Risultati per: Screening del cancro del polmone

Circulation, Volume 150, Issue Suppl_1, Page A4138647-A4138647, November 12, 2024. Introduction/Background:We previously demonstrated that an open-source deep learning model (CXR-CVD Risk) can predict 10-year major adverse cardiovascular events (myocardial infarction&stroke), based on a chest radiograph image (CXR). As deep learning models are black boxes, establishing the biological processes the model captures to predict risk may help build understanding and trust in the model.Research Questions/Hypothesis:To test associations between deep-learning derived CXR-CVD Risk and markers of cardiovascular disease including coronary artery calcium (CAC) and stenosis ≥50% on CT, systolic blood pressure (SBP), ankle brachial index (ABI), and prevalent myocardial infarction and stroke.Methods/Approach:We conducted external validation of CXR-CVD-Risk in two cohorts: 1) 2,097 volunteers in the Project Baseline Health Study (PBHS) and 2) 1,644 Mass General Brigham Biobank (MGBB) patients. The CXR-CVD-Risk model estimated 10-year cardiovascular event risk (probability between 0 and 1) from a CXR image. We calculated linear associations with SBP, ABI, and the logarithm of coronary artery calcium and odds ratios for prevalent hypertension, myocardial infarction, stroke, and, in the MGBB, coronary artery stenosis ≥50%. Analyses were adjusted for age, BMI, sex, smoking status, and enrolling site.Results/Data:CXR-CVD-Risk was associated with CAC in both populations (PBHS: 1.11-fold increase, 95% CI: [1.07-1.16]; MGBB: 1.03-fold increase [1.01-1.05] in CAC per 1% increase in CXR-CV-Risk). CXR-CVD-Risk was also associated with SBP (0.59 mmHg increase [0.24-0.93] in SBP per 1% increase in CXR-CV-Risk), history of hypertension, history of myocardial infarction, and stroke. There was an inverse association with ABI (0.010 decrease [0.005-0.014] in ABI) in the PBHS. In the MGBB, CXR-CVD-Risk was associated with coronary artery stenosis ≥50% (OR = 1.004 [1.002-1.007]). All estimates are after covariate adjustment.Conclusion:This deep learning CXR risk score was associated with coronary artery disease (calcium score and stenosis ≥50%), CVD risk factors, and prevalent CVD. Opportunistic screening using CXRs in the electronic record can identify patients at high risk of CVD who may benefit from prevention.

Circulation, Volume 150, Issue Suppl_1, Page A4146283-A4146283, November 12, 2024. Objective:The incidence of cognitive decline following coronary artery bypass grafting (CABG) is well-documented, significantly impacting patient morbidity, mortality, and quality of life. We conducted a systematic review that examines cognitive outcomes in CABG randomized controlled trials (RCTs) to identify which cognitive assessments were used, their administration frequency, attrition rates, and their effectiveness in detecting perioperative cognitive changes in control groups.Methods:We conducted a search of MEDLINE, EMBASE, Cochrane Library, and PsycINFO for CABG RCTs that included cognitive assessments, from January 2005 to December 2023. Descriptive statistics were used to summarize the frequency, domains, and attrition rates of each cognitive task. For tasks assessed both pre- and post-operatively in at least three RCTs, control group scores and standard deviations were reported.Results:Out of 3337 screened studies, 2163 were CABG RCTs, and only 69 (3.2%) included cognitive evaluations (Figure 1). These trials involved 15,839 subjects (79% male, mean age 64.4, median follow-up time 90 days) and used 145 unique cognitive tasks. The Trailmaking Test Part B (40/69; 58.0%) and Part A (38/69; 55.0%) were the most frequently used. Only 7 tasks had means and standard deviations reported before and after surgery in more than three RCTs, and none detected significant pre- to post-operative changes. Attrition rates averaged 19.3%, with a wide range from 0% to 62%. Figure 2 demonstrates the decline in cognitive assessments in CABG trials over the years, with a sharp decline after 2014. Trials that assessed cogntion after 2014 tended to favor screening tasks (MMSE/MoCA) alone.Conclusion:Cognitive assessments are infrequent in CABG trials, and existing tests fail to consistently detect cognitive changes. To effectively evaluate and address cognitive impact after CABG, new assessment strategies that are resilient to attrition and practical for use in diverse trial settings are needed.

