Miller, Robert J.H.

Summary Background Body composition is recognized as a major determinant of health outcomes, but its multidimensional nature makes clinical adoption challenging. We sought to develop and validate a body composition index (BCI) for all-cause mortality risk assessment, integrating variables of six body composition tissues. Methods We analyzed 28509 consecutive patients undergoing myocardial perfusion imaging with routine low-dose chest CT attenuation correction (CTAC) scans acquired during myocardial perfusion imaging (MPI) at 12 centers across four countries. An artificial intelligence-based BCI was developed in a cohort of 15037 patients’ CTACs by integrating the CT-derived metrics of bone, skeletal muscle, and four adipose tissue compartments, coronary artery calcium score, and basic demographic variables (age, sex, BMI). The performance of BCI for mortality prediction was validated in an internal cohort of 6444 patients and an external cohort of 7028 patients by prognosis, calibration, net benefit, and explainability. Model-based simulation of tissue metrics modification was performed to evaluate estimated mortality risk reduction. Findings During a median of 3.5 (IQR [1.9, 5.1]) years, 4697 (16%) patients died. In the external testing cohort, the BCI demonstrated excellent discrimination for mortality (area under receiver operating characteristic curve 0.78 (95% CI [0.76, 0.79]) and Harrell’s concordance index 0.75 [0.73, 0.76]), calibration, and net benefit overall and across pre-specified subgroups stratified by patient characteristics and imaging protocols. Visceral adipose tissue attenuation was the most influential body composition measure, followed by skeletal muscle volume. Simulated improvement in body composition was associated with significant mortality risk reduction. Interpretation An index combining six body composition measures obtained opportunistically from routine chest CT provides robust mortality risk stratification. By converting complex body composition information into a single interpretable score, the BCI can facilitate clinical implementation of opportunistic CT biomarkers and guide individualized preventive strategies. Funding National Institute of Health Research in context Evidence before this study We searched PubMed and Google Scholar on July 7, 2026 for English language studies using the terms (“mortality prediction” OR “death prediction”) AND (“integrated body composition analysis” OR “body composition metrics integration”) AND (“predictive model” OR “model development”), and identified 41 publications describing predictive models incorporating body composition metrics. Recent advances in artificial intelligence (AI) have enabled increasingly granular quantification of body composition from CT, with multiple tissues and tissue-specific metrics showing independent prognostic value for all-cause mortality (ACM) prediction. However, reported associations of body composition metrics with mortality risk were highly inconsistent or even contradictory across studies. This heterogeneity likely reflected the differences in study design or the inherent complexity of body composition analysis, such as the interaction among variables derived from multiple tissues. Thus, it is difficult to interpret body composition results reliably in clinical practice. We hypothesized that integrating multiple body composition metrics could achieve comprehensive and reliable prediction of mortality across patient populations. Added value of this study In this large international, multicenter longitudinal cohort study of 28509 consecutive patients with suspected or known coronary artery disease (CAD) undergoing myocardial perfusion imaging across 12 sites in four countries, we developed and externally validated an artificial intelligence-based body composition index (BCI) for all-cause mortality prediction. The BCI integrated chest CT-derived metrics of six body composition tissue compartments – bone, skeletal muscle (SM), subcutaneous adipose tissue (SAT), intramuscular adipose tissue (IMAT), visceral adipose tissue (VAT), and epicardial adipose tissue (EAT), together with demographics (age, sex, BMI) and CT-derived coronary artery calcium (CAC) score, all derived automatically from routine low-dose attenuation correction CT scans without additional imaging or laboratory tests. In an external validation cohort of 7028 patients, the BCI achieved robust discrimination for mortality prediction, substantially outperforming a baseline model using demographics and calcium score alone, and exceeded the discriminative performance of prior body composition models. Performance was consistent across subgroups defined by sex, age, body mass index, cardiometabolic risk factors, imaging modality, and acquisition protocol, supporting generalizability across clinical settings. The BCI demonstrated excellent calibration and net clinical benefit. Explainability analysis identified visceral adipose tissue attenuation and skeletal muscle volume as the dominant contributors to mortality risk, offering tissue-specific therapeutic targets that complement generic weight-based metrics. Model-based simulations suggested that improvements in these specific compartments could reduce estimated mortality risk more effectively than equivalent changes in BMI alone, pointing toward precision therapeutic targets beyond weight reduction. Our study improved over previous literatures on body composition-based predictive models in one or more of the following ways: (1) we considered six types of body composition tissues while existing studies considered only three or less tissues, thus significantly higher granularity and improved ability to capture refined tissue interactions; (2) our model was rigorously validated in external sites, showing cross-site generalizability while most previous work lacked external validation; (3) our model achieved significant prediction performance improvement over previous body composition predictive models, offering better clinical outcomes prediction and facilitating the suitability for widespread clinical adoption; (4) our study was conducted with a large multi-center cohort across multiple countries, achieving statistical power and demonstrating reliability towards patients characteristics and imaging acquisition protocols while previous studies involved small single-center cohorts; (5) our model required only CT scans and basic demographics which were widely available in clinical routine while the existing models required dedicated laboratory tests or specialized imaging modalities, enhancing the applicability in routine clinical practice. Implications of all the available evidence BCI offers an explainable and clinically deployable tool for improved prediction of mortality risk from existing chest CT scans. Its use could inform updates to existing risk models, guide precision preventive strategies, and support development of therapeutics targeting specific body composition phenotypes.

