Holistic AI analysis of hybrid cardiac perfusion images for mortality prediction.

Background: While low-dose computed tomography scans are traditionally used for attenuation correction in hybrid myocardial perfusion imaging (MPI), they also contain additional anatomic and pathologic information not utilized in clinical assessment. We seek to uncover the full potential of these scans utilizing a holistic artificial intelligence (AI)-driven image framework for image assessment. Methods: Patients with SPECT/CT MPI from 4 REFINE SPECT registry sites were studied. A multi-structure model segmented 33 structures and quantified 15 radiomics features for each on CT attenuation correction (CTAC) scans. Coronary artery calcium and epicardial adipose tissue scores were obtained from separate deep-learning models. Normal standard quantitative MPI features were derived by clinical software. Extreme Gradient Boosting derived all-cause mortality risk scores from SPECT, CT, stress test, and clinical features utilizing a 10-fold cross-validation regimen to separate training from testing data. The performance of the models for the prediction of all-cause mortality was evaluated using area under the receiver-operating characteristic curves (AUCs). Results: Of 10,480 patients, 5,745 (54.8%) were male, and median age was 65 (interquartile range [IQR] 57-73) years. During the median follow-up of 2.9 years (1.6-4.0), 651 (6.2%) patients died. The AUC for mortality prediction of the model (combining CTAC, MPI, and clinical data) was 0.80 (95% confidence interval [0.74-0.87]), which was higher than that of an AI CTAC model (0.78 [0.71-0.85]), and AI hybrid model (0.79 [0.72-0.86]) incorporating CTAC and MPI data (p<0.001 for all). Conclusion: In patients with normal perfusion, the comprehensive model (0.76 [0.65-0.86]) had significantly better performance than the AI CTAC (0.72 [0.61-0.83]) and AI hybrid (0.73 [0.62-0.84]) models (p<0.001, for all).CTAC significantly enhances AI risk stratification with MPI SPECT/CT beyond its primary role - attenuation correction. A comprehensive multimodality approach can significantly improve mortality prediction compared to MPI information alone in patients undergoing cardiac SPECT/CT.

Influence of Body Mass Index on Radiation Exposure Across Imaging Modalities in the Evaluation of Chest Pain.

BACKGROUND: Essential to a patient-centered approach to imaging individuals with chest pain is knowledge of differences in radiation effective dose across imaging modalities. Body mass index (BMI) is an important and underappreciated predictor of effective dose. This study evaluated the impact of BMI on estimated radiation exposure across imaging modalities. METHODS AND RESULTS: This was a retrospective analysis of patients with concern for cardiac ischemia undergoing positron emission tomography (PET)/computed tomography (CT), cadmium zinc telluride single-photon emission CT (SPECT) myocardial perfusion imaging, or coronary CT angiography (CCTA) using state-of-the-art imaging modalities and optimal radiation-sparing protocols. Radiation exposure was calculated across BMI categories based on established cardiac imaging-specific conversion factors. Among 9046 patients (mean±SD age, 64.3±13.1 years; 55% men; mean±SD BMI, 30.6±6.9 kg/m2), 4787 were imaged with PET/CT, 3092 were imaged with SPECT/CT, and 1167 were imaged with CCTA. Median (interquartile range) radiation effective doses were 4.4 (3.9-4.9) mSv for PET/CT, 4.9 (4.0-6.3) mSv for SPECT/CT, and 6.9 (4.0-11.2) mSv for CCTA. Patients at a BMI <20 kg/m2 had similar radiation effective dose with all 3 imaging modalities, whereas those with BMI ≥20 kg/m2 had the lowest effective dose with PET/CT. Radiation effective dose and variability increased dramatically with CCTA as BMI increased, and was 10 times higher in patients with BMI >45 kg/m2 compared with <20 kg/m2 (median, 26.9 versus 2.6 mSv). After multivariable adjustment, PET/CT offered the lowest effective dose, followed by SPECT/CT, and then CCTA (P<0.001). CONCLUSIONS: Although median radiation exposure is modest across state-of-the-art PET/CT, SPECT/CT, and CCTA systems using optimal radiation-sparing protocols, there are significant variations across modalities based on BMI. These data are important for making patient-centered decisions for ischemic testing.

Cardiovascular testing recovery in Latin America one year into the COVID-19 pandemic: An analysis of data from an international longitudinal survey.