Circulation, Volume 150, Issue Suppl_1, Page A4143150-A4143150, November 12, 2024. Background:The FACTOR-64 study was a randomized controlled trial designed to assess whether routine screening for CAD by coronary computed tomography angiography (CCTA) in high-risk patients with diabetes followed by CCTA-directed therapy would reduce the risk of death and nonfatal coronary outcomes. Results at four years showed a lower revascularization rate (3.1% (14) vs. 8.9% (40), p

Circulation, Volume 150, Issue Suppl_1, Page A4140219-A4140219, November 12, 2024. Background:Poor healthcare access results in late- or non-diagnosis of rheumatic heart disease (RHD), perpetuating the burden of RHD in low-resource settings. The ADUNU program, a partnership with the Ugandan Ministry of Health in Kitgum, Uganda, aims to improve RHD case detection through decentralized screening led by primary care nurses, who independently perform and interpret brief screening echocardiograms using handheld echocardiography.Hypothesis:We hypothesized ADUNU’s simplified screening protocol would achieve sensitivity and specificity greater than 80% on confirmatory evaluation.Aim:To determine the health system impact of deploying a novel RHD screening protocol into the public health system in Uganda through a cross-sectional study of diagnostic accuracy.Methods:Primary healthcare nurses, certified to perform echocardiographic screening using a single parasternal long axis view in 2D and color Doppler, integrated screening into their clinical and outreach workflows. Community members with positive screens (mitral regurgitation jet ≥2cm or aortic regurgitation jet ≥1cm) were referred for confirmatory echocardiograms at the District Hospital. A random subset with negative screens were recruited for confirmatory echocardiograms at the time of screening as well. Sensitivity, specificity, predictive values, likelihood ratios, accuracy, and agreement (Cohen’s kappa) were calculated between the screening protocol and the confirmatory results.Results:Between May 2023 and April 2024, 3020 community screenings (ages 5-70 years) were conducted by 19 certified nurses. Among 113 positive screens, 61 (53.9%) were confirmed to have RHD. Among 430 negative screens, 14 (3.3%) had RHD. Screening sensitivity was 82.4% (95% CI 72.2-89.4%) and specificity 89.1% (85.9-91.6%). Positive and negative predictive values were 54.5% (45.2-63.4%) and 97.0% (94.9-98.2%). Likelihood ratios were 7.55(+) and 0.19(-). Accuracy was 88.3% (85.2 – 91.4%) and kappa was 0.59 (0.49-0.68).Conclusions:ADUNU’s novel approach to RHD active case finding achieved acceptable diagnostic performance. Nurse-led RHD screening programs that are integrated into routine clinical care shows potential for use in a comprehensive public health program. Very few RHD cases were missed, and under two referrals were generated for every positive case, an acceptable false positive rate. Further economic evaluation is underway to understand the budgetary impact and cost-effectiveness of this program.

Circulation, Volume 150, Issue Suppl_1, Page A4121454-A4121454, November 12, 2024. Introduction:Recent research has shown that AI is able to assess biological aging and cardiovascular disease (CVD) risk using chest radiographs. However, the lack of explainability of such deep learning algorithms hinders clinical utility and adoption. This motivates the current study which searches for and tests the use of machine extractable quantitative features in chest radiographs to predict CVD risk in population screening.Method:Chest radiograph measurements characterizing cardiomediastinal geometry, aortic calcification and tortuosity were handpicked for development of a segmentation-based feature extraction algorithm. The algorithm was applied on the PLCO lung screening dataset for analysis. The association between measurement-based imaging features, clinical characteristics (age, sex, BMI, smoking status, hypertension, diabetes, liver disease) with CVD mortality and 10-year major adverse cardiovascular events (MACE) were analysed by using proportional hazard regression, with feature selection done by LASSO.Result:Of 29,453 eligible subjects, 5693 subjects from a single study centre were used for fitting of all models. The median follow-up time was 19 years. A total of 32 imaging features were extracted and analysed. For both 10-year MACE and CVD mortality, model using imaging features, age, and sex performed similarly to model using conventional risk factors, and a deep learning chest radiograph CVD risk model. Two imaging features, mediastinal width at valve-level [HR 1.36 (1.23-1.50)] and maximal lateral displacement of descending aorta [HR 1.29 (1.18-1.42)] were found to be prognostic. To the best of our knowledge, these features have not been reported previously.Conclusion:Quantitative imaging features can predict CVD risk in chest radiograph similar to deep learning models while providing feature interpretability and explainability. Two novel imaging features prognostic of CVD risk were found and shown to be complementary to conventional risk factors.

