Strategies for Implementing Machine Learning Algorithms in the Clinical Practice of Radiology.

Despite recent advancements in machine learning (ML) applications in health care, there have been few benefits and improvements to clinical medicine in the hospital setting. To facilitate clinical adaptation of methods in ML, this review proposes a standardized framework for the step-by-step implementation of artificial intelligence into the clinical practice of radiology that focuses on three key components: problem identification, stakeholder alignment, and pipeline integration. A review of the recent literature and empirical evidence in radiologic imaging applications justifies this approach and offers a discussion on structuring implementation efforts to help other hospital practices leverage ML to improve patient care. Clinical trial registration no. 04242667 © RSNA, 2024 Supplemental material is available for this article.

Progression of Coronary Artery Calcification and Risk of Clinical Events in CKD: The Chronic Renal Insufficiency Cohort Study.

RATIONALE & OBJECTIVE: Coronary artery calcification (CAC) progresses rapidly in people with chronic kidney disease (CKD) compared with the general population. We studied the association between CAC progression and higher risks of atherosclerotic cardiovascular disease (CVD), congestive heart failure, and all-cause mortality among adults with CKD. STUDY DESIGN: Prospective cohort study. SETTING: & Participants: 1,310 participants in the Chronic Renal Insufficiency Cohort (CRIC) Study who had at least one CAC scan with no prior history of CVD and with observed or imputed data on changes in CAC over time. EXPOSURE: Observed or imputed CAC progression, categorized as incident CAC among participants with zero CAC on the baseline scan, or progressive CAC when the baseline scan demonstrated CAC and there was an increase in CAC ≥50 Agatston units per year. OUTCOMES: Atherosclerotic CVD (myocardial infarction or stroke), congestive heart failure, and all-cause mortality. ANALYTICAL APPROACH: Cause-specific Cox proportional hazards regression, stratified by presence of CAC at baseline. RESULTS: A total of 545 participants without and 765 with prevalent CAC at baseline were included. During a mean 3.3 years between CAC assessments, 177 (32.5%) participants without baseline CAC developed incident CAC while 270 participants (35.3%) with baseline CAC developed a ≥50 Agatston units per year increase in CAC. After multivariable adjustment, incident CAC was associated with 2.42-fold higher rate of atherosclerotic CVD (95% confidence interval [CI]: 1.23-4.79) and 1.82-fold higher rate of all-cause mortality (95% CI: 1.03-3.22). Progressive CAC (≥50 units per year) was not associated with atherosclerotic CVD (hazard ratio [HR]: 1.42; 95% CI: 0.85-2.35) but was associated with a 1.73-fold higher rate of all-cause mortality (95% CI: 1.31-2.28). Progressive CAC was not associated with incident heart failure. LIMITATIONS: Residual confounding and limited statistical power for some outcomes. CONCLUSIONS: Among adults with CKD stages 2-4, CAC progression over a mean 3.3 years was associated with higher risk of atherosclerotic CVD and all-cause mortality. The associations were strongest among participants without CAC at baseline.

Evinacumab Reduces Triglyceride-Rich Lipoproteins in Patients with Hyperlipidemia: A Post-Hoc Analysis of Three Randomized Clinical Trials.

PURPOSE: Natural selection (Mendelian randomization) studies support a causal relationship between elevated triglyceride-rich lipoproteins (TRLs) and atherosclerotic cardiovascular disease (ASCVD). This post-hoc analysis assessed the efficacy of evinacumab in reducing TRLs in patient cohorts from three separate clinical trials with evinacumab. METHODS: Patients with homozygous familial hypercholesterolemia (HoFH) and low-density lipoprotein cholesterol (LDL-C) ≥ 70 mg/dL were enrolled in a phase III trial (R1500-CL-1629; NCT03399786). Patients diagnosed with refractory hypercholesterolemia, with LDL-C ≥ 70 mg/dL or ≥ 100 mg/dL for those with or without ASCVD, respectively, were enrolled in a phase II trial (R1500-CL-1643; NCT03175367). Patients with severe hypertriglyceridemia (fasting TGs ≥ 500 mg/dL) were enrolled in a phase II trial (R1500-HTG-1522; NCT03452228). Patients received evinacumab intravenously (5 or 15 mg/kg) every 4 weeks, or subcutaneously (300 or 450 mg) every week or every 2 weeks. Efficacy outcomes included change in TRLs (calculated as total cholesterol minus high-density lipoprotein cholesterol minus LDL-C) and other lipid parameters from baseline to 12, 16, or 24 weeks for trial 1522, 1643, and 1629, respectively. RESULTS: At baseline, TRL levels were higher for patients with severe hypertriglyceridemia entering the 1522 trial vs. other cohorts. Reductions in TRLs were observed across all studies with evinacumab, with > 50% reduction from baseline observed at the highest doses evaluated in patients with HoFH or refractory hypercholesterolemia. Within all three trials, evinacumab was generally well tolerated. CONCLUSIONS: Despite limitations in direct comparisons between study groups, these data indicate that TRL levels could be a future target for lipid-lowering therapies.