Background: The COVID-19 pandemic disproportionately impacted Latin America (LATAM), significantly disrupting cardiovascular testing. This study evaluated cardiac procedure recovery in LATAM one year after the outbreak. Methods: The International Atomic Energy Agency (IAEA) surveyed 669 centers in 107 countries worldwide, including 135 facilities in 19 LATAM countries, to assess cardiovascular procedure volumes in March 2019, April 2020, and April 2021, and changes in center practices and staffing conditions one year into the COVID-19 pandemic. Findings: LATAM centers reported a 21 % decrease in procedure volumes in April 2021 from pre-pandemic-baseline, vs. a 0 % change in the rest of the world (RoW), and greater volume reductions for almost all procedure types. Centers in Central America and Mexico reported the largest procedure reductions (47 % reduction) compared to the Caribbean (15 %), and South America (14 %, p = 0.01), and this LATAM region was a significant predictor of lower procedure recovery in multivariable regression. More LATAM centers reported reduced salaries and increased layoffs of clinical staff compared to RoW, and LATAM respondents estimated that half of physician and non-physician staff experienced excess psychological stress related to the pandemic, compared to 25 % and 30 % in RoW (p < 0.001). Conclusions: Cardiovascular testing recovery in LATAM trailed behind RoW for most procedure types, with centers in Central America and Mexico reporting the greatest volume reductions. This study found lasting impacts of COVID-19 on cardiovascular care in LATAM and the need for mental health support for LATAM healthcare workers in current and future pandemics.

Predicting mortality from AI cardiac volumes mass and coronary calcium on chest computed tomography.

Chest computed tomography is one of the most common diagnostic tests, with 15 million scans performed annually in the United States. Coronary calcium can be visualized on these scans, but other measures of cardiac risk such as atrial and ventricular volumes have classically required administration of contrast. Here we show that a fully automated pipeline, incorporating two artificial intelligence models, automatically quantifies coronary calcium, left atrial volume, left ventricular mass, and other cardiac chamber volumes in 29,687 patients from three cohorts. The model processes chamber volumes and coronary artery calcium with an end-to-end time of ~18 s, while failing to segment only 0.1% of cases. Coronary calcium, left atrial volume, and left ventricular mass index are independently associated with all-cause and cardiovascular mortality and significantly improve risk classification compared to identification of abnormalities by a radiologist. This automated approach can be integrated into clinical workflows to improve identification of abnormalities and risk stratification, allowing physicians to improve clinical decision-making.

Deep learning to detect left ventricular structural abnormalities in chest X-rays.

BACKGROUND AND AIMS: Early identification of cardiac structural abnormalities indicative of heart failure is crucial to improving patient outcomes. Chest X-rays (CXRs) are routinely conducted on a broad population of patients, presenting an opportunity to build scalable screening tools for structural abnormalities indicative of Stage B or worse heart failure with deep learning methods. In this study, a model was developed to identify severe left ventricular hypertrophy (SLVH) and dilated left ventricle (DLV) using CXRs. METHODS: A total of 71 589 unique CXRs from 24 689 different patients completed within 1 year of echocardiograms were identified. Labels for SLVH, DLV, and a composite label indicating the presence of either were extracted from echocardiograms. A deep learning model was developed and evaluated using area under the receiver operating characteristic curve (AUROC). Performance was additionally validated on 8003 CXRs from an external site and compared against visual assessment by 15 board-certified radiologists. RESULTS: The model yielded an AUROC of 0.79 (0.76-0.81) for SLVH, 0.80 (0.77-0.84) for DLV, and 0.80 (0.78-0.83) for the composite label, with similar performance on an external data set. The model outperformed all 15 individual radiologists for predicting the composite label and achieved a sensitivity of 71% vs. 66% against the consensus vote across all radiologists at a fixed specificity of 73%. CONCLUSIONS: Deep learning analysis of CXRs can accurately detect the presence of certain structural abnormalities and may be useful in early identification of patients with LV hypertrophy and dilation. As a resource to promote further innovation, 71 589 CXRs with adjoining echocardiographic labels have been made publicly available.

Impact of cardiac size on SPECT myocardial perfusion imaging performance: Insights from the REFINE-SPECT registry.