Circulation, Volume 150, Issue Suppl_1, Page A4145119-A4145119, November 12, 2024. Background:The burden of cardiovascular disease (CVD) is increasing among people with HIV (PWH) in sub-Saharan Africa. Integrating CVD screening into routine HIV care represents an opportunity to diagnose CVD at an earlier stage in a potentially high-risk population.Research questionsIs integrating CVD risk factor screening feasible and sustainable in a public HIV clinic in Mwanza, Tanzania? What is the magnitude of CVD risk of the general adult PWH population? What is the unmet need for blood pressure (BP) and diabetes management?Methods:We adapted the AHA Life’s Essential 8 (LE8) into a rapid questionnaire that was administered to every PWH in a large public adult HIV clinic. Questions included demographics; LE8 risk factors (BMI, diet, physical activity, sleep, and smoking); and the hypertension and diabetes continuum of care. Every patient had their BP measured; BP was measured two additional times for those with an initial BP >140/90 mmHg. We administered random blood glucose screening to anyone with a high BP, obese BMI, current smoking, or history of diabetes. Implementation and effectiveness were evaluated using the RE-AIM framework.Results:In 3 months, 1072 PWH were screened at least once. Mean age was 50 years and 72% were female. On average, PWH had a nutritious diet and received adequate physical activity per AHA guidelines. The prevalence of hypertension was 34%; the continuum of care is shown in Figure 1. Of those screened, 21% had diabetes or pre-diabetes. Evaluation via the RE-AIM framework is shown in Table 1. Successes included the reach and effectiveness of screening in only 3 months. Adoption was the biggest challenge due to staffing and supply constraints. The intervention was feasible, implemented with fidelity, and is ongoing.Conclusions:Integrating CVD risk screening into routine HIV care in a busy Tanzanian clinic was feasible and demonstrated a high magnitude of undiagnosed and untreated hypertension among the general PWH population.

Circulation, Volume 150, Issue Suppl_1, Page A4131622-A4131622, November 12, 2024. Introduction:Chronic liver disease affects more than 1.5 billion adults worldwide, but the majority of cases are asymptomatic and undiagnosed. Echocardiography is broadly performed and visualizes the liver; however, this information is not diagnostically leveraged.Hypothesis and Aims:We hypothesized that a deep-learning algorithm can detect chronic liver diseases using subcostal echocardiography images that contains hepatic tissue. To develop and evaluate a deep learning algorithm on subcostal echocardiography videos to enable opportunistic screening for chronic liver disease.Methods:We identified adult patients who received echocardiography and abdominal imaging (either abdominal ultrasound or abdominal magnetic resonance imaging) with ≤30 days between tests. A convolutional neural network pipeline was developed to predict the presence of cirrhosis or steatotic liver disease (SLD) using echocardiogram images. The model performance was evaluated in a held-out test dataset, dataset in which diagnosis was made by magnetic resonance imaging, and external dataset.Results:A total of 2,083,932 echocardiography videos (51,608 studies) from Cedars-Sinai Medical Center (CSMC) were used to develop EchoNet-Liver, an automated pipeline that identifies high quality subcostal images from echocardiogram studies and detects presence of cirrhosis or SLD. In a total of 11,419 quality-controlled subcostal videos from 4,849 patients, a chronic liver disease detection model was able to detect the presence of cirrhosis with an AUC of 0.837 (0.789 – 0.880) and SLD with an AUC of 0.799 (0.758 – 0.837). In a separate test cohort with paired abdominal MRIs, cirrhosis was detected with an AUC of 0.726 (0.659-0.790) compared to MR elastography and SLD was detected with an AUC of 0.704 (0.689-0.718). In the external test cohort of 66 patients (n = 130 videos), the model detected cirrhosis with an AUC of 0.830 (0.738 – 0.909) and SLD with an AUC of 0.768 (0.652 – 0.875).Conclusions:Deep learning assessment of clinically indicated echocardiography enables opportunistic screening of SLD and cirrhosis. Application of this algorithm may identify patients who may benefit from further diagnostic testing and treatment for hepatic disease.