High-density lipoprotein metrics during midlife and future subclinical atherosclerosis in women: the SWAN HDL study.

OBJECTIVE: The clinical utility of high-density lipoprotein cholesterol (HDL-C) in risk classification is limited, especially in midlife women. Novel metrics of HDL may better reflect this risk. We clustered a comprehensive profile of HDL metrics into favorable and unfavorable clusters and assessed how these two clusters are related to future subclinical atherosclerosis (carotid intima media thickness [cIMT], interadventitial diameter [IAD], and carotid plaque presence) in midlife women. METHODS: Four hundred sixty-one women (baseline age: 50.4 [2.7] years; 272 White, 137 Black, 52 Chinese) from the Study of Women's Health Across the Nation HDL ancillary study who had baseline measures of HDL cholesterol efflux capacity (HDL-CEC), lipid contents (HDL-phospholipids [HDL-PL] and HDL triglycerides [HDL-Tg]), and HDL particle (HDL-P) distribution and size, followed by carotid ultrasound (average 12.9 [SD: 2.6] years later), were included. Using latent cluster analysis, women were clustered into a favorable (high HDL-CEC, HDL-PL, large and medium HDL-P, less HDL-Tg and small HDL-P, larger size) or an unfavorable HDL cluster (low HDL-CEC, HDL-PL, large and medium HDL-P, more HDL-Tg, and small HDL-P, smaller size) and then linked to future subclinical atherosclerosis using linear or logistic regression. RESULTS: The favorable HDL cluster was associated with lower cIMT, IAD, and odds of carotid plaque presence. These associations were attenuated by body mass index, except in Chinese women where the association with cIMT persisted (0.72 [0.63, 0.83]). CONCLUSIONS: The association between favorable HDL clusters and a better postmenopausal subclinical atherosclerosis profile is largely explained by body mass index; however, racial/ethnic differences may exist.

Family cascade screening for equitable identification of familial hypercholesterolemia: study protocol for a hybrid effectiveness-implementation type III randomized controlled trial.

BACKGROUND: Familial hypercholesterolemia (FH) is a heritable disorder affecting 1.3 million individuals in the USA. Eighty percent of people with FH are undiagnosed, particularly minoritized populations including Black or African American people, Asian or Asian American people, and women across racial groups. Family cascade screening is an evidence-based practice that can increase diagnosis and improve health outcomes but is rarely implemented in routine practice, representing an important care gap. In pilot work, we leveraged best practices from behavioral economics and implementation science-including mixed-methods contextual inquiry with clinicians, patients, and health system constituents-to co-design two patient-facing implementation strategies to address this care gap: (a) an automated health system-mediated strategy and (b) a nonprofit foundation-mediated strategy with contact from a foundation-employed care navigator. This trial will test the comparative effectiveness of these strategies on completion of cascade screening for relatives of individuals with FH, centering equitable reach. METHODS: We will conduct a hybrid effectiveness-implementation type III randomized controlled trial testing the comparative effectiveness of two strategies for implementing cascade screening with 220 individuals with FH (i.e., probands) per arm identified from a large northeastern health system. The primary implementation outcome is reach, or the proportion of probands with at least one first-degree biological relative (parent, sibling, child) in the USA who is screened for FH through the study. Our secondary implementation outcomes include the number of relatives screened and the number of relatives meeting the American Heart Association criteria for FH. Our secondary clinical effectiveness outcome is post-trial proband cholesterol level. We will also use mixed methods to identify implementation strategy mechanisms for implementation strategy effectiveness while centering equity. DISCUSSION: We will test two patient-facing implementation strategies harnessing insights from behavioral economics that were developed collaboratively with constituents. This trial will improve our understanding of how to implement evidence-based cascade screening for FH, which implementation strategies work, for whom, and why. Learnings from this trial can be used to equitably scale cascade screening programs for FH nationally and inform cascade screening implementation efforts for other genetic disorders. TRIAL REGISTRATION: ClinicalTrials.gov, NCT05750667. Registered 15 February 2023-retrospectively registered, https://clinicaltrials.gov/study/NCT05750667 .