BACKGROUND: Aortic enlargement is a powerful predictor of dissection and rupture, yet it is rarely evaluated during routine myocardial perfusion imaging, despite the widespread availability of computed tomography (CT) attenuation correction scans. The aim of this study was to determine whether fully automated, opportunistically derived, artificial intelligence-based aortic measurements from myocardial perfusion imaging CT attenuation correction scans are associated with adverse outcomes in a large multicenter cohort. METHODS: CT attenuation correction scans from patients undergoing positron emission tomography/CT and single-photon emission CT/CT myocardial perfusion imaging across 10 centers were included. A deep learning model automatically segmented the thoracic aorta, and a postprocessing algorithm extracted maximum ascending and descending diameters. The aortic size index was calculated by indexing the diameter to body surface area. RESULTS: A total of 29 339 patients (56% men; median age, 66 years [interquartile range, 58–75 years]) were included. Over a median follow-up of 3.5 years (interquartile range, 1.9–5.0 years), 5083 (17.3%) patients died. Median ascending and descending aortic size index values were 1.8 cm/m 2 (interquartile range, 1.6–2.0) and 1.5 cm/m 2 (interquartile range, 1.4–1.6), respectively, with an increase with age and higher values in females. Elevated aortic size index thresholds (ascending >2.2 cm/m 2 ; descending >1.6 cm/m 2 ) were significantly associated with increased all-cause mortality (ascending: adjusted hazard ratio, 1.16 [95% CI, 1.07–1.26], P <0.001; descending: adjusted hazard ratio, 1.23 [95% CI, 1.14–1.31]; P <0.001). Notably, the prognostic value of an abnormal aortic size index persisted independent of age, sex, and perfusion abnormalities. CONCLUSIONS: Artificial intelligence can unlock previously unused information within routine myocardial perfusion imaging CT attenuation correction scans by rapidly and automatically quantifying aortic size at scale. Opportunistic aortic measurements derived from CT attenuation correction may serve as an adjunctive risk biomarker and could add prognostic value to standard myocardial perfusion imaging without additional imaging or radiation.