Circulation, Volume 150, Issue Suppl_1, Page A4137986-A4137986, November 12, 2024. Background:Clinical trial screening is labor-intensive, time-consuming, and error prone. We have developed RECTIFIER, an AI-based clinical trial screening tool, to enhance the efficiency and accuracy of patient recruitment. This study aims to evaluate RECTIFIER’s effectiveness compared to manual screening in a randomized implementation study.Methods:This study was designed as an implementation study as part of an active heart failure trial named COPILOT-HF (NCT05734690). Potential eligible patients were identified via a structured electronic medical record query and randomized to be screened for clinical trial eligibility either by RECTIFIER or manually by clinical staff. The outcome measures included the number of patients contacted, and the number of patients reached for clinical trial enrollment. Data was collected over a period of 3 months.Results:A total of 3834 patients were included in the study, with 1919 patients randomized to the RECTIFIER group and 1915 patients to the manual screening group (Figure). Study staff could manually screen only 1367 patients at the end of the 3-month period. RECTIFIER identified more eligible patients compared to manual screening (833[43.4%] vs. 284[14.8%], p

Circulation, Volume 150, Issue Suppl_1, Page A4141975-A4141975, November 12, 2024. Background:Refugee populations often experience high rates of cardiovascular disease (CVD). Factors such as significant physiological stress, trauma, limited access to healthcare, substance abuse, and poor lifestyle choices contribute to disease progression and an increased incidence of cardiovascular events. We sought to evaluate the feasibility of using wearables to obtain high-fidelity ECG signals for CVD screening in refugees in Jordan.Methods:This observational cross-sectional study involved outpatients at one of four regional United Nations’ primary care clinics for Palestinian refugee in Jordan. Research assistants collected health histories from consented patients and recorded a 30-second, 6-lead ECG using a handheld, Bluetooth-enabled, wearable device (KardiaMobile 6L, AliveCor Inc., Mountain View, CA, USA). The digital ECG signals were stored on the Bluetooth-synced mobile device and then exported to a cloud server for offline analysis. The raw ECG recordings were preprocessed, and a single median beat was calculated per lead. Waveforms were segmented, and duration and amplitude measures were determined using a previously validated custom algorithm (University of Pittsburgh, PA, USA). All ECG recordings were reviewed by an independent physician.Result:The sample included 31 patients (age 52±13, 64% Females). Risk factors were prevalent in this group, including hypertension (74%), high cholesterol (65%), diabetes (64%), in-camp living (33%), and smoking (30%). Figure 1 shows the population-averaged median beat with 99% CI distribution of this sample. Mean QRS duration was 95±23 ms (range 53−150) and QTc interval was 403±53 (range 267−513). Most patients were in normal sinus rhythm (84%), and remaining patients were in atrial fibrillation or flutter (16%). Other clinically significant abnormalities included non-specific ST-T changes (9.7%), left bundle branch block (1.6%), and LVH with left ventricular strain (1.6%).Conclusion:This pilot study demonstrated that it is feasible to obtain high fidelity ECG signals using wearables to screen for CVD in refugees. Such affordable, noninvasive, point-of-care screening tools could enable early diagnosis and treatment in these patients.