Protein-truncating variant in APOL3 increases chronic kidney disease risk in epistasis with APOL1 risk alleles.

BACKGROUND: Two coding alleles within the APOL1 gene, G1 and G2, found almost exclusively in individuals genetically similar to West African populations, contribute substantially to the pathogenesis of chronic kidney disease (CKD). The APOL gene cluster on chromosome 22 contains a total of six APOL genes that have arisen as a result of gene duplication. METHODS: Using a genome-first approach in the Penn Medicine Biobank, we identified 62 protein-altering variants in the six APOL genes with a minor allele frequency > 0.1% in a population of participants genetically similar to African reference populations and performed population-specific phenome-wide association studies. RESULTS: We identified rs1108978, a stop-gain variant in APOL3 (p.Q58*), to be significantly associated with increased CKD risk, even after conditioning on APOL1 G1/G2 carrier status. These findings were replicated in the Veterans Affairs Million Veteran Program and the All of Us Research Program. APOL3 p.Q58* was also significantly associated with a number of quantitative traits linked to CKD including decreased kidney volume. This truncating variant contributed the most risk for CKD in patients monoallelic for APOL1 G1/G2, suggesting an epistatic interaction and a potential protective effect of wild-type APOL3 against APOL1-induced kidney disease. CONCLUSION: This study demonstrates the utility of targeting population-specific variants in a genome-first approach, even in the context of well-studied gene-disease relationships. FUNDING: National Heart, Lung, and Blood Institute (F30HL172382, R01HL169378, R01HL169458), Doris Duke Foundation (grant 2023-0224), National Institute of Biomedical Imaging and Bioengineering (P41EB029460), National Center for Advancing Translational Sciences (UL1-TR-001878).

Polygenic risk scores for cardiometabolic traits demonstrate importance of ancestry for predictive precision medicine.

Polygenic risk scores (PRS) have predominantly been derived from genome-wide association studies (GWAS) conducted in European ancestry (EUR) individuals. In this study, we present an in-depth evaluation of PRS based on multi-ancestry GWAS for five cardiometabolic phenotypes in the Penn Medicine BioBank (PMBB) followed by a phenome-wide association study (PheWAS). We examine the PRS performance across all individuals and separately in African ancestry (AFR) and EUR ancestry groups. For AFR individuals, PRS derived using the multi-ancestry LD panel showed a higher effect size for four out of five PRSs (DBP, SBP, T2D, and BMI) than those derived from the AFR LD panel. In contrast, for EUR individuals, the multi-ancestry LD panel PRS demonstrated a higher effect size for two out of five PRSs (SBP and T2D) compared to the EUR LD panel. These findings underscore the potential benefits of utilizing a multi-ancestry LD panel for PRS derivation in diverse genetic backgrounds and demonstrate overall robustness in all individuals. Our results also revealed significant associations between PRS and various phenotypic categories. For instance, CAD PRS was linked with 18 phenotypes in AFR and 82 in EUR, while T2D PRS correlated with 84 phenotypes in AFR and 78 in EUR. Notably, associations like hyperlipidemia, renal failure, atrial fibrillation, coronary atherosclerosis, obesity, and hypertension were observed across different PRSs in both AFR and EUR groups, with varying effect sizes and significance levels. However, in AFR individuals, the strength and number of PRS associations with other phenotypes were generally reduced compared to EUR individuals. Our study underscores the need for future research to prioritize 1) conducting GWAS in diverse ancestry groups and 2) creating a cosmopolitan PRS methodology that is universally applicable across all genetic backgrounds. Such advances will foster a more equitable and personalized approach to precision medicine.

mTORC1 controls murine postprandial hepatic glycogen synthesis via Ppp1r3b.

In response to a meal, insulin drives hepatic glycogen synthesis to help regulate systemic glucose homeostasis. The mechanistic target of rapamycin complex 1 (mTORC1) is a well-established insulin target and contributes to the postprandial control of liver lipid metabolism, autophagy, and protein synthesis. However, its role in hepatic glucose metabolism is less understood. Here, we used metabolomics, isotope tracing, and mouse genetics to define a role for liver mTORC1 signaling in the control of postprandial glycolytic intermediates and glycogen deposition. We show that mTORC1 is required for glycogen synthase activity and glycogenesis. Mechanistically, hepatic mTORC1 activity promotes the feeding-dependent induction of Ppp1r3b, a gene encoding a phosphatase important for glycogen synthase activity whose polymorphisms are linked to human diabetes. Reexpression of Ppp1r3b in livers lacking mTORC1 signaling enhances glycogen synthase activity and restores postprandial glycogen content. mTORC1-dependent transcriptional control of Ppp1r3b is facilitated by FOXO1, a well characterized transcriptional regulator involved in the hepatic response to nutrient intake. Collectively, we identify a role for mTORC1 signaling in the transcriptional regulation of Ppp1r3b and the subsequent induction of postprandial hepatic glycogen synthesis.