BACKGROUND: Although the prognostic utility of positron emission tomography (PET) myocardial flow reserve (MFR) is well established, emerging data suggest that reduced subendocardial flows also predict adverse outcomes. However, the incremental value of subendocardial MFR (MFR SE ) beyond transmural MFR (MFR TM ) remains unclear. METHODS: We studied patients in a multicenter PET registry with normal perfusion on stress/rest Rb-82 PET, excluding those with a previous history of coronary artery bypass surgery, heart transplantation, or left ventricular ejection fraction <40%. The optimal MFR SE cutoff for predicting major adverse cardiovascular events (MACEs; death, myocardial infarction [MI], revascularization, or heart failure [HF] hospitalization) was determined using Youden’s index. Patients were stratified into 3 groups: concordant-normal (MFR TM ≥2.0; MFR SE ≥2.1), discordant (low-MFR SE , normal MFR TM ), and abnormal MFR TM . Clinical outcomes were compared by MFR groups. RESULTS: Among 6603 patients (normal N=4103; discordant N=885; abnormal N=1615) the mean age was 66.3±12.4 years, and 54% were women. Compared with the concordant-normal group, patients with discordant low-MFR SE were older and more likely to have hypertension, diabetes, peripheral artery disease, and previous percutaneous coronary intervention. The median MFR TM for normal, discordant, and abnormal groups were 2.86, 2.15, and 1.72, respectively. Over a median follow-up of 4.9 years, 1661 MACE events occurred. Discordant low-MFR SE patients had a higher risk of MACE (hazard ratio [HR], 1.41; 95% CI, 1.22–1.64) and all-cause mortality (HR, 1.36; 95% CI, 1.14–1.61) compared with concordant-normal patients. The discordant group had an intermediate absolute risk of MACE, with an adjusted annualized event rate of 5.79% (95% CI, 5.10–6.49) compared with 3.99% (95% CI, 3.67–4.30; P <0.001) in the concordant-normal group and 8.35% (95% CI, 7.71–9.00; P <0.001) in the abnormal MFR TM group. CONCLUSIONS: Subendocardial MFR reveals clinically meaningful risk heterogeneity among patients with preserved transmural flow reserve, helping refine risk stratification beyond traditional PET metrics.

ABSTRACT Background Anemia is an established marker of cardiovascular disease severity and risk which leads to elevations in resting myocardial blood flow (MBF) and impaired myocardial flow reserve (MFR) in patients without obstructive coronary artery disease (CAD). Anemia can potentially be detected opportunistically from blood pool density changes on computed tomography (CT) imaging. Objectives We evaluated relationships between chamber density measurements with hemoglobin, positron emission tomography (PET) findings, and cardiovascular events. Methods We included 33460 patients from 13 sites in the REFINE-PET who underwent PET and 24368 patients undergoing lung cancer screening chest CT. A deep learning model segmented cardiac chambers from CT images, then quantified chamber density. We evaluated the relationship between chamber density measures with resting MBF and MFR, as well as associations with death or myocardial infarction (MI). Results We included a total of 57,828 patients. A higher density in myocardium compared to left ventricle blood pool was associated with reduced MFR (adjusted odds ratio 3.02 per SD increase, 95% confidence interval[CI] 2.72 – 3.38) and an increased risk of death or MI in (adjusted hazard ratio[HR] 1.38 per SD increase, 95% CI 1.26-1.51). Having myocardial density higher than blood pool density was also associated with cardiovascular death in patients undergoing low-dose chest CT (adjusted HR 1.73, 95% CI 1.20-2.52). Conclusions In a large multimodality dataset, lower cardiac chamber density is associated with impaired MFR and independently associated with cardiovascular events. These biomarkers can be automatically extracted from CT to provide physiologic insights and potentially guide patient care. CONDENSED ABSTRACT Anemia is an important marker of cardiovascular disease severity and predictor of cardiovascular events. We utilized deep learning to measure cardiac chamber density on computed tomography imaging as a surrogate for anemia in 57,828 patients from two large multicenter studies. A higher density in myocardium compared to left ventricle blood pool was associated with reduced MFR and an increased risk of death or MI in patients undergoing positron emission tomography, and an increased risk of cardiovascular death in patients undergoing low-dose computed tomography. These biomarkers can provide additionally physiologic insights which could be used to guide patient care.

