recommendations in a health check-up sample. Materials and Methods This single-center retrospective study included consecutive current and former smokers aged 50-80 years who underwent chest radiography during a health check-up between January 2004 and June 2018. Discrimination performance, including receiver operating characteristic curve analysis and area under the receiver operating characteristic curve (AUC) calculation, of the model for incident lung cancers was evaluated. The added value of the model to the 2021 USPSTF recommendations was investigated for lung cancer inclusion rate, proportion of selected CT screening candidates, and positive predictive value (PPV). Results For model validation, a total of 19 488 individuals (mean age, 58 years ± 6 [SD]; 18 467 [95%] men) and the subset of USPSTF-eligible individuals (n = 7835; mean age, 57 years ± 6; 7699 [98%] men) were assessed, and the AUCs for incident lung cancers were 0.68 (95% CI: 0.62, 0.73) and 0.75 (95% CI: 0.68, 0.81), respectively. In individuals with pack-year information (n = 17 390), when excluding low- and indeterminate-risk categories from the USPSTF-eligible sample, the proportion of selected CT screening candidates was reduced to 35.8% (6233 of 17 390) from 45.1% (7835 of 17 390, P < .001), with three missed lung cancers (0.2%). The cancer inclusion rate (0.3% [53 of 17 390] vs 0.3% [56 of 17 390], P = .85) and PPV (0.9% [53 of 6233] vs 0.7% [56 of 7835], P = .42) remained unaffected. Conclusion An externally validated deep learning model showed the added value to the 2021 U.S. Preventive Services Task Force recommendations for low-dose CT lung cancer screening in reducing the number of screening candidates while maintaining the inclusion rate and positive predictive value for incident lung cancer. © RSNA, 2022 Online supplemental material is available for this article.

CausalMGM: an interactive web-based causal discovery tool.

High-throughput sequencing and the availability of large online data repositories (e.g. The Cancer Genome Atlas and Trans-Omics for Precision Medicine) have the potential to revolutionize systems biology by enabling researchers to study interactions between data from different modalities (i.e. genetic, genomic, clinical, behavioral, etc.). Currently, data mining and statistical approaches are confined to identifying correlates in these datasets, but researchers are often interested in identifying cause-and-effect relationships. Causal discovery methods were developed to infer such cause-and-effect relationships from observational data. Though these algorithms have had demonstrated successes in several biomedical applications, they are difficult to use for non-experts. So, there is a need for web-based tools to make causal discovery methods accessible. Here, we present CausalMGM (http://causalmgm.org/), the first web-based causal discovery tool that enables researchers to find cause-and-effect relationships from observational data. Web-based CausalMGM consists of three data analysis tools: (i) feature selection and clustering; (ii) automated identification of cause-and-effect relationships via a graphical model; and (iii) interactive visualization of the learned causal (directed) graph. We demonstrate how CausalMGM enables an end-to-end exploratory analysis of biomedical datasets, giving researchers a clearer picture of its capabilities.

Association Between Immune Checkpoint Inhibitors With Cardiovascular Events and Atherosclerotic Plaque.