A genome-first approach to variants in MLXIPL and their association with hepatic steatosis and plasma lipids.

BACKGROUND: Common variants of the max-like protein X (MLX)-interacting protein-like (MLXIPL) gene, encoding the transcription factor carbohydrate-responsive element-binding protein, have been shown to be associated with plasma triglyceride levels. However, the role of these variants in steatotic liver disease (SLD) is unclear. METHODS: We used a genome-first approach to analyze a variety of metabolic phenotypes and clinical outcomes associated with a common missense variant in MLXIPL, Gln241His, in 2 large biobanks: the UK Biobank and the Penn Medicine Biobank. RESULTS: Carriers of MLXIPL Gln241His were associated with significantly lower serum levels of triglycerides, apolipoprotein-B, gamma-glutamyl transferase, and alkaline phosphatase. Additionally, MLXIPL Gln241His carriers were associated with significantly higher serum levels of HDL cholesterol and alanine aminotransferase. Carriers homozygous for MLXIPL Gln241His showed a higher risk of SLD in 2 unrelated cohorts. Carriers of MLXIPL Gln241His were especially more likely to be diagnosed with SLD if they were female, obese, and/or also carried the PNPLA3 I148M variant. Furthermore, the heterozygous carriage of MLXIPL Gln241His was associated with significantly higher all-cause, liver-related, and cardiovascular mortality rates. Nuclear magnetic resonance metabolomics data indicated that carriage of MLXIPL Gln241His was significantly associated with lower serum levels of VLDL and increased serum levels of HDL cholesterol. CONCLUSIONS: Analyses of the MLXIPL Gln241His polymorphism showed a significant association with a higher risk of SLD diagnosis and elevated serum alanine aminotransferase as well as significantly lower serum triglycerides and apolipoprotein-B levels. MLXIPL might, therefore, be a potential pharmacological target for the treatment of SLD and hyperlipidemia, notably for patients at risk. More mechanistic studies are needed to better understand the role of MLXIPL Gln241His on lipid metabolism and steatosis development.

Sleep and Activity Patterns in Autism Spectrum Disorder.

Background: Autism spectrum disorder (ASD) is a highly heritable and heterogeneous neurodevelopmental disorder characterized by impaired social interactions, repetitive behaviors, and a wide range of comorbidities. Between 44-83% of autistic individuals report sleep disturbances, which may share an underlying neurodevelopmental basis with ASD. Methods: We recruited 382 ASD individuals and 223 of their family members to obtain quantitative ASD-related traits and wearable device-based accelerometer data spanning three consecutive weeks. An unbiased approach identifying traits associated with ASD was achieved by applying the elastic net machine learning algorithm with five-fold cross-validation on 6,878 days of data. The relationship between sleep and physical activity traits was examined through linear mixed-effects regressions using each night of data. Results: This analysis yielded 59 out of 242 actimetry measures associated with ASD status in the training set, which were validated in a test set (AUC: 0.777). For several of these traits (e.g. total light physical activity), the day-to-day variability, in addition to the mean, was associated with ASD. Individuals with ASD were found to have a stronger correlation between physical activity and sleep, where less physical activity decreased their sleep more significantly than that of their non-ASD relatives. Conclusions: The average duration of sleep/physical activity and the variation in the average duration of sleep/physical activity strongly predict ASD status. Physical activity measures were correlated with sleep quality, traits, and regularity, with ASD individuals having stronger correlations. Interventional studies are warranted to investigate whether improvements in both sleep and increased physical activity may improve the core symptoms of ASD.

Kagami Ogata syndrome: a small deletion refines critical region for imprinting.

Kagami-Ogata syndrome is a rare imprinting disorder and its phenotypic overlap with multiple different etiologies hampers diagnosis. Genetic etiologies include paternal uniparental isodisomy (upd(14)pat), maternal allele deletions of differentially methylated regions (DMR) in 14q32.2 or pure primary epimutations. We report a patient with Kagami-Ogata syndrome and an atypical diagnostic odyssey with several negative standard-of-care genetic tests followed by epigenetic testing using methylation microarray and a targeted analysis of whole-genome sequencing to reveal a 203 bp deletion involving the MEG3 transcript and MEG3:TSS-DMR. Long-read sequencing enabled the simultaneous detection of the deletion, phasing, and biallelic hypermethylation of the MEG3:TSS-DMR region in a single assay. This case highlights the challenges in the sequential genetic testing paradigm, the utility of long-read sequencing as a single comprehensive diagnostic assay, and the smallest reported deletion causing Kagami-Ogata syndrome allowing important insights into the mechanism of imprinting effects at this locus.