Abstract Background Previous studies evaluated large language model (LLM) performance on the American Society of Nuclear Cardiology (ASNC) Board Preparation Exam. Without domain-specific context, the best model (GPT-4o) achieved 63.1%, below the estimated 65% passing threshold and the 78% mean score of human fellows-in-training (FITs). Providing textbook context improved GPT-4o to 73.8% on text-only questions, but still fell short of human trainees. Whether next-generation LLMs with retrieval-augmented generation (RAG) can exceed this gap is unknown. Methods Claude Opus 4.7 and GPT-5.5 were administered all 168 questions (141 text-only, 27 image-based) from the 2023 ASNC Board Preparation Exam across 5 iterations each, using RAG with a nuclear cardiology textbook, companion atlas, and ASNC clinical guidelines. Claude used local FAISS-based semantic retrieval; GPT-5.5 used Azure’s cloud-hosted vector store. Performance was compared to prior LLM results and 13 human FITs. Results Across 5 iterations, Claude Opus 4.7 achieved a mean accuracy of 86.3% ± 1.4% (text 88.8%, image 73.3%). GPT-5.5 achieved 86.7% ± 2.2% (text 88.5%, image 77.0%) but refused a mean of 12.2 questions (7.3%) per iteration due to safety filters. Both models surpassed the human FIT mean (78.0%) and the estimated passing threshold. Compared to GPT-4o without context (63.1%), this represents a 23-percentage-point improvement in 18 months. Conclusion Next-generation LLMs with RAG now surpass average human trainee performance on nuclear cardiology board preparation questions, suggesting significant potential as educational tools and knowledge-reference aids in cardiovascular imaging. Condensed Abstract Across 5 iterations each, Claude Opus 4.7 and GPT-5.5 with retrieval-augmented generation achieved mean accuracies of 86.3% and 86.7% on the 2023 ASNC Board Preparation Exam (168 questions), both surpassing the mean human fellow-in-training score of 78%. GPT-5.5 refused a mean of 12.2 questions (7.3%) per iteration due to safety filters. These results represent a 23-percentage-point improvement over the best prior LLM without context (63.1%), demonstrating that RAG-enhanced LLMs have reached human-level proficiency in nuclear cardiology knowledge. Graphical Abstract Overview of the three-study research arc evaluating LLM performance on the 2023 ASNC Board Preparation Exam. Study 1 (2024) tested four LLMs without context (best: GPT-4o, 63.1%). Study 2 (2025) added textbook context to GPT-4o (73.8%). Study 3 (2026, current) evaluated Claude Opus 4.7 and GPT-5.5 with retrieval-augmented generation across 5 iterations each (mean 86.3% and 86.7%, respectively), both surpassing the human fellow-in-training mean of 78%. Right panel shows the performance scale with key thresholds.

ABSTRACT Aims Exercise capacity is a powerful predictor of cardiovascular risk. In patients unable to exercise, body composition analysis can potentially be used to estimate cardiorespiratory fitness. We developed a body composition “fitness” score, then validated its utility in two external populations. Methods and Results We included patients from four sites undergoing single photon emission computed tomography (SPECT) and twelve sites undergoing positron emission tomography (PET). We quantified body composition using deep learning. We evaluated associations between body composition and good exercise capacity (defined as completing ≥7 minutes on a Bruce protocol) then developed a body composition “fitness” score. We then assessed the associations of “fitness” score with exercise capacity and all-cause mortality in external populations. In total, 36471 patients were included with median age 67 (interquartile range 58 – 74). Median skeletal muscle density was higher among patients with good exercise capacity. In the external SPECT population, the body composition “fitness” score had higher prediction performance for good exercise capacity (AUC 0.771, 95% CI 0.752 – 0.789) than age (AUC 0.717, p<0.01). In the external PET population, high body composition “fitness” score was associated with lower cardiovascular death (adjusted hazard ratio 0.70, 95% CI 0.62 – 0.79, p<0.001). Conclusions We demonstrated that a comprehensive body composition “fitness” score could identify patients with good cardiorespiratory fitness. This approach transforms routinely acquired CT data into a surrogate marker of fitness which can be applied in patients undergoing PET, or other CT imaging, where exercise testing is not performed. Graphical Abstract Overview of study design. The overall population (n=36471) was split as outlined above. Body composition was analyzed from available computed tomography imaging. The distribution of body composition measures were analyzed in the combined single photon emission computed tomography (SPECT) populations. A body composition “fitness” score was derived to predict good exercise capacity in the internal population, with associations assessed in the two external testing populations.

