Elastic Net Regularized Regression Research Articles

VICTOR: Validation and inspection of cell type annotation through optimal regression

Single-cell RNA sequencing provides unprecedent opportunities to explore the heterogeneity and dynamics inherent in cellular biology. An essential step in the data analysis involves the automatic annotation of cells. Despite development of numerous tools for automated cell annotation, assessing the reliability of predicted annotations remains challenging, particularly for rare and unknown cell types. Here, we introduce VICTOR: Validation and inspection of cell type annotation through optimal regression. VICTOR aims to gauge the confidence of cell annotations by an elastic-net regularized regression with optimal thresholds. We demonstrated that VICTOR performed well in identifying inaccurate annotations, surpassing existing methods in diagnostic ability across various single-cell datasets, including within-platform, cross-platform, cross-studies, and cross-omics settings.

Circulating cell-free and extracellular vesicles-derived microRNA as prognostic biomarkers in patients with early-stage NSCLC: results from RESTING study

BackgroundFactors to accurately stratify patients with early-stage non-small cell lung cancer (NSCLC) in different prognostic groups are still needed. This study aims to investigate 1) the prognostic potential of circulating cell-free (CF) and extracellular vesicles (EVs)-derived microRNA (miRNAs), and 2) their added value with respect to known prognostic factors (PFs).MethodsThe RESTING study is a multicentre prospective observational cohort study on resected stage IA-IIIA patients with NSCLC. The primary end-point was disease-free survival (DFS), and the main analyses were carried out separately for CF- and EV-miRNAs. CF- and EV-miRNAs were isolated from plasma, and miRNA-specific libraries were prepared and sequenced. To reach the study aims, three statistical models were specified: one using the miRNA data only (Model 1); one using both miRNAs and known PFs (age, gender, and pathological stage) (Model 2), and one using the PFs alone (Model 3). Five-fold cross-validation (CV) was used to assess the predictive performance of each. Standard Cox regression and elastic net regularized Cox regression were used.ResultsA total of 222 patients were enrolled. The median follow-up time was 26.3 (95% CI 25.4–27.6) months. From Model 1, three CF-miRNAs and 21 EV-miRNAs were associated with DFS. In Model 2, two CF-miRNAs (miR-29c-3p and miR-877-3p) and five EV-miRNAs (miR-181a-2-3p, miR-182-5p, miR-192-5p, miR-532-3p and miR-589-5p) remained associated with DFS. From pathway enrichment analysis, TGF-beta and NOTCH were the most involved pathways.ConclusionThis study identified promising prognostic CF- and EV-miRNAs that could be used as a non-invasive, cost-effective tool to aid clinical decision-making. However, further evaluation of the obtained miRNAs in an external cohort of patients is warranted.

The oncologic burden of residual disease in incidental gallbladder cancer: An elastic net regression model to profile high-risk features

IntroductionIncidental Gallbladder Cancer (IGBC) following cholecystectomy constitutes a significant portion of gallbladder cancer diagnoses. Re-exploration is advocated to optimize disease clearance and enhance survival rates. The consistent association of residual disease (RD) with inferior oncologic outcomes prompts a critical examination of re-resection's role as a modifying factor in the natural history of IGBC. MethodsAll patients diagnosed with gallbladder cancer between 2012 and 2022 were included. An elastic net regularized regression model was employed to profile high-risk predictors of RD within the IGBC group. Survival outcomes were assessed based on resection margins and RD. ResultsAmong the 181 patients undergoing re-exploration for IGBC, 133 (73.5 %) harbored RD, while 48 (26.5 %) showed no evidence. The elastic net model, utilizing a selected λ = 0.029, identified six coefficients associated with the risk of RD: aspiration from cholecystectomy (0.141), hepatic tumor origin (1.852), time to re-exploration >8 weeks (1.879), positive margin status (2.575), higher T stage (1.473), and poorly differentiated tumors (2.241). Furthermore, the study revealed a median overall survival of 44 months (CI 38–60) for IGBC patients with no evidence of RD, compared to 31 months (23–42) for those with RD (p < 0.001). ConclusionRe-resection revealed a high incidence of RD (73.5 %), significantly correlating with poorer survival outcomes. The preoperative identification of high-risk features provides a reliable biological disease profile. This aids in strategic preselection of patients who may benefit from re-resection, underscoring the need to consolidate outcomes with tailored chemotherapy for those with unfavorable characteristics.

Person-specific and pooled prediction models for binge eating, alcohol use and binge drinking in bulimia nervosa and alcohol use disorder.