Targeted Quantitative Plasma Metabolomics Identifies Metabolite Signatures that Distinguish Heart Failure with Reduced and Preserved Ejection Fraction.

Background: Two general phenotypes of heart failure (HF) are recognized: HF with reduced ejection fraction (HFrEF) and with preserved EF (HFpEF). To develop HF disease phenotype-specific approaches to define and guide treatment, distinguishing biomarkers are needed. The goal of this study was to utilize quantitative metabolomics on a large, diverse population to replicate and extend existing knowledge of the plasma metabolic signatures in human HF. Methods: Quantitative, targeted LC/MS plasma metabolomics was conducted on 787 samples collected by the Penn Medicine BioBank from subjects with HFrEF (n=219), HFpEF (n=357), and matched non-failing Controls (n=211). A total of 90 metabolites were analyzed, comprising 28 amino acids, 8 organic acids, and 54 acylcarnitines. 733 of these samples were also processed via an OLINK protein panel for proteomic profiling. Results: Consistent with previous studies, unsaturated forms of medium/long chain acylcarnitines were elevated in the HFrEF group to a greater extent than the HFpEF group compared to Controls. A number of amino acid derivatives, including 1- and 3-methylhistidine, homocitrulline, and symmetric (SDMA) and asymmetric (ADMA) dimethylarginine were elevated in HF, with ADMA elevated uniquely in HFpEF. Plasma branched-chain amino acids (BCAA) were not different across the groups; however, short-chain acylcarnitine species indicative of BCAA catabolism were significantly elevated in both HF groups. The ketone body 3-hydroxybutyrate (3-HBA) and its metabolite C4-OH carnitine were uniquely elevated in the HFrEF group. Linear regression models demonstrated a significant correlation between plasma 3-HBA and NT-proBNP in both forms of HF, stronger in HFrEF. Conclusions: These results identify plasma signatures that are shared as well as potentially distinguish between HFrEF and HFpEF. Metabolite markers for ketogenic metabolic reprogramming in extra-cardiac tissues were identified as unique signatures in the HFrEF group, possibly related to the lipolytic action of increased levels of BNP. Future studies will be necessary to further validate these metabolites as HF biosignatures that may guide phenotype-specific therapeutics and provide insight into the systemic metabolic responses to HFpEF and HFrEF.

Population Performance and Individual Agreement of Coronary Artery Disease Polygenic Risk Scores.

Importance: Polygenic risk scores (PRSs) for coronary artery disease (CAD) are a growing clinical and commercial reality. Whether existing scores provide similar individual-level assessments of disease liability is a critical consideration for clinical implementation that remains uncharacterized. Objective: Characterize the reliability of CAD PRSs that perform equivalently at the population level at predicting individual-level risk. Design: Cross-sectional Study. Setting: All of Us Research Program (AOU), Penn Medicine Biobank (PMBB), and UCLA ATLAS Precision Health Biobank. Participants: Volunteers of diverse genetic backgrounds enrolled in AOU, PMBB, and UCLA with available electronic health record and genotyping data. Exposures: Polygenic risk for CAD from previously published PRSs and new PRSs developed separately from the testing cohorts. Main Outcomes and Measures: Sets of CAD PRSs that perform population prediction equivalently were identified by comparing calibration and discrimination (Brier score and AUROC) of generalized linear models of prevalent CAD using Bayesian analysis of variance. Among equivalently performing scores, individual-level agreement between risk estimates was tested with intraclass correlation (ICC) and Light's Kappa, measures of inter-rater reliability. Results: 50 PRSs were calculated for 171,095 AOU participants. When included in a model of prevalent CAD, 48 scores had practically equivalent Brier scores and AUROCs (region of practical equivalence = 0.02). Across these scores, 84% of participants had at least one score in both the top and bottom risk quintile. Continuous agreement of individual risk predictions from the 48 scores was poor, with an ICC of 0.351 (95% CI; 0.349, 0.352). Agreement between two statistically equivalent scores was moderate, with an ICC of 0.649 (95% CI; 0.646, 0.652). Light's Kappa, used to evaluate consistency of assignment to high-risk thresholds, did not exceed 0.56 (interpreted as 'fair') across statistically and practically equivalent scores. Repeating the analysis among 41,193 PMBB and 50,748 UCLA participants yielded different sets of statistically and practically equivalent scores which also lacked strong individual agreement. Conclusions and Relevance: Across three diverse biobanks, CAD PRSs that performed equivalently at the population level produced unreliable individual risk estimates. Approaches to clinical implementation of CAD PRSs must consider the potential for discordant individual risk estimates from otherwise indistinguishable scores.