Abstract Purpose Spatial distribution of coronary artery calcium (CAC) may provide additional prognostic value in patients undergoing SPECT and PET myocardial perfusion imaging (MPI). We aimed to automatically identify CAC in proximal segments from attenuation correction CT (CTAC) scans using artificial intelligence (AI) and to evaluate prognostic significance in two large international multicenter registries. Methods From hybrid MPI/CT imaging (N=43,099) across 15 sites, we included 4,552 most relevant patients with 1) no prior coronary artery disease; 2) AI-derived mild CAC scores (1-99); and 3) normal perfusion (stress total perfusion deficit <5%). The independent associations between AI-identified proximal CAC and major adverse cardiovascular events (MACE) and all-cause mortality (ACM) were evaluated using multivariable Cox regression, likelihood ratio test (LRT), and continuous net reclassification index (NRI). Results Among the patients with mild CAC and normal perfusion (mean age 65±12 years, 51% male), 1,730 (38%) had proximal CAC. Over 3.6 (inter-quartile interval 2.1, 5.2) years follow-up, 599 (13%) and 444 (10%) patients had MACE or ACM, respectively. Proximal CAC was associated with an increased risk of MACE (adjusted hazard ratio [HR] 1.24, 95% CI 1.03–1.48, P=0.02) and ACM (adjusted HR 1.25, 95% CI 1.01–1.53, P=0.04) after the adjustment of CAC score and density, clinical risk factors, and perfusion deficit. Proximal CAC improved the risk stratification of MACE (LRT P=0.02; NRI 12%) and ACM (LRT P=0.04; NRI 12%). Conclusion In patients with mild CAC and normal perfusion, AI detection of proximal CAC identified a higher-risk group for adverse outcomes, highlighting its prognostic utility. Graphical Abstract From patients who underwent hybrid myocardial perfusion imaging (MPI) from 15 sites, we analyzed those without prior coronary artery disease (CAD), mild coronary artery calcium (CAC) scores (1-99), and normal perfusion (stress total perfusion deficit <5%). A previously developed AI model was used to identify CAC lesions in proximal coronary segments on CT attenuation correction maps (CTAC). We evaluated associations with major adverse cardiovascular events (MACE) and all-cause mortality (ACM), showing risk stratification of proximal CAC and improvement by net reclassification index (NRI). CAC lesion color: green, left anterior descending artery (LAD) with left main artery; red, left circumflex artery (LCX); yellow, right coronary artery (RCA). Adjusted hazard ratios (HRs) are shown with 95% confidence intervals.

Abstract Background Quantitative myocardial blood flow (MBF) and myocardial flow reserve (MFR) provide incremental diagnostic and prognostic value in cardiac PET, but their widespread use is limited by the technical demands of dynamic imaging protocols. We evaluated the feasibility of using artificial intelligence (AI) to predict MBF and MFR from static and gated PET images, without the need for dynamic acquisition. Methods A machine learning (XGBoost) model was trained on 82Rb PET multi-center dataset using static perfusion imaging, injected dose, hemodynamic measures, clinical data and CT-derived features (including body composition) from the hybrid CT attenuation scan. Model performance was evaluated externally in an independent cohort. Results In total, 10,566 (derivation-cohort) and 7,842 (external-cohort) patients were included in this multi-center study. On the external-cohort, AI approach achieved an Area under the curve (AUC) of 0.92 (0.92–0.93) for abnormal stress MBF and 0.91 (0.90–0.92) for abnormal MFR; Intra-class correlation (ICC) 0.80 (0.78–0.82) and 0.78 (0.76–0.79), respectively. AI MFR closely mirrored the prognostic performance of measured MFR, showing nearly identical Kaplan–Meier risk stratification (both p<0.0001) and maintaining strong, and independently significant associations with all-cause mortality (HR 3.4 [2.8–4.2] vs. 4.6 [3.6–5.8]; both p<0.001), and demonstrated similar added value to perfusion for mortality prediction. Conclusion AI-predicted virtual stress MBF and MFR assessment using static and gated PET data is feasible and generalizable across cohorts. By removing the dependency on dynamic acquisitions, this approach has the potential to broaden the clinical adoption of flow quantification. STRUCTURED GRAPHICAL ABSTRACT PET: Positron Emission Tomography, CT: Computed Tomography, MFR: Myocardial Flow Reserve Key Question: Can machine learning models trained on dynamic PET datasets accurately predict regional stress myocardial blood flow (MBF) and myocardial flow reserve (MFR) from static image features, physiological parameters, and CT-based anatomical measures? Key Finding: Artificial intelligence can accurately estimate MBF and MFR from non-dynamic PET data, with strong agreement to reference standards. Take-home Message: By eliminating reliance on dynamic PET acquisitions, machine-learning has the potential to broaden clinical adoption of quantitative flow assessment.