Circulation, Volume 150, Issue Suppl_1, Page A4142502-A4142502, November 12, 2024. Background:AI-ECG is a cost-effective tool for left ventricular dysfunction (LVD) screening. However, its cost-effectiveness for other forms of structural heart disease (SHD) is unknown. While AI-ECG is inexpensive, a drawback is low positive predictive value (PPV), which leads to high costs from unnecessary follow-up tests. Therefore, strategies to improve the yield of AI-ECG-based screening are needed.Aim:To evaluate the cost savings of a stepwise approach to SHD screening with AI-ECG followed by POCUS compared to AI-ECG alone.Methods:286 adult outpatients undergoing AI-ECG were selected at random. Participants received same-day POCUS and had a recent TTE (our gold standard for SHD). We evaluated four SHDs: aortic stenosis (AS), cardiac amyloidosis (CA), HCM, and LVD. The costs of AI-ECG ($75) and TTE ($1,305) were obtained from Healthcare Bluebook. The cost of POCUS ($100) was estimated independently. Cost savings were analyzed for simultaneous screening for all forms of SHD and screening for individual SHDs.Results:AI-ECG identified potential SHD in 125 patients, but only 39 were true positives by TTE (31% PPV). In AI-ECG positive patients, POCUS demonstrated findings of SHD in 52/125. Compared to TTE, this stepwise approach yielded 32 true positives and 20 false positives (62% PPV). The cost per patient diagnosed with SHD was $4,733 with AI-ECG alone but decreased to $3,182 with stepwise screening (33% cost savings). Screening for individual SHDs resulted in cost reduction from $18,724 to $6,315 (66% savings) for AS, $21,023 to $12,230 (42% savings) for CA, $9,883 to $6,175 (38% savings) for HCM, and $4,019 to $3,582 (11% savings) for LVD.Conclusions:Stepwise screening for SHD with AI-ECG followed by POCUS significantly reduces costs compared to AI-ECG alone. We also suggest a model for parallel screening for multiple SHDs, which is likely more cost-effective than screening for individual SHDs.

Circulation, Volume 150, Issue Suppl_1, Page A4124675-A4124675, November 12, 2024. Introduction:The prevalence of hypertrophic cardiomyopathy (HCM) in the UK Biobank based on ICD-10 codes (.07%) is lower than global estimates of disease prevalence (0.2 – 0.5%). Prior studies using this data have remarked on the limitations of findings given likely underdiagnosis. The availability of cardiac MRI scans on a fraction of the participants offers an opportunity to identify missed diagnoses.Aims:This study seeks to utilize a generalizable deep learning model to detect likely cases of undiagnosed hypertrophic cardiomyopathy from cardiac MRIs in the UK Biobank.Methods:The foundational model was trained on a multi-institutional dataset of 14,073 cardiac MRIs via a self-supervised contrastive learning approach that sought to minimize the divergence between scans and their associated radiology reports. The pre-trained model was fine-tuned to diagnose hypertrophic cardiomyopathy on a distinct cohort of 4,870 MRIs with 368 cases of HCM, achieving an AUC of 0.94. The fine-tuned model was applied to the UK Biobank cardiac MRI dataset to ascertain predicted probabilities of HCM. Cases exceeding a threshold of 95% – correlating to the top 0.5% of cases (expected specificity of 97% and sensitivity of 60%) – were screened in for manual reading. In a blinded fashion, a board-certified radiologist was tasked with diagnosing HCM on a sample of cases composed of high and low predicted probabilities.Results:Of the 43,017 patients with cardiac MRIs, only 9 (.02%) had an ICD diagnosis of HCM. 266 cardiac MRIs were manually reviewed: 216 had greater than 95% predicted probability of HCM; 50 negative controls were randomly selected amongst cases with predicted probability less than 10%. The radiologist concurred with an HCM diagnosis for 115 cases (sensitivity 53%, specificity 98%), 112 of which were previously undiagnosed. The prevalence of hypertension and aortic stenosis did not significantly differ between the cohort of true positives (69.2%) and false positives (76.6%). The corrected prevalence of HCM in the UK BioBank MRI cohort is estimated at 0.28%.Conclusions:The findings of this study illustrate the remarkable ability of a generalizable deep learning model to detect undiagnosed cases of a rare disease process from cardiac MRIs. This is an important milestone that may allow for widespread screening of hypertrophic cardiomyopathy while minimizing demand for radiologist labor, and thereby allow patients to reap the substantial benefits of earlier treatment.