BACKGROUND: Immune checkpoint inhibitors (ICIs) treat an expanding range of cancers. Consistent basic data suggest that these same checkpoints are critical negative regulators of atherosclerosis. Therefore, our objectives were to test whether ICIs were associated with accelerated atherosclerosis and a higher risk of atherosclerosis-related cardiovascular events. METHODS: The study was situated in a single academic medical center. The primary analysis evaluated whether exposure to an ICI was associated with atherosclerotic cardiovascular events in 2842 patients and 2842 controls matched by age, a history of cardiovascular events, and cancer type. In a second design, a case-crossover analysis was performed with an at-risk period defined as the 2-year period after and the control period as the 2-year period before treatment. The primary outcome was a composite of atherosclerotic cardiovascular events (myocardial infarction, coronary revascularization, and ischemic stroke). Secondary outcomes included the individual components of the primary outcome. In addition, in an imaging substudy (n=40), the rate of atherosclerotic plaque progression was compared from before to after the ICI was started. All study measures and outcomes were blindly adjudicated. RESULTS: In the matched cohort study, there was a 3-fold higher risk for cardiovascular events after starting an ICI (hazard ratio, 3.3 [95% CI, 2.0-5.5]; P<0.001). There was a similar increase in each of the individual components of the primary outcome. In the case-crossover, there was also an increase in cardiovascular events from 1.37 to 6.55 per 100 person-years at 2 years (adjusted hazard ratio, 4.8 [95% CI, 3.5-6.5]; P<0.001). In the imaging study, the rate of progression of total aortic plaque volume was >3-fold higher with ICIs (from 2.1%/y before 6.7%/y after). This association between ICI use and increased atherosclerotic plaque progression was attenuated with concomitant use of statins or corticosteroids. CONCLUSIONS: Cardiovascular events were higher after initiation of ICIs, potentially mediated by accelerated progression of atherosclerosis. Optimization of cardiovascular risk factors and increased awareness of cardiovascular risk before, during, and after treatment should be considered among patients on an ICI.

Neurological Complications Acquired During Pediatric Critical Illness: Exploratory "Mixed Graphical Modeling" Analysis Using Serum Biomarker Levels.

OBJECTIVES: Neurologic complications, consisting of the acute development of a neurologic disorder, that is, not present at admission but develops during the course of illness, can be difficult to detect in the PICU due to sedation, neuromuscular blockade, and young age. We evaluated the direct relationships of serum biomarkers and clinical variables to the development of neurologic complications. Analysis was performed using mixed graphical models, a machine learning approach that allows inference of cause-effect associations from continuous and discrete data. DESIGN: Secondary analysis of a previous prospective observational study. SETTING: PICU, single quaternary-care center. PATIENTS: Individuals admitted to the PICU, younger than18 years old, with intravascular access via an indwelling catheter. INTERVENTIONS: None. MEASUREMENTS: About 101 patients were included in this analysis. Serum (days 1-7) was analyzed for glial fibrillary acidic protein, ubiquitin C-terminal hydrolase-L1, and alpha-II spectrin breakdown product 150 utilizing enzyme-linked immunosorbent assays. Serum levels of neuron-specific enolase, myelin basic protein, and S100 calcium binding protein B used in these models were reported previously. Demographic data, use of selected clinical therapies, lengths of stay, and ancillary neurologic testing (head CT, brain MRI, and electroencephalogram) results were recorded. The Mixed Graphical Model-Fast-Causal Inference-Maximum algorithm was applied to the dataset. MAIN RESULTS: About 13 of 101 patients developed a neurologic complication during their critical illness. The mixed graphical model identified peak levels of the neuronal biomarker neuron-specific enolase and ubiquitin C-terminal hydrolase-L1, and the astrocyte biomarker glial fibrillary acidic protein to be the direct causal determinants for the development of a neurologic complication; in contrast, clinical variables including age, sex, length of stay, and primary neurologic diagnosis were not direct causal determinants. CONCLUSIONS: Graphical models that include biomarkers in addition to clinical data are promising methods to evaluate direct relationships in the development of neurologic complications in critically ill children. Future work is required to validate and refine these models further, to determine if they can be used to predict which patients are at risk for/or with early neurologic complications.

Deep Learning Using Chest Radiographs to Identify High-Risk Smokers for Lung Cancer Screening Computed Tomography: Development and Validation of a Prediction Model.