A Cloud-Based System for Automated AI Image Analysis and Reporting.

Although numerous AI algorithms have been published, the relatively small number of algorithms used clinically is partly due to the difficulty of implementing AI seamlessly into the clinical workflow for radiologists and for their healthcare enterprise. The authors developed an AI orchestrator to facilitate the deployment and use of AI tools in a large multi-site university healthcare system and used it to conduct opportunistic screening for hepatic steatosis. During the 60-day study period, 991 abdominal CTs were processed at multiple different physical locations with an average turnaround time of 2.8 min. Quality control images and AI results were fully integrated into the existing clinical workflow. All input into and output from the server was in standardized data formats. The authors describe the methodology in detail; this framework can be adapted to integrate any clinical AI algorithm.

CT imaging-derived phenotypes for abdominal muscle and their association with age and sex in a medical biobank.

The study of muscle mass as an imaging-derived phenotype (IDP) may yield new insights into determining the normal and pathologic variations in muscle mass in the population. This can be done by determining 3D abdominal muscle mass from 12 distinct abdominal muscle regions and groups using computed tomography (CT) in a racially diverse medical biobank. To develop a fully automatic technique for assessment of CT abdominal muscle IDPs and preliminarily determine abdominal muscle IDP variations with age and sex in a clinically and racially diverse medical biobank. This retrospective study was conducted using the Penn Medicine BioBank (PMBB), a research protocol that recruits adult participants during outpatient visits at hospitals in the Penn Medicine network. We developed a deep residual U-Net (ResUNet) to segment 12 abdominal muscle groups including the left and right psoas, quadratus lumborum, erector spinae, gluteus medius, rectus abdominis, and lateral abdominals. 110 CT studies were randomly selected for training, validation, and testing. 44 of the 110 CT studies were selected to enrich the dataset with representative cases of intra-abdominal and abdominal wall pathology. The studies were divided into non-overlapping training, validation and testing sets. Model performance was evaluated using the Sørensen-Dice coefficient. Volumes of individual muscle groups were plotted to distribution curves. To investigate associations between muscle IDPs, age, and sex, deep learning model segmentations were performed on a larger abdominal CT dataset from PMBB consisting of 295 studies. Multivariable models were used to determine relationships between muscle mass, age and sex. The model's performance (Dice scores) on the test data was the following: psoas: 0.85 ± 0.12, quadratus lumborum: 0.72 ± 0.14, erector spinae: 0.92 ± 0.07, gluteus medius: 0.90 ± 0.08, rectus abdominis: 0.85 ± 0.08, lateral abdominals: 0.85 ± 0.09. The average Dice score across all muscle groups was 0.86 ± 0.11. Average total muscle mass for females was 2041 ± 560.7 g with a high of 2256 ± 560.1 g (41-50 year old cohort) and a change of - 0.96 g/year, declining to an average mass of 1579 ± 408.8 g (81-100 year old cohort). Average total muscle mass for males was 3086 ± 769.1 g with a high of 3385 ± 819.3 g (51-60 year old cohort) and a change of - 1.73 g/year, declining to an average mass of 2629 ± 536.7 g (81-100 year old cohort). Quadratus lumborum was most highly correlated with age for both sexes (correlation coefficient of - 0.5). Gluteus medius mass in females was positively correlated with age with a coefficient of 0.22. These preliminary findings show that our CNN can automate detailed abdominal muscle volume measurement. Unlike prior efforts, this technique provides 3D muscle segmentations of individual muscles. This technique will dramatically impact sarcopenia diagnosis and research, elucidating its clinical and public health implications. Our results suggest a peak age range for muscle mass and an expected rate of decline, both of which vary between genders. Future goals are to investigate genetic variants for sarcopenia and malnutrition, while describing genotype-phenotype associations of muscle mass in healthy humans using imaging-derived phenotypes. It is feasible to obtain 3D abdominal muscle IDPs with high accuracy from patients in a medical biobank using fully automated machine learning methods. Abdominal muscle IDPs showed significant variations in lean mass by age and sex. In the future, this tool can be leveraged to perform a genome-wide association study across the medical biobank and determine genetic variants associated with early or accelerated muscle wasting.