BACKGROUND: Myocardial flow reserve (MFR), measured by positron emission tomography (PET) myocardial perfusion imaging, provides valuable information on epicardial coronary disease, diffuse atherosclerosis, and microvascular function. Despite its routine use, the prognostic efficacy of 13 N-ammonia PET MFR remains unconfirmed in larger multicenter cohorts of patients with suspected or known coronary artery disease. METHODS: We considered patients from 5 sites in the REFINE PET (Registry of Flow and Perfusion Imaging for Artificial Intelligence with PET) registry who underwent 13 N-ammonia PET myocardial perfusion imaging for coronary artery disease. Clinical and imaging data were collected at the time of myocardial perfusion imaging. MFR was quantified as the ratio of stress to rest myocardial blood flow, using QPET software (Cedars-Sinai Medical Center, Los Angeles, CA). The primary outcome was all-cause mortality. Survival analyses were performed using Kaplan-Meier and Cox regression models adjusted for clinical and imaging covariates. RESULTS: In total, 6277 patients were included (median age of 65 years, 56% male). Median follow-up time was 3.8 years. There were 1895 patients with MFR ≤2 and 4382 with MFR >2. Patients with MFR ≤2 had significantly higher mortality than those with MFR >2 (n=701 [37.0%] versus n=537 [12.3%], respectively; P <0.001). Annualized all-cause mortality rates by MFR and summed stress score ranged from 1.7 to 15.8. In multivariable analysis, MFR ≤2 was independently associated with increased all-cause mortality in the overall population (hazard ratio, 2.70 [95% CI, 2.41–3.03]; P <0.001), even among patients with no perfusion defects (hazard ratio, 2.36 [95% CI, 1.93–2.89]; P <0.001). Mortality risk decreased across increasing MFR deciles, ranging from hazard ratio, 2.73 (95% CI, 2.39–3.11) to hazard ratio, 0.35 (95% CI, 0.25–0.49). CONCLUSIONS: In this large multicenter cohort, MFR derived from 13 N-ammonia PET myocardial perfusion imaging is a strong, independent predictor of all-cause mortality, even in patients with normal perfusion. An MFR of ≤2 identifies elevated risk, while higher values are associated with improved survival. These findings support the routine integration of MFR to enhance risk stratification in patients with suspected or known coronary artery disease.

BACKGROUND: Computed tomography (CT) attenuation correction scans are an intrinsic part of positron emission tomography (PET) myocardial perfusion imaging using PET/CT, but anatomic information is rarely derived from these ultralow-dose CT scans. We aimed to assess the association between deep learning-derived cardiac chamber volumes (right atrial, right ventricular, left ventricular, and left atrial) and mass (left ventricular) from these scans with myocardial flow reserve and heart failure hospitalization. METHODS: We included 18 079 patients with cardiac PET/CT from 6 sites. A deep learning model estimated cardiac chamber volumes and left ventricular mass from CT attenuation correction imaging. Associations between deep learning-derived CT mass and volumes with heart failure hospitalization and reduced myocardial flow reserve were assessed in a multivariable analysis. RESULTS: During a median follow-up of 4.3 years, 1721 (9.5%) patients experienced heart failure hospitalization. Patients with 3 or 4 abnormal chamber volumes were 7× more likely to be hospitalized for heart failure compared with patients with normal volumes. In adjusted analyses, left atrial volume (hazard ratio [HR], 1.25 [95% CI, 1.19–1.30]), right atrial volume (HR, 1.29 [95% CI, 1.23–1.35]), right ventricular volume (HR, 1.25 [95% CI, 1.20–1.31]), left ventricular volume (HR, 1.27 [95% CI, 1.23–1.35]), and left ventricular mass (HR, 1.25 [95% CI, 1.18–1.32]) were independently associated with heart failure hospitalization. In multivariable analyses, left atrial volume (odds ratio, 1.14 [95% CI, 1.0–1.19]) and ventricular mass (odds ratio, 1.12 [95% CI, 1.6–1.17]) were independent predictors of reduced myocardial flow reserve. CONCLUSIONS: Deep learning–derived chamber volumes and left ventricular mass from CT attenuation correction were predictive of heart failure hospitalization and reduced myocardial flow reserve in patients undergoing cardiac PET perfusion imaging. This anatomic data can be routinely reported along with other PET/CT parameters to improve risk prediction.