BACKGROUND: Lung cancer screening with chest computed tomography (CT) reduces lung cancer death. Centers for Medicare & Medicaid Services (CMS) eligibility criteria for lung cancer screening with CT require detailed smoking information and miss many incident lung cancers. An automated deep-learning approach based on chest radiograph images may identify more smokers at high risk for lung cancer who could benefit from screening with CT. OBJECTIVE: To develop and validate a convolutional neural network (CXR-LC) that predicts long-term incident lung cancer using data commonly available in the electronic medical record (EMR) (chest radiograph, age, sex, and whether currently smoking). DESIGN: Risk prediction study. SETTING: U.S. lung cancer screening trials. PARTICIPANTS: The CXR-LC model was developed in the PLCO (Prostate, Lung, Colorectal, and Ovarian) Cancer Screening Trial (n = 41 856). The final CXR-LC model was validated in additional PLCO smokers (n = 5615, 12-year follow-up) and NLST (National Lung Screening Trial) heavy smokers (n = 5493, 6-year follow-up). Results are reported for validation data sets only. MEASUREMENTS: Up to 12-year lung cancer incidence predicted by CXR-LC. RESULTS: The CXR-LC model had better discrimination (area under the receiver-operating characteristic curve [AUC]) for incident lung cancer than CMS eligibility (PLCO AUC, 0.755 vs. 0.634; P < 0.001). The CXR-LC model's performance was similar to that of PLCOM2012, a state-of-the-art risk score with 11 inputs, in both the PLCO data set (CXR-LC AUC of 0.755 vs. PLCOM2012 AUC of 0.751) and the NLST data set (0.659 vs. 0.650). When compared in equal-sized screening populations, CXR-LC was more sensitive than CMS eligibility in the PLCO data set (74.9% vs. 63.8%; P = 0.012) and missed 30.7% fewer incident lung cancers. On decision curve analysis, CXR-LC had higher net benefit than CMS eligibility and similar benefit to PLCOM2012. LIMITATION: Validation in lung cancer screening trials and not a clinical setting. CONCLUSION: The CXR-LC model identified smokers at high risk for incident lung cancer, beyond CMS eligibility and using information commonly available in the EMR. PRIMARY FUNDING SOURCE: None.

Mixed graphical models for integrative causal analysis with application to chronic lung disease diagnosis and prognosis.

MOTIVATION: Integration of data from different modalities is a necessary step for multi-scale data analysis in many fields, including biomedical research and systems biology. Directed graphical models offer an attractive tool for this problem because they can represent both the complex, multivariate probability distributions and the causal pathways influencing the system. Graphical models learned from biomedical data can be used for classification, biomarker selection and functional analysis, while revealing the underlying network structure and thus allowing for arbitrary likelihood queries over the data. RESULTS: In this paper, we present and test new methods for finding directed graphs over mixed data types (continuous and discrete variables). We used this new algorithm, CausalMGM, to identify variables directly linked to disease diagnosis and progression in various multi-modal datasets, including clinical datasets from chronic obstructive pulmonary disease (COPD). COPD is the third leading cause of death and a major cause of disability and thus determining the factors that cause longitudinal lung function decline is very important. Applied on a COPD dataset, mixed graphical models were able to confirm and extend previously described causal effects and provide new insights on the factors that potentially affect the longitudinal lung function decline of COPD patients. AVAILABILITY AND IMPLEMENTATION: The CausalMGM package is available on http://www.causalmgm.org. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Feasibility of lung cancer prediction from low-dose CT scan and smoking factors using causal models.

INTRODUCTION: Low-dose CT (LDCT) is currently used in lung cancer screening of high-risk populations for early lung cancer diagnosis. However, 96% of individuals with detected nodules are false positives. METHODS: In order to develop an efficient early lung cancer predictor from clinical, demographic and LDCT features, we studied a total of 218 subjects with lung cancer or benign nodules. Probabilistic graphical models (PGMs) were used to integrate demographics, clinical data and LDCT features from 92 subjects (training cohort) from the Pittsburgh Lung Screening Study cohort. RESULTS: Learnt PGMs identified three variables directly (causally) linked to malignant nodules and the largest benign nodule and used them to build the Lung Cancer Causal Model (LCCM), which was validated in a separate cohort of 126 subjects. Nodule and vessel numbers and years since the subject quit smoking were sufficient to discriminate malignant from benign nodules. Comparison with existing predictors in the training and validation cohorts showed that (1) incorporating LDCT scan features greatly enhances predictive accuracy; and (2) LCCM improves cancer detection over existing methods, including the Brock parsimonious model (p<0.001). Notably, the number of surrounding vessels, a feature not previously used in predictive models, significantly improves predictive efficiency. Based on the validation cohort results, LCCM is able to identify 30% of the benign nodules without risk of misclassifying cancer nodules. DISCUSSION: LCCM shows promise as a lung cancer predictor as it is significantly improved over existing models. Validated in a larger, prospective study, it may help reduce unnecessary follow-up visits and procedures.

piMGM: incorporating multi-source priors in mixed graphical models for learning disease networks.