The common p.Ile291Val variant of ERLIN1 enhances TM6SF2 function and is associated with protection against MASLD.

BACKGROUND: The ERLIN1 p.Ile291Val single-nucleotide polymorphism (rs2862954) is associated with protection from steatotic liver disease (SLD), but effects of this variant on metabolic phenotypes remain uncertain. METHODS: Metabolic phenotypes and outcomes associated with ERLIN1 p.Ile291Val were analyzed by using a genome-first approach in the UK Biobank (UKB), Penn Medicine BioBank (PMBB), and All of Us cohort. FINDINGS: ERLIN1 p.Ile291Val carriers exhibited significantly lower serum levels of alanine aminotransferase and aspartate aminotransferase as well as higher levels of triglycerides, low-density lipoprotein cholesterol, Apolipoprotein B, high-density lipoprotein cholesterol, and Apolipoprotein A1 in UKB, and these values were affected by ERLIN1 p.Ile291Val in an allele-dose-dependent manner. Homozygous ERLIN1 p.Ile291Val carriers had a significantly reduced risk of developing metabolic dysfunction-associated SLD (MASLD, adjusted odds ratio [aOR] = 0.92, 95% confidence interval [CI], 0.88-0.96). The protective effect of this variant was enhanced in patients with alcoholic liver disease. Our results were replicated in PMBB and the All of Us cohort. Strikingly, the protective effects of ERLIN1 p.Ile291Val were not apparent in individuals carrying the TM6SF2 p.Glu167Lys variant associated with increased risk of SLD. We analyzed the effects of predicted loss-of-function ERLIN1 variants and found that they had opposite effects, namely reduced plasma lipids, suggesting that ERLIN1 p.Ile291Val may be a gain-of-function variant. CONCLUSION: Our study contributes to a better understanding of ERLIN1 by investigating a coding variant that has emerged as a potential gain-of-function mutation with protective effects against MASLD development.

A missense variant in human perilipin 2 (PLIN2 Ser251Pro) reduces hepatic steatosis in mice.

Background & Aims: Non-alcoholic fatty liver disease (NAFLD) is characterised by the accumulation of lipid droplets (LDs) within hepatocytes. Perilipin 2 (PLIN2) is the most abundant protein in hepatic LDs and its expression correlates with intracellular lipid accumulation. A recently discovered PLIN2 coding variant, Ser251Pro (rs35568725), was found to promote the accumulation of small LDs in embryonic kidney cells. In this study, we investigate the role of PLIN2-Ser251Pro (PLIN2-Pro251) on hepatic LD metabolism in vivo and research the metabolic phenotypes associated with this variant in humans. Methods: For our animal model, we used Plin2 knockout mice in which we expressed either human PLIN2-Pro251 (Pro251 mice) or wild-type human PLIN2-Ser251 (Ser251 mice) in a hepatocyte-specific manner. We fed both cohorts a lipogenic high-fat, high-cholesterol, high-fructose diet for 12 weeks. Results: Pro251 mice were associated with reduced liver triglycerides (TGs) and had lower mRNA expression of fatty acid synthase and diacylglycerol O-acyltransferase-2 compared with Ser251 mice. Moreover, Pro251 mice had a reduction of polyunsaturated fatty acids-TGs and reduced expression of epoxygenase genes. For our human study, we analysed the Penn Medicine BioBank, the Million Veteran Program, and UK Biobank. Across these databases, the minor allele frequency of PLIN2-Pro251 was approximately 5%. There was no association with the clinical diagnosis of NAFLD, however, there was a trend toward reduced liver fat in PLIN2-Pro251 carriers by MRI-spectroscopy in UK Biobank subjects. Conclusions: In mice lacking endogenous Plin2, expression of human PLIN2-Pro251 attenuated high-fat, high-fructose, high-cholesterol, diet-induced hepatic steatosis compared with human wild-type PLIN2-Ser251. Moreover, Pro251 mice had lower polyunsaturated fatty acids-TGs and epoxygenase genes expression, suggesting less liver oxidative stress. In humans, PLIN2-Pro251 is not associated with NAFLD. Impact and Implications: Lipid droplet accumulation in hepatocytes is the distinctive characteristic of non-alcoholic fatty liver disease. Perilipin 2 (PLIN2) is the most abundant protein in hepatic lipid droplets; however, little is known on the role of a specific polymorphism PLIN2-Pro251 on hepatic lipid droplet metabolism. PLIN2-Pro251 attenuates liver triglycerides accumulation after a high-fat-high-glucose-diet. PLIN2-Pro251 may be a novel lipid droplet protein target for the treatment of liver steatosis.