Machine learning could predict binge behavior and help develop treatments for bulimia nervosa (BN) and alcohol use disorder (AUD). Therefore, this study evaluates person-specific and pooled prediction models for binge eating (BE), alcohol use, and binge drinking (BD) in daily life, and identifies the most important predictors. A total of 120 patients (BN: 50; AUD: 51; BN/AUD: 19) participated in an experience sampling study, where over a period of 12 months they reported on their eating and drinking behaviors as well as on several other emotional, behavioral, and contextual factors in daily life. The study had a burst-measurement design, where assessments occurred eight times a day on Thursdays, Fridays, and Saturdays in seven bursts of three weeks. Afterwards, person-specific and pooled models were fit with elastic net regularized regression and evaluated with cross-validation. From these models, the variables with the 10% highest estimates were identified. The person-specific models had a median AUC of 0.61, 0.80, and 0.85 for BE, alcohol use, and BD respectively, while the pooled models had a median AUC of 0.70, 0.90, and 0.93. The most important predictors across the behaviors were craving and time of day. However, predictors concerning social context and affect differed among BE, alcohol use, and BD. Pooled models outperformed person-specific models and the models for alcohol use and BD outperformed those for BE. Future studies should explore how the performance of these models can be improved and how they can be used to deliver interventions in daily life.

Weight gained during treatment predicts 6-month body mass index in a large sample of patients with anorexia nervosa using ensemble machine learning.

This study used machine learning methods to analyze data on treatment outcomes from individuals with anorexia nervosa admitted to a specialized eating disorders treatment program. Of 368 individuals with anorexia nervosa (209 adolescents and 159 adults), 160 individuals had data available for a 6-month follow-up analysis. Participants were treated in a 6-day-per-week partial-hospital program. Participants were assessed for eating disorder-specific and non-specific psychopathology. The analyses used established machine learning procedures combined in an ensemble model from support vector machine learning, random forest prediction, and the elastic net regularized regression with an exploration (training; 75%) and confirmation (test; 25%) split of the data. The models predicting body mass index (BMI) at 6-month follow-up explained a 28.6% variance in the training set (n = 120). The model had good performance in predicting 6-month BMI in the test dataset (n = 40), with predicted BMI significantly correlating with actual BMI (r = .51, p = 0.01). The change in BMI from admission to discharge was the most important predictor, strongly correlating with reported BMI at 6-month follow-up (r = .55). Behavioral variables were much less predictive of BMI outcome. Results were similar for z-transformed BMI in the adolescent-only group. Length of stay was most predictive of weight gain in treatment (r = .56) but did not predict longer-term BMI. This study, using an agnostic ensemble machine learning approach in the largest to-date sample of individuals with anorexia nervosa, suggests that achieving weight gain goals in treatment predicts longer-term weight-related outcomes. Other potential predictors, personality, mood, or eating disorder-specific symptoms were relatively much less predictive. The results from this study indicate that the amount of weight gained during treatment predicts BMI 6 months after discharge from a high level of care. This suggests that patients require sufficient time in a higher level of care treatment to meet their specific weight goals and be able to maintain normal weight.

What causes US equity market sector volatilities during the coronavirus pandemic?

ABSTRACT This paper seeks to identify key variables contributing to sectoral stock market volatilities in the US under the enduring pressure of the COVID-19 pandemic, using a broad array of candidate factors. We adopt a Beta-Skew-t-EGARCH model to capture the time-varying dynamics of the individual sectoral return volatilities. The empirical analysis is performed via an elastic-net regularized regression model. We find that trading volume, volatility of broad US dollar exchange rates, coronavirus infection rates, VIX, Google search trends, US economic policy uncertainty, and the initiation of vaccination programmes are the most common determinants of sectoral volatility.

How the acceleration phase influences energy flow and the resulting joint moments of the throwing shoulder in the deceleration phase of the javelin throw.

The throwing motion in the javelin throw applies high loads to the musculoskeletal system of the shoulder, both in the acceleration and deceleration phases. While the loads occurring during the acceleration phase and their relationship to kinematics and energy flow have been relatively well investigated, there is a lack of studies focusing the deceleration phase. Therefore, the aim of this study is to investigate how the throwing arm is brought to rest, which resultant joint torques are placed on the shoulder and how they are influenced by the kinematics of the acceleration phase. The throwing movement of 10 javelin throwers were recorded using a 12-infrared camera system recording at 300 Hz and 16 markers placed on the body. Joint kinematics, kinetics and energy flow were calculated between the touchdown of the rear leg and the timepoint of maximum internal rotation after release +0.1 s. Elastic net regularization regression was used to predict the joint loads in the deceleration phase using the kinematics and energy flow of the acceleration phase. The results show that a significant amount of energy is transferred back to the proximal segments, while a smaller amount of energy is absorbed. Furthermore, relationships between the kinematics and the energy flow in the acceleration phase and the loads placed on the shoulder joint in the deceleration phase, based on the elastic net regularized regression, could be established. The results indicate that the loads of the deceleration phase placed on the shoulder can be influenced by the kinematics of the acceleration phase. For example, an additional upper body forward tilt can help to increase the braking distance of the arm and thus contribute to a reduced joint load. Furthermore, the energy flow of the acceleration phase can be linked to joint stress. However, as previously demonstrated the generation of mechanical energy at the shoulder seems to have a negative effect on shoulder loading while the transfer can help optimize the stress. The results therefore show initial potential for optimizing movement, to reduce strain and improve injury prevention in the deceleration phase.