Motivation: Learning probabilistic graphs over mixed data is an important way to combine gene expression and clinical disease data. Leveraging the existing, yet imperfect, information in pathway databases for mixed graphical model (MGM) learning is an understudied problem with tremendous potential applications in systems medicine, the problems of which often involve high-dimensional data. Results: We present a new method, piMGM, which can learn with accuracy the structure of probabilistic graphs over mixed data by appropriately incorporating priors from multiple experts with different degrees of reliability. We show that piMGM accurately scores the reliability of prior information from a given expert even at low sample sizes. The reliability scores can be used to determine active pathways in healthy and disease samples. We tested piMGM on both simulated and real data from TCGA, and we found that its performance is not affected by unreliable priors. We demonstrate the applicability of piMGM by successfully using prior information to identify pathway components that are important in breast cancer and improve cancer subtype classification. Availability and implementation: http://www.benoslab.pitt.edu/manatakisECCB2018.html. Supplementary information: Supplementary data are available at Bioinformatics online.

Biomarker identification for statin sensitivity of cancer cell lines.

Statins are potent cholesterol reducing drugs that have been shown to reduce tumor cell proliferation in vitro and tumor growth in animal models. Moreover, retrospective human cohort studies demonstrated decreased cancer-specific mortality in patients taking statins. We previously implicated membrane E-cadherin expression as both a marker and mechanism for resistance to atorvastatin-mediated growth suppression of cancer cells; however, a transcriptome-profile-based biomarker signature for statin sensitivity has not yet been reported. Here, we utilized transcriptome data from fourteen NCI-60 cancer cell lines and their statin dose-response data to produce gene expression signatures that identify statin sensitive and resistant cell lines. We experimentally confirmed the validity of the identified biomarker signature in an independent set of cell lines and extended this signature to generate a proposed statin-sensitive subset of tumors listed in the TCGA database. Finally, we predicted drugs that would synergize with statins and found several predicted combination therapies to be experimentally confirmed. The combined bioinformatics-experimental approach described here can be used to generate an initial biomarker signature for anticancer drug therapy.

Cellular and transcriptional profiles of peripheral blood mononuclear cells pre-vaccination predict immune response to preventative MUC1 vaccine.

A single arm trial (NCT007773097) and a double-blind, placebo controlled randomized trial ( NCT02134925 ) were conducted in individuals with a history of advanced colonic adenoma to test the safety and immunogenicity of the MUC1 tumor antigen vaccine and its potential to prevent new adenomas. These were the first two trials of a non-viral cancer vaccine administered in the absence of cancer. The vaccine was safe and strongly immunogenic in 43% (NCT007773097) and 25% ( NCT02134925 ) of participants. The lack of response in a significant number of participants suggested, for the first time, that even in a premalignant setting, the immune system may have already been exposed to some level of suppression previously reported only in cancer. Single-cell RNA-sequencing (scRNA-seq) on banked pre-vaccination peripheral blood mononuclear cells (PBMCs) from 16 immune responders and 16 non-responders identified specific cell types, genes, and pathways of a productive vaccine response. Responders had a significantly higher percentage of CD4+ naive T cells pre-vaccination, but a significantly lower percentage of CD8+ T effector memory (TEM) cells and CD16+ monocytes. Differential gene expression (DGE) and transcription factor inference analysis showed a higher level of expression of T cell activation genes, such as Fos and Jun, in CD4+ naive T cells, and pathway analysis showed enriched signaling activity in responders. Furthermore, Bayesian network analysis suggested that these genes were mechanistically connected to response. Our analyses identified several immune mechanisms and candidate biomarkers to be further validated as predictors of immune responses to a preventative cancer vaccine that could facilitate selection of individuals likely to benefit from a vaccine or be used to improve vaccine responses.