AIMS: Variation in diagnostic performance of SPECT myocardial perfusion imaging (MPI) has been observed, yet the impact of cardiac size has not been well characterized. We assessed whether low left ventricular volume influences SPECT MPI's ability to detect obstructive coronary artery disease (CAD), and its interaction with age and sex. METHODS AND RESULTS: A total of 2,066 patients without known CAD (67% male, 64.7 ± 11.2 years) across 9 institutions underwent SPECT MPI with solid-state scanners followed by coronary angiography as part of the REgistry of Fast Myocardial Perfusion Imaging with NExt Generation SPECT. Area under receiver-operating characteristic curve (AUC) analyses evaluated performance of quantitative and visual assessments according to cardiac size (end- diastolic volume [EDV]; < 20th vs. ≥ 20th population or sex-specific percentiles), age (<75 vs. ≥ 75 years), and sex. Significantly decreased performance was observed in patients with low EDV compared to those without (AUC: population 0.72 vs. 0.78, p = 0.03; sex-specific 0.72 vs. 0.79, p = 0.01) and elderly patients compared to younger patients (AUC 0.72 vs. 0.78, p = 0.03), whereas males and females demonstrated similar AUC (0.77 vs. 0.76, p = 0.67). The reduction in accuracy attributed to lower volumes was primarily observed in males (sex-specific threshold: EDV 0.69 vs. 0.79, p = 0.01). Accordingly, a significant decrease in AUC, sensitivity, specificity, and negative predictive value for quantitative and visual assessments was noted in patients with at least two characteristics of low EDV, elderly age, or male sex. CONCLUSIONS: Detection of CAD with SPECT MPI is negatively impacted by small cardiac size, most notably in elderly and male patients.

Recovery Rates of Diagnostic Cardiac Procedural Volume in Oceania 1 Year Into COVID-19: The IAEA Non-Invasive Cardiology Protocol Survey on COVID-19 (INCAPS COVID 2).

AIM: The aim of this study was to assess the recovery rates of diagnostic cardiac procedure volumes in the Oceania Region, midway through the coronavirus disease 2019 (COVID-19) pandemic. METHODS: A survey was performed comparing procedure volumes between March 2019 (pre-pandemic), April 2020 (during first wave of COVID-19 pandemic), and April 2021 (1 year into the COVID-19 pandemic). A total of 31 health care facilities within Oceania that perform cardiac diagnostic procedures were surveyed, including a mixture of metropolitan and regional, hospital and outpatient, public and private sites, as well as teaching and non-teaching hospitals. A comparison was made with 549 centres in 96 countries in the rest of the world (RoW) outside of Oceania. The total number and median percentage change in procedure volume were measured between the three timepoints, compared by test type and by facility. RESULTS: A total of 11,902 cardiac diagnostic procedures were performed in Oceania in April 2021 as compared with 11,835 pre-pandemic in March 2019 and 5,986 in April 2020; whereas, in the RoW, 499,079 procedures were performed in April 2021 compared with 497,615 pre-pandemic in March 2019 and 179,014 in April 2020. There was no significant difference in the median recovery rates for total procedure volumes between Oceania (-6%) and the RoW (-3%) (p=0.81). While there was no statistically significant difference in percentage recovery been functional ischaemia testing and anatomical coronary testing in Oceania as compared with the RoW, there was, however, a suggestion of poorer recovery in anatomical coronary testing in Oceania as compared with the RoW (CT coronary angiography -16% in Oceania vs -1% in RoW, and invasive coronary angiography -20% in Oceania vs -9% in RoW). There was no statistically significant difference in recovery rates in procedure volume between metropolitan vs regional (p=0.44), public vs private (p=0.92), hospital vs outpatient (p=0.79), or teaching vs non-teaching centres (p=0.73). CONCLUSIONS: Total cardiology procedure volumes in Oceania normalised 1 year post-pandemic compared to pre-pandemic levels, with no significant difference compared with the RoW and between the different types of health care facilities.

AI-derived epicardial fat measurements improve cardiovascular risk prediction from myocardial perfusion imaging.