Global metabolomics revealed deviations from the metabolic aging clock in colorectal cancer patients.

Background: Markers of aging hold promise in the context of colorectal cancer (CRC) care. Utilizing high-resolution metabolomic profiling, we can unveil distinctive age-related patterns that have the potential to predict early CRC development. Our study aims to unearth a panel of aging markers and delve into the metabolomic alterations associated with aging and CRC. Methods: We assembled a serum cohort comprising 5,649 individuals, consisting of 3,002 healthy volunteers, 715 patients diagnosed with colorectal advanced precancerous lesions (APL), and 1,932 CRC patients, to perform a comprehensive metabolomic analysis. Results: We successfully identified unique age-associated patterns across 42 metabolic pathways. Moreover, we established a metabolic aging clock, comprising 9 key metabolites, using an elastic net regularized regression model that accurately estimates chronological age. Notably, we observed significant chronological disparities among the healthy population, APL patients, and CRC patients. By combining the analysis of circulative carcinoembryonic antigen levels with the categorization of individuals into the "hypo" metabolic aging subgroup, our blood test demonstrates the ability to detect APL and CRC with positive predictive values of 68.4% (64.3%, 72.2%) and 21.4% (17.8%, 25.9%), respectively. Conclusions: This innovative approach utilizing our metabolic aging clock holds significant promise for accurately assessing biological age and enhancing our capacity to detect APL and CRC.

Elastic net-based high dimensional data selection for regression

High-dimensional feature selection is of particular interest to researchers. In some domains, such as microarray data, it is quite common for a group of highly correlated explanatory variables to be of equal importance for inclusion in the predictive model. This paper proposes a new hybrid feature selection approach that integrates feature screening based on Kendall’s tau and Elastic Net regularized regression (K-EN). K-EN as an approach that embeds the Elastic Net, has the advantage of the grouping effect, which automatically includes all the highly correlated variables in the group. The K-EN approach offers insightful solutions to high-dimensional regression problems and improves Elastic Net performance since the screening phase is preceded by a step that further reduces the number of explanatory variables by removing those that disagree with the target based on Kendall’s tau. The use of Kendall’s tau further enhances Elastic Net performance, as it is robust enough to handle heavy-tailed distributions, non-parametric models, outliers, and non-normal data with greater ease. K-EN is therefore a time-saving approach. The proposed algorithm is evaluated on four simulation scenarios and four publicly available datasets, including riboflavin, eyedata, Longley, and Boston Housing, and achieves 0.2528, 0.0098, 0.1007, and 0.4121 respectively as the Mean Squared Error (MSE). K-EN’s MSEs are the best compared to those achieved by the state-of-the-art approaches reviewed in this paper. In addition, K-EN selects up to 100% of relevant features when run on simulated data.

Predicting anxiety and depression over 12 months of the COVID-19 pandemic: A machine learning study.

The coronavirus disease 2019 (COVID-19) pandemic was associated with substantial increases in anxiety and depressive symptoms. To understand individual risk, we examined a large set of potential risk factors for anxiety and depression in the pandemic context. Adults in the United States (N = 1200) completed eight online self-report assessments over 12 months of the COVID-19 pandemic. Area under the curve scores summarized cumulative experiences of anxiety and depression over the assessment period. A machine learning approach to elastic net regularized regression was used to select predictors of cumulative anxiety and depression severity from a set of 68 sociodemographic, psychological, and pandemic-related baseline variables. Cumulative anxiety severity was most strongly explained by stress and depression-related variables (such as perceived stress) and select sociodemographic characteristics. Cumulative depression severity was predicted by psychological variables, including generalized anxiety and depressive symptom reactivity. Being immunocompromised or having a medical condition were also important. By considering many predictors, findings provide a more complete view than previous studies focused on specific predictors. Important predictors included psychological variables suggested by prior research and variables more specific to the pandemic context. We discuss how such findings can be used in understanding risk and planning interventions.