External Testing of a Deep Learning Model to Estimate Biologic Age Using Chest Radiographs.

Purpose To assess the prognostic value of a deep learning-based chest radiographic age (hereafter, CXR-Age) model in a large external test cohort of Asian individuals. Materials and Methods This single-center, retrospective study included chest radiographs from consecutive, asymptomatic Asian individuals aged 50-80 years who underwent health checkups between January 2004 and June 2018. This study performed a dedicated external test of a previously developed CXR-Age model, which predicts an age adjusted based on the risk of all-cause mortality. Adjusted hazard ratios (HRs) of CXR-Age for all-cause, cardiovascular, lung cancer, and respiratory disease mortality were assessed using multivariable Cox or Fine-Gray models, and their added values were evaluated by likelihood ratio tests. Results A total of 36 924 individuals (mean chronological age, 58 years ± 7 [SD]; CXR-Age, 60 years ± 5; 22 352 male) were included. During a median follow-up of 11.0 years, 1250 individuals (3.4%) died, including 153 cardiovascular (0.4%), 166 lung cancer (0.4%), and 98 respiratory (0.3%) deaths. CXR-Age was a significant risk factor for all-cause (adjusted HR at chronological age of 50 years, 1.03; at 60 years, 1.05; at 70 years, 1.07), cardiovascular (adjusted HR, 1.11), lung cancer (adjusted HR for individuals who formerly smoked, 1.12; for those who currently smoke, 1.05), and respiratory disease (adjusted HR, 1.12) mortality (P < .05 for all). The likelihood ratio test demonstrated added prognostic value of CXR-Age to clinical factors, including chronological age for all outcomes (P < .001 for all). Conclusion Deep learning-based chest radiographic age was associated with various survival outcomes and had added value to clinical factors in asymptomatic Asian individuals, suggesting its generalizability. Keywords: Conventional Radiography, Thorax, Heart, Lung, Mediastinum, Outcomes Analysis, Quantification, Prognosis, Convolutional Neural Network (CNN) Supplemental material is available for this article. © RSNA, 2024 See also the commentary by Adams and Bressem in this issue.

Deep learning analysis of epicardial adipose tissue to predict cardiovascular risk in heavy smokers.

BACKGROUND: Heavy smokers are at increased risk for cardiovascular disease and may benefit from individualized risk quantification using routine lung cancer screening chest computed tomography. We investigated the prognostic value of deep learning-based automated epicardial adipose tissue quantification and compared it to established cardiovascular risk factors and coronary artery calcium. METHODS: We investigated the prognostic value of automated epicardial adipose tissue quantification in heavy smokers enrolled in the National Lung Screening Trial and followed for 12.3 (11.9-12.8) years. The epicardial adipose tissue was segmented and quantified on non-ECG-synchronized, non-contrast low-dose chest computed tomography scans using a validated deep-learning algorithm. Multivariable survival regression analyses were then utilized to determine the associations of epicardial adipose tissue volume and density with all-cause and cardiovascular mortality (myocardial infarction and stroke). RESULTS: Here we show in 24,090 adult heavy smokers (59% men; 61 ± 5 years) that epicardial adipose tissue volume and density are independently associated with all-cause (adjusted hazard ratios: 1.10 and 1.38; P < 0.001) and cardiovascular mortality (adjusted hazard ratios: 1.14 and 1.78; P < 0.001) beyond demographics, clinical risk factors, body habitus, level of education, and coronary artery calcium score. CONCLUSIONS: Our findings suggest that automated assessment of epicardial adipose tissue from low-dose lung cancer screening images offers prognostic value in heavy smokers, with potential implications for cardiovascular risk stratification in this high-risk population.