Epicardial adipose tissue (EAT) volume and attenuation are associated with cardiovascular risk, but manual annotation is time-consuming. We evaluated whether automated deep learning-based EAT measurements from ungated computed tomography (CT) are associated with death or myocardial infarction (MI). We included 8781 patients from 4 sites without known coronary artery disease who underwent hybrid myocardial perfusion imaging. Of those, 500 patients from one site were used for model training and validation, with the remaining patients held out for testing (n = 3511 internal testing, n = 4770 external testing). We modified an existing deep learning model to first identify the cardiac silhouette, then automatically segment EAT based on attenuation thresholds. Deep learning EAT measurements were obtained in <2 s compared to 15 min for expert annotations. There was excellent agreement between EAT attenuation (Spearman correlation 0.90 internal, 0.82 external) and volume (Spearman correlation 0.90 internal, 0.91 external) by deep learning and expert segmentation in all 3 sites (Spearman correlation 0.90-0.98). During median follow-up of 2.7 years (IQR 1.6-4.9), 565 patients experienced death or MI. Elevated EAT volume and attenuation were independently associated with an increased risk of death or MI after adjustment for relevant confounders. Deep learning can automatically measure EAT volume and attenuation from low-dose, ungated CT with excellent correlation with expert annotations, but in a fraction of the time. EAT measurements offer additional prognostic insights within the context of hybrid perfusion imaging.

Disparities in Noninvasive Traditional and Advanced Testing for Coronary Artery Disease: Findings from the INCAPS-COVID 2 Study.

The COVID-19 pandemic disrupted the delivery of cardiovascular care, including noninvasive testing protocols and test selection for the evaluation of coronary artery disease (CAD). Trends in test selection in traditional versus advanced noninvasive tests for CAD during the pandemic and in countries of varying income status have not been well studied. The International Atomic Energy Agency conducted a global survey to assess the pandemic-related changes in the practice of cardiovascular diagnostic testing. Site procedural volumes for noninvasive tests to evaluate CAD from March 2019 (prepandemic), April 2020 (onset), and April 2021 (initial recovery) were collected. We considered traditional testing modalities, such as exercise electrocardiography, stress echocardiography, and stress single-photon emission computed tomography, and advanced testing modalities, such as stress cardiac magnetic resonance, coronary computed tomography angiography, and stress positron emission tomography. Survey data were obtained from 669 centers in 107 countries, reporting the performance of 367,933 studies for CAD during the study period. Compared with 2019, traditional tests were performed 14% less frequently (recovery rate 82%) in 2021 versus advanced tests, which were performed 15% more frequently (128% recovery rate). Coronary computed tomography angiography, stress cardiac magnetic resonance, and stress positron emission tomography showed 14%, 25%, and 25% increases in volumes from 2019 to 2021, respectively. The increase in advanced testing was isolated to high- and upper middle-income countries, with 132% recovery in advanced tests by 2021 compared with 55% in lower income nations. The COVID-19 pandemic exacerbated economic disparities in CAD testing practice between wealthy and poorer countries. Greater recovery rates and even new growth were observed for advanced imaging modalities; however, this growth was restricted to wealthy countries. Efforts to reduce practice variations in CAD testing because of economic status are warranted.

Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study.

BACKGROUND: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. METHODS: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. FINDINGS: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64-8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53-3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40-2.36). INTERPRETATION: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. FUNDING: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].

Cardiovascular Testing in the United States during the COVID-19 Pandemic: Volume Recovery and Worldwide Comparison.

Purpose: To characterize the recovery of diagnostic cardiovascular procedure volumes in U.S. and non-U.S. facilities in the year following the initial COVID-19 outbreak. Materials and Methods: The International Atomic Energy Agency (IAEA) coordinated a worldwide study called the IAEA Noninvasive Cardiology Protocols Study of COVID-19 2 (INCAPS COVID 2), collecting data from 669 facilities in 107 countries, including 93 facilities in 34 U.S. states, to determine the impact of the pandemic on diagnostic cardiovascular procedure volumes. Participants reported volumes for each diagnostic imaging modality used at their facility for March 2019 (baseline), April 2020, and April 2021. This secondary analysis of INCAPS COVID 2 evaluated differences in changes in procedure volume between U.S. and non-U.S. facilities and among U.S. regions. Factors associated with return to prepandemic volumes in the United States were also analyzed in a multivariable regression analysis. Results: Reduction in procedure volumes in April 2020 compared with baseline was similar for U.S. and non-U.S. facilities (-66% vs -71%, P = .27). U.S. facilities reported greater return to baseline in April 2021 than did all non-U.S. facilities (4% vs -6%, P = .008), but there was no evidence of a difference when comparing U.S. facilities with non-U.S. high-income country (NUHIC) facilities (4% vs 0%, P = .18). U.S. regional differences in return to baseline were observed between the Midwest (11%), Northeast (9%), South (1%), and West (-7%, P = .03), but no studied factors were significant predictors of 2021 change from prepandemic baseline. Conclusion: The reductions in cardiac testing during the early pandemic have recovered within a year to prepandemic baselines in the United States and NUHICs, while procedure volumes remain depressed in lower-income countries.Keywords: SPECT, Cardiac, Epidemiology, Angiography, CT Angiography, CT, Echocardiography, SPECT/CT, MR Imaging, Radionuclide Studies, COVID-19, Cardiovascular Imaging, Diagnostic Cardiovascular Procedure, Cardiovascular Disease, Cardiac Testing Supplemental material is available for this article. © RSNA, 2023.