Circulation, Volume 150, Issue Suppl_1, Page A4137770-A4137770, November 12, 2024. Background:Metabolic syndrome is a cluster of conditions that increase the risk of heart disease and diabetes. Early identification and management are crucial, particularly in economically challenged regions where access to healthcare may be limited.Research Questions/Hypothesis:User-friendly self-report data accurately predict metabolic outcomes.Aims:To develop and validate nomograms for individualized estimation of metabolic syndrome risk.Methods:Data from 521 college students (60.1% aged 17-20 years; 68.7% female; 28.0% white) were collected in 2022/2023 from two Brazilian cities. These cities are located in the country’s poorest states, with Gini indices of 0.56 and 0.43. The potential predictors include demographic and economic variables, school-related factors, behaviors, and body weight. Based on predictors for abdominal obesity identified through multilevel logistic regression, we created a nomogram model. We performed the Hosmer-Lemeshow test to assess model calibration and used a bootstrapping approach (B = 150) for internal validation. To evaluate external validity, we assessed metabolic syndrome in a subset of 375 students. The area under the receiver operating characteristic curve (AUROC), with a threshold of 0.70, was used to evaluate the model’s discrimination accuracy.Results:We identified 114 (23.0%) college students who were abdominally obese. We found ten variables associated with the primary outcome: age, biological sex, physical education facilities, enrollment in sports competition (during elementary school); grade retention, preferred subject, physical education classes per week; enrollment in sports training (during secondary school); adherence of 24-hour movement behaviors and body weight. The proposed nomogram showed acceptable performance in the AUROC (0.94 [95% CI: 0.92-0.96). The calibration assessment indicated reasonable consistency of our model (p > 0.05). In the internal validation, we observed a decreased predictive capability (AUROC = 0.86).Conclusion:The 24h-MESYN risk score offers an effective self-screening tool for college students from diverse racial and ethnic backgrounds in economically challenged regions to assess their risk of developing metabolic syndrome.

Circulation, Volume 150, Issue Suppl_1, Page A4143538-A4143538, November 12, 2024. Introduction:Transthyretin amyloid cardiomyopathy (ATTR-CM) is an underdiagnosed disease that may result in heart failure (HF), arrhythmias, and valvular disease. Our aim was to develop (1) screening criteria to identify high-risk patients for ATTR-CM and (2) our own predictive tool of ATTR-CM.Methods:This was a prospective observational registry at 2 academic sites in Canada. We designed screening criteria to identify high-risk patients in HF, atrial fibrillation, transcatheter valve clinics, and in cardiologist’s offices from January 2019-December 2022. Patients >60 years were included if one of several screening criteria was met and they were referred for pyrophosphate scan by the cardiologist. Univariate and multivariate logistic regression were used to identify predictive clinical, imaging, and biochemical characteristics.Results:In total, 2500 patients were screened, and 200 patients were enrolled with a follow-up duration of 3 years. The mean age was 78 years and 65% were male. Forty-six (23%) had a diagnosis of ATTR-CM and 7 (4%) were diagnosed with AL-amyloidosis. ATTR-CM patients were older (83±7 vs. 77±8; p

Circulation, Volume 150, Issue Suppl_1, Page A4147292-A4147292, November 12, 2024. Background:Tissue hypoxia and chronic anemia associated with sickle cell disease (SCD) leads to structural and physiological alterations in the heart. Early detection of heart failure (HF) in patients with SCD can assist with timely interventions, but current methods (e.g., echocardiogram and heart MRI) are not easily accessible in resource-deprived settings. The integration of artificial intelligence (AI)-powered tools utilizing low-cost ECG data to increase the power to detect more patients eligible for early treatment, thus improving patient outcomes, and needs to be validated.Hypothesis:We hypothesize that ECG-AI models developed to detect incident HF in the general population can detect HF in SCD patients.Methods/Approach:We previously developed an ECG-AI model employing convolutional neural networks to classify patients with HF using a large ECG-repository at Wake Forest Baptist Health (WFBH). This model was developed using 1,078,198 digital ECGs from 165,243 patients, 73% White, 19% Black, and 52% female individuals, with a mean age (SD) of 58 (15) years. The hold-out AUC of this previous model in distinguishing ECGs of HF patients from controls was 0.87. In this study, we externally validated this ECG-AI model using SCD patients’ data from the University of Tennessee Health Science Center (UTHSC). Additionally, a logistic regression (LR) model was constructed in the UTHSC cohort by incorporating other simple demographic variables with the outcome of ECG-AI model.Results/Data:The UTHSC external validation cohort included data from 2,107 SCD patients (188 HF and 1,919 SCD patients with no HF), 98% were Black, 72% were female, with a mean age of 39 (14) years. Despite demographic differences between the validation (more Blacks) and derivation cohorts (lower age), our ECG-AI model accurately identified HF with an AUC of 0.80 (0.77-0.82) in the UTHSC SCD cohort. When incorporating ECG-AI outcome (an ECG-based risk value between 0 and 1), age, sex, and race in a LR model, the AUC significantly improved (DeLong Test, p