Heavy smokers are at increased risk of poor health outcomes, particularly outcomes related to cardiovascular disease. We explore how fat surrounding the heart, known as epicardial adipose tissue, may be an indicator of the health of heavy smokers. We use an artificial intelligence system to measure the heart fat on chest scans of heavy smokers taken during a lung cancer screening trial and following their health for 12 years. We find that higher amounts and denser epicardial adipose tissue are linked to an increased risk of death from any cause, specifically from heart-related issues, even when considering other health factors. This suggests that measuring epicardial adipose tissue during lung cancer screenings could be a valuable tool for identifying heavy smokers at greater risk of heart problems and death, possibly helping to guide their medical management and improve their cardiovascular health.

Deep learning to estimate lung disease mortality from chest radiographs.

Prevention and management of chronic lung diseases (asthma, lung cancer, etc.) are of great importance. While tests are available for reliable diagnosis, accurate identification of those who will develop severe morbidity/mortality is currently limited. Here, we developed a deep learning model, CXR Lung-Risk, to predict the risk of lung disease mortality from a chest x-ray. The model was trained using 147,497 x-ray images of 40,643 individuals and tested in three independent cohorts comprising 15,976 individuals. We found that CXR Lung-Risk showed a graded association with lung disease mortality after adjustment for risk factors, including age, smoking, and radiologic findings (Hazard ratios up to 11.86 [8.64-16.27]; p < 0.001). Adding CXR Lung-Risk to a multivariable model improved estimates of lung disease mortality in all cohorts. Our results demonstrate that deep learning can identify individuals at risk of lung disease mortality on easily obtainable x-rays, which may improve personalized prevention and treatment strategies.

Deep Learning to Predict Mortality After Cardiothoracic Surgery Using Preoperative Chest Radiographs.

BACKGROUND: The Society of Thoracic Surgeons Predicted Risk of Mortality (STS-PROM) estimates mortality risk only for certain common procedures (eg, coronary artery bypass or valve surgery) and is cumbersome, requiring greater than 60 inputs. We hypothesized that deep learning can estimate postoperative mortality risk based on a preoperative chest radiograph for cardiac surgeries in which STS-PROM scores were available (STS index procedures) or unavailable (non-STS index procedures). METHODS: We developed a deep learning model (CXR-CTSurgery) to predict postoperative mortality based on preoperative chest radiographs in 9283 patients at Massachusetts General Hospital (MGH) having cardiac surgery before April 8, 2014. CXR-CTSurgery was tested on 3615 different MGH patients and externally tested on 2840 patients from Brigham and Women's Hospital (BWH) having surgery after April 8, 2014. Discrimination for mortality was compared with the STS-PROM using the C-statistic. Calibration was assessed using the observed-to-expected ratio (O/E ratio). RESULTS: For STS index procedures, CXR-CTSurgery had a C-statistic similar to STS-PROM at MGH (CXR-CTSurgery: 0.83 vs STS-PROM: 0.88; P = .20) and BWH (0.74 vs 0.80; P = .14) testing cohorts. The CXR-CTSurgery C-statistic for non-STS index procedures was similar to STS index procedures in the MGH (0.87 vs 0.83) and BWH (0.73 vs 0.74) testing cohorts. For STS index procedures, CXR-CTSurgery had better calibration than the STS-PROM in the MGH (O/E ratio: 0.74 vs 0.52) and BWH (O/E ratio: 0.91 vs 0.73) testing cohorts. CONCLUSIONS: CXR-CTSurgery predicts postoperative mortality based on a preoperative CXR with similar discrimination and better calibration than the STS-PROM. This may be useful when the STS-PROM cannot be calculated or for non-STS index procedures.

Validation of a Deep Learning-Based Model to Predict Lung Cancer Risk Using Chest Radiographs and Electronic Medical Record Data.