Evaluating Radiation Exposure in Patients with Stable Chest Pain in the SCOT-HEART Trial.

Background In the Scottish Computed Tomography of the Heart (SCOT-HEART) trial in individuals with stable chest pain, a treatment strategy based on coronary CT angiography (CTA) led to improved outcomes. Purpose To assess 5-year cumulative radiation doses of participants undergoing investigation for suspected angina due to coronary artery disease with or without coronary CTA. Materials and Methods This secondary analysis of the SCOT-HEART trial included data from six of 12 recruiting sites and two of three imaging sites. Participants were recruited between November 18, 2010, and September 24, 2014, with follow-up through January 31, 2018. Study participants had been randomized (at a one-to-one ratio) to standard care with CT (n = 1466) or standard care alone (n = 1428). Imaging was performed on a 64-detector (n = 223) or 320-detector row scanner (n = 1466). Radiation dose from CT (dose-length product), SPECT (injected activity), and invasive coronary angiography (ICA; kerma-area product) was assessed for 5 years after enrollment. Effective dose was calculated using conversion factors appropriate for the imaging modality and body region imaged (using 0.026 mSv/mGy · cm for cardiac CT). Results Cumulative radiation dose was assessed in 2894 participants. Median effective dose was 3.0 mSv (IQR, 2.6-3.3 mSv) for coronary calcium scoring, 4.1 mSv (IQR, 2.6-6.1 mSv) for coronary CTA, 7.4 mSv (IQR, 6.2-8.5 mSv) for SPECT, and 4.1 mSv (IQR, 2.5-6.8 mSv) for ICA. After 5 years, total per-participant cumulative dose was higher in the CT group (median, 8.1 mSv; IQR, 5.5-12.4 mSv) compared with standard-care group (median, 0 mSv; IQR, 0-4.5 mSv; P < .001). In participants who underwent any imaging, cumulative radiation exposure was higher in the CT group (n = 1345; median, 8.6 mSv; IQR, 6.1-13.3 mSv) compared with standard-care group (n = 549; median, 6.4 mSv; IQR, 3.4-9.2 mSv; P < .001). Conclusion In the SCOT-HEART trial, the 5-year cumulative radiation dose from cardiac imaging was higher in the coronary CT angiography group compared with the standard-care group, largely because of the radiation exposure from CT. Clinical trial registration no. NCT01149590 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Dodd and Bosserdt in this issue.

Flexible-Interval High-Sensitivity Troponin Velocity for the Detection of Acute Coronary Syndromes.

Many algorithms for emergency department (ED) evaluation of acute coronary syndrome (ACS) using high-sensitivity troponin assays rely on the detection of a "delta," the difference in concentration over a predetermined interval, but collecting specimens at specific times can be difficult in the ED. We evaluate the use of troponin "velocity," the rate of change of troponin concentration over a flexible short interval for the prediction of major adverse cardiac events (MACEs) at 30 days. We conducted a prospective, observational study on a convenience sample of 821 patients who underwent ACS evaluation at a high-volume, urban ED. We determined the diagnostic performance of a novel velocity-based algorithm and compared the performance of 1- and 2-hour algorithms adapted from the European Society of Cardiology (ESC) using delta versus velocity. A total of 7 of 332 patients (2.1%) classified as low risk by the velocity-based algorithm experienced a MACE by 30 days compared with 35 of 221 (13.8%) of patients classified as greater than low risk, yielding a sensitivity of 83.3% (95% confidence interval [CI] 68.6% to 93.0%) and negative predictive value (NPV) of 97.9% (95% CI 95.9% to 98.9%). The ESC-derived algorithms using delta or velocity had NPVs ranging from 98.4% (95% CI 96.4% to 99.3%) to 99.6% (95% CI 97.0% to 99.9%) for 30-day MACEs. The NPV of the novel velocity-based algorithm for MACE at 30 days was borderline, but the substitution of troponin velocity for delta in the framework of the ESC algorithms performed well. In conclusion, specimen collection within strict time intervals may not be necessary for rapid evaluation of ACS with high-sensitivity troponin.