Circulation, Volume 150, Issue Suppl_1, Page A4145524-A4145524, November 12, 2024. Introduction:White-coat hypertension (WCH) and masked hypertension (MH) complicate accurate blood pressure (BP) monitoring. While ambulatory BP monitoring (ABPM) is effective, its high cost and limited availability are significant barriers.Hypothesis:We hypothesized that a machine learning (ML) model using clinical data from a single outpatient visit could accurately predict WCH and MH.Aims:This study aimed to develop and validate ML-based prediction models for WCH and MH using accessible clinical data to improve diagnostic efficiency and accessibility.Methods:We enrolled patients from two hypertension cohorts, after excluding those with incomplete data. Patients were classified by office BP and ABPM readings per American Heart Association guidelines. ML models, including Multi-layer Perceptron （MLP）, Support Vector Machine (SVM), and Tabular Prior-Data Fitted Network (Tab-PFN), were developed. Input parameters included demographic data (age, gender, height, weight, smoker), and office BP (OBP) and heart rate measurements. Principal Component Analysis (PCA), kernel PCA (kPCA), or t-distributed stochastic neighbor embedding (t-SNE) were used to improve class separability.Results:The study population comprised 1481 participants with a mean age of 47.6 years (SD 13.6), 65% of whom were male and 20.1% were smokers. OBP measurements showed a mean systolic BP (SBP) of 128.7 mmHg (SD 15.4) and a mean diastolic BP (DBP) of 84.2 mmHg (SD 11.6). ABPM showed a mean 24-hour systolic BP of 122.5 mmHg (SD 11.8) and diastolic BP of 79.3 mmHg (SD 10.1). The inclusion of demographic and OBP data, along with advanced resampling and dimensionality reduction techniques, significantly improved the model’s predictive ability. The final TabPFN model achieved the best performance with recall, precision, F1 score, and accuracy of 0.747, 0.931, 0.829, and 0.807 for WCH, and 0.713, 0.954, 0.816, and 0.907 for MH.Conclusion:Our ML-based model effectively predicts WCH and MH using accessible clinical data, offering a cost-effective alternative before applying ABPM.

Circulation, Volume 150, Issue Suppl_1, Page A4144083-A4144083, November 12, 2024. Background:The AI-CVD initiative aims to extract all useful opportunistic screening information from coronary artery calcium (CAC) scans and combines them with traditional risk factors to create a stronger predictor of cardiovascular diseases (CVD). These measurements include cardiac chambers volumes (left atrium (LA), left ventricle (LV), right atrium (RA), right ventricle (RV), and left ventricular mass (LVM)), aortic wall and valvular calcification, aorta and pulmonary artery volumes, torso visceral fat, emphysema score, thoracic bone mineral density, and fatty liver score. We have previously reported that the automated cardiac chambers volumetry component of AI-CVD predicts incident atrial fibrillation (AF), heart failure (HF), and stroke in the Multi-Ethnic Study of Atherosclerosis (MESA). In this report, we examine the contribution of other AI-CVD components for all coronary heart disease (CHD), AF, HF, stroke plus transient ischemic attack (TIA), all-CVD, and all-cause mortality.Methods:We applied AI-CVD to CAC scans of 5830 individuals (52.2% women, age 61.7±10.2 years) without known CVD that were previously obtained for CAC scoring at MESA baseline examination. We used 10-year outcomes data and assessed hazard ratios for AI-CVD components plus CAC score and known CVD risk factors (age, sex, diabetes, smoking, LDL-C, HDL-C, systolic and diastolic blood pressure, hypertension medication). AI-CVD predictors were modeled per standard deviation (SD) increase using Cox proportional hazards regression.Results:Over 10 years of follow-up, 1058 CVD (550 AF, 198 HF, 163 stroke, 389 CHD) and 628 all-cause mortality events accrued with some cases having multiple events. Among AI-CVD components, CAC score and chamber volumes were the strongest predictors of different outcomes. Expectedly, age was the strongest predictor for all outcomes except HF where LV volume and LV mass were stronger predictors than age. Figure 1 shows contribution of each predictor for various outcomes.Conclusion:AI-enabled opportunistic screening of useful information in CAC scans contributes substantially to CVD and total mortality prediction independently of CAC score and CVD risk factors. Further studies are warranted to evaluate the clinical utility of AI-CVD.