Importance: Lung cancer screening with chest computed tomography (CT) prevents lung cancer death; however, fewer than 5% of eligible Americans are screened. CXR-LC, an open-source deep learning tool that estimates lung cancer risk from existing chest radiograph images and commonly available electronic medical record (EMR) data, may enable automated identification of high-risk patients as a step toward improving lung cancer screening participation. Objective: To validate CXR-LC using EMR data to identify individuals at high-risk for lung cancer to complement 2022 US Centers for Medicare & Medicaid Services (CMS) lung cancer screening eligibility guidelines. Design, Setting, and Participants: This prognostic study compared CXR-LC estimates with CMS screening guidelines using patient data from a large US hospital system. Included participants were persons who currently or formerly smoked cigarettes with an outpatient posterior-anterior chest radiograph between January 1, 2013, and December 31, 2014, with no history of lung cancer or screening CT. Data analysis was performed between May 2021 and June 2022. Exposures: CXR-LC lung cancer screening eligibility (previously defined as having a 3.297% or greater 12-year risk) based on inputs (chest radiograph image, age, sex, and whether currently smoking) extracted from the EMR. Main Outcomes and Measures: 6-year incident lung cancer. Results: A total of 14 737 persons were included in the study population (mean [SD] age, 62.6 [6.8] years; 7154 [48.5%] male; 204 [1.4%] Asian, 1051 [7.3%] Black, 432 [2.9%] Hispanic, 12 330 [85.2%] White) with a 2.4% rate of incident lung cancer over 6 years (361 patients with cancer). CMS eligibility could be determined in 6277 patients (42.6%) using smoking pack-year and quit-date from the EMR. Patients eligible by both CXR-LC and 2022 CMS criteria had a high rate of lung cancer (83 of 974 patients [8.5%]), higher than those eligible by 2022 CMS criteria alone (5 of 177 patients [2.8%]; P < .001). Patients eligible by CXR-LC but not 2022 CMS criteria also had a high 6-year incidence of lung cancer (121 of 3703 [3.3%]). In the 8460 cases (57.4%) where CMS eligibility was unknown, CXR-LC eligible patients had a 5-fold higher rate of lung cancer than ineligible (127 of 5177 [2.5%] vs 18 of 2283 [0.5%]; P < .001). Similar results were found in subgroups, including female patients and Black persons. Conclusions and Relevance: Using routine chest radiographs and other data automatically extracted from the EMR, CXR-LC identified high-risk individuals who may benefit from lung cancer screening CT.

Pre-Existing Autoimmune Disease Increases the Risk of Cardiovascular and Noncardiovascular Events After Immunotherapy.

Background: The use of immune checkpoint inhibitors (ICI) is associated with cardiovascular (CV) events, and patients with pre-existing autoimmune disease are at increased CV risk. Objectives: The aim of this study was to characterize the risk for CV events in patients with pre-existing autoimmune disease post-ICI. Methods: This was a retrospective study of 6,683 patients treated with ICIs within an academic network. Autoimmune disease prior to ICI was confirmed by chart review. Baseline characteristics and risk for CV and non-CV immune-related adverse events were compared with a matched control group (1:1 ratio) of ICI patients without autoimmune disease. Matching was based on age, sex, history of coronary artery disease, history of heart failure, and diabetes mellitus. CV events were a composite of myocardial infarction, percutaneous coronary intervention, coronary artery bypass graft, stroke, transient ischemic attack, deep venous thrombosis, pulmonary embolism, or myocarditis. Univariable and multivariable Cox proportional hazards models were used to determine the association between autoimmune disease and CV events. Results: Among 502 patients treated with ICIs, 251 patients with and 251 patients without autoimmune disease were studied. During a median follow-up period of 205 days, there were 45 CV events among patients with autoimmune disease and 22 CV events among control subjects (adjusted HR: 1.77; 95% CI: 1.04-3.03; P = 0.0364). Of the non-CV immune-related adverse events, there were increased rates of psoriasis (11.2% vs 0.4%; P < 0.001) and colitis (24.3% vs 16.7%; P = 0.045) in patients with autoimmune disease. Conclusions: Patients with autoimmune disease have an increased risk for CV and non-CV events post-ICI.