Clinical Penetrance of the Transthyretin V122I Variant in Older Black Patients With Heart Failure: The SCAN-MP (Screening for Cardiac Amyloidosis With Nuclear Imaging in Minority Populations) Study.

Background Transthyretin amyloid cardiomyopathy (ATTR-CM) is an underdiagnosed cause of heart failure (HF) among patients ≥60 years of age. Although the V122I (valine to isoleucine substitution at position 122 of the transthyretin protein) variant associated with hereditary ATTR-CM is present in 3.4% of self-identified Black individuals in the United States (or 1.5 million people), the phenotypic penetrance is not known. Methods and Results The SCAN-MP (Screening for Cardiac Amyloidosis With Nuclear Imaging in Minority Populations) study is a currently accruing prospective multisite study designed to determine the prevalence of ATTR-CM using technetium-99m-pyrophosphate imaging in older (≥60 years of age) self-identified Black and Hispanic individuals with HF. Calculations of the penetrance and prevalence of the V122I allele, along with analyses of functional, biochemical, and echocardiographic parameters, were performed for the first 278 Black participants in SCAN-MP. The prevalence of ATTR-CM was 6.8% (95% CI, 4.2-10.5; n=19 cases), of whom 63% were ATTR wild-type. The prevalence of V122I was 6.5% (n=18 carriers), of whom 7 had ATTR-CM, yielding a phenotypic penetrance of 39% (95% CI, 17-64). V122I carriers with ATTR-CM evidenced more advanced HF than carriers without ATTR-CM. Prealbumin concentration was lowest among V122I carriers with ATTR-CM (12.9 mg/dL) versus carriers without ATTR-CM (21.0 mg/dL) and HF controls (25.0 mg/dL, P<0.0001). Conclusions Among older Black individuals with HF and increased left ventricular wall thickness, of those with ATTR-CM, 63% had wild-type, and of those with V122I, the phenotypic penetrance of ATTR-CM was 39% (95% CI, 17-64), suggesting that genotype alone is insufficient for diagnosis. Prealbumin concentration may be useful to identify V122I carriers with ATTR-CM. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT03812172.

Prevalence and significance of extracardiac uptake on pyrophosphate imaging in the SCAN-MP study: the first 379 cases.

INTRODUCTION: Technetium-labeled bone-avid radiotracers can be used to diagnose transthyretin cardiac amyloidosis (ATTR-CA). Extracardiac uptake of technetium pyrophosphate (Tc-99m PYP) in this context has not been extensively explored and its significance is not well characterized. We assessed extracardiac Tc-99m PYP uptake in individuals undergoing nuclear scintigraphy and the extent of clinically actionable findings. METHODS: The Screening for Cardiac Amyloidosis with Nuclear Imaging in Minority Populations (SCAN-MP) study utilizes Tc-99m PYP imaging to identify ATTR-CA in self-identified Black and Caribbean Hispanic participants ≥ 60 years old with heart failure. We characterized the distribution of extracardiac uptake, including stratification of findings by timing of scan (1 hour vs 3 hours after Tc-99m PYP administration) and noted any additional testing in these subjects. RESULTS: Of 379 participants, 195 (51%) were male, 306 (81%) Black race, and 120 (32%) Hispanic ethnicity; mean age was 73 years. Extracardiac Tc-99m PYP uptake was found in 42 subjects (11.1%): 21 with renal uptake only, 14 with bone uptake only, 4 with both renal and bone uptake, 2 with breast uptake, and 1 with thyroid uptake. Extracardiac uptake was more common in subjects with Tc-99m PYP scans at 1 hour (23.8%) than at 3 hours (6.2%). Overall, four individuals (1.1%) had clinically actionable findings. CONCLUSION: Extracardiac Tc-99m PYP uptake manifested in about 1 in 9 SCAN-MP subjects but was clinically actionable in only 1.1% of cases.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging.

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.