Novel ancestry-specific primary open-angle glaucoma loci and shared biology with vascular mechanisms and cell proliferation.

Primary open-angle glaucoma (POAG), a leading cause of irreversible blindness globally, shows disparity in prevalence and manifestations across ancestries. We perform meta-analysis across 15 biobanks (of the Global Biobank Meta-analysis Initiative) (n = 1,487,441: cases = 26,848) and merge with previous multi-ancestry studies, with the combined dataset representing the largest and most diverse POAG study to date (n = 1,478,037: cases = 46,325) and identify 17 novel significant loci, 5 of which were ancestry specific. Gene-enrichment and transcriptome-wide association analyses implicate vascular and cancer genes, a fifth of which are primary ciliary related. We perform an extensive statistical analysis of SIX6 and CDKN2B-AS1 loci in human GTEx data and across large electronic health records showing interaction between SIX6 gene and causal variants in the chr9p21.3 locus, with expression effect on CDKN2A/B. Our results suggest that some POAG risk variants may be ancestry specific, sex specific, or both, and support the contribution of genes involved in programmed cell death in POAG pathogenesis.

Clinical correlates of CT imaging-derived phenotypes among lean and overweight patients with hepatic steatosis.

The objective of this study is to define CT imaging derived phenotypes for patients with hepatic steatosis, a common metabolic liver condition, and determine its association with patient data from a medical biobank. There is a need to further characterize hepatic steatosis in lean patients, as its epidemiology may differ from that in overweight patients. A deep learning method determined the spleen-hepatic attenuation difference (SHAD) in Hounsfield Units (HU) on abdominal CT scans as a quantitative measure of hepatic steatosis. The patient cohort was stratified by BMI with a threshold of 25 kg/m2 and hepatic steatosis with threshold SHAD ≥ - 1 HU or liver mean attenuation ≤ 40 HU. Patient characteristics, diagnoses, and laboratory results representing metabolism and liver function were investigated. A phenome-wide association study (PheWAS) was performed for the statistical interaction between SHAD and the binary characteristic LEAN. The cohort contained 8914 patients-lean patients with (N = 278, 3.1%) and without (N = 1867, 20.9%) steatosis, and overweight patients with (N = 1863, 20.9%) and without (N = 4906, 55.0%) steatosis. Among all lean patients, those with steatosis had increased rates of cardiovascular disease (41.7 vs 27.8%), hypertension (86.7 vs 49.8%), and type 2 diabetes mellitus (29.1 vs 15.7%) (all p < 0.0001). Ten phenotypes were significant in the PheWAS, including chronic kidney disease, renal failure, and cardiovascular disease. Hepatic steatosis was found to be associated with cardiovascular, kidney, and metabolic conditions, separate from overweight BMI.

Meta-Analysis of Genome-Wide Association Studies Reveals Genetic Mechanisms of Supraventricular Arrhythmias.

BACKGROUND: Substantial data support a heritable basis for supraventricular tachycardias, but the genetic determinants and molecular mechanisms of these arrhythmias are poorly understood. We sought to identify genetic loci associated with atrioventricular nodal reentrant tachycardia (AVNRT) and atrioventricular accessory pathways or atrioventricular reciprocating tachycardia (AVAPs/AVRT). METHODS: We performed multiancestry meta-analyses of genome-wide association studies to identify genetic loci for AVNRT (4 studies) and AVAP/AVRT (7 studies). We assessed evidence supporting the potential causal effects of candidate genes by analyzing relations between associated variants and cardiac gene expression, performing transcriptome-wide analyses, and examining prior genome-wide association studies. RESULTS: Analyses comprised 2384 AVNRT cases and 106 489 referents, and 2811 AVAP/AVRT cases and 1,483 093 referents. We identified 2 significant loci for AVNRT, which implicate NKX2-5 and TTN as disease susceptibility genes. A transcriptome-wide association analysis supported an association between reduced predicted cardiac expression of NKX2-5 and AVNRT. We identified 3 significant loci for AVAP/AVRT, which implicate SCN5A, SCN10A, and TTN/CCDC141. Variant associations at several loci have been previously reported for cardiac phenotypes, including atrial fibrillation, stroke, Brugada syndrome, and electrocardiographic intervals. CONCLUSIONS: Our findings highlight gene regions associated with ion channel function (AVAP/AVRT), as well as cardiac development and the sarcomere (AVAP/AVRT and AVNRT) as important potential effectors of supraventricular tachycardia susceptibility.