Sleep Patterns, Plasma Metabolome, and Risk of Incident Type 2 Diabetes Mellitus.

A healthy sleep pattern has been related to a lower risk of type 2 diabetes mellitus (T2DM). We aimed to identify the metabolomic signature for the healthy sleep pattern and assess its potential causality with T2DM. This study included 78 659 participants with complete phenotypic data (sleep information and metabolomic measurements) from the UK Biobank study. Elastic net regularized regression was applied to calculate a metabolomic signature reflecting overall sleep patterns. We also performed genome-wide association analysis of the metabolomic signature and one-sample mendelian randomization (MR) with T2DM risk. During a median of 8.8 years of follow-up, we documented 1489 incident T2DM cases. Compared with individuals who had an unhealthy sleep pattern, those with a healthy sleep pattern had a 49% lower risk of T2DM (multivariable-adjusted hazard ratio [HR], 0.51; 95% CI, 0.40-0.63). We further constructed a metabolomic signature using elastic net regularized regressions that comprised 153 metabolites, and robustly correlated with sleep pattern (r = 0.19; P = 3×10-325). In multivariable Cox regressions, the metabolomic signature showed a statistically significant inverse association with T2DM risk (HR per SD increment in the signature, 0.56; 95% CI, 0.52-0.60). Additionally, MR analyses indicated a significant causal relation between the genetically predicted metabolomic signature and incident T2DM (P for trend < .001). In this large prospective study, we identified a metabolomic signature for the healthy sleep pattern, and such a signature showed a potential causality with T2DM risk independent of traditional risk factors.

Exploring structural connectomes in children with unilateral cerebral palsy using graph theory.

We explored structural brain connectomes in children with spastic unilateral cerebral palsy (uCP) and its relation to sensory-motor function using graph theory. In 46 children with uCP (meanage=10 years 7 months ± 2 years 9 months; Manual Ability Classification System I=15, II=16, III=15)we assessed upper limb somatosensory and motor function. We collected multi-shell diffusion-weighted, T1-weighted and T2-FLAIR MRI and identified the corticospinal tract (CST) wiring pattern using transcranial magnetic stimulation. Structural connectomes were constructed using Virtual Brain Grafting-modified FreeSurfer parcellations and multi-shell multi-tissue constrained spherical deconvolution-based anatomically-constrained tractography. Graph metrics (characteristic path length, global/local efficiency and clustering coefficient) of the whole brain, the ipsilesional/contralesional hemisphere, and the full/ipsilesional/contralesional sensory-motor network were compared between lesion types (periventricular white matter (PWM)=28, cortical and deep gray matter (CDGM)=18) and CST-wiring patterns (ipsilateral=14, bilateral=14, contralateral=12, unknown=6) using ANCOVA with age as covariate. Using elastic-net regularized regression we investigated how graph metrics, lesion volume, lesion type, CST-wiring pattern and age predicted sensory-motor function. In both the whole brain and subnetworks, we observed a hyperconnectivity pattern in children with CDGM-lesions compared with PWM-lesions, with higher clustering coefficient (p=[<.001-.047], =[0.09-0.27]), characteristic path length (p=.003, =0.19) and local efficiency (p=[.001-.02], =[0.11-0.21]), and a lower global efficiency with age (p=[.01-.04], =[0.09-0.15]). No differences were found between CST-wiring groups. Overall, good predictions of sensory-motor function were obtained with elastic-net regression (R2 =.40-.87). CST-wiring pattern was the strongest predictor for motor function. For somatosensory function, all independent variables contributed equally to the model. Inconclusion, we demonstrated the potential of structural connectomics in understanding disease severity and brain development in children with uCP.

Elastic Net Regularization Paths for All Generalized Linear Models.

The lasso and elastic net are popular regularized regression models for supervised learning. Friedman, Hastie, and Tibshirani (2010) introduced a computationally efficient algorithm for computing the elastic net regularization path for ordinary least squares regression, logistic regression and multinomial logistic regression, while Simon, Friedman, Hastie, and Tibshirani (2011) extended this work to Cox models for right-censored data. We further extend the reach of the elastic net-regularized regression to all generalized linear model families, Cox models with (start, stop] data and strata, and a simplified version of the relaxed lasso. We also discuss convenient utility functions for measuring the performance of these fitted models.

Gain of chr1q Portends Poor Outcomes in Multiple Myeloma Patients Treated with Venetoclax

Venetoclax is a BH3-mimetic small molecule that selectively inhibits the anti-apoptotic protein BCL-2 and triggers cell death. While it is only approved for Acute Myeloid Leukemia (AML) and Chronic Lymphocytic Leukemia (CLL), its use in Multiple Myeloma (MM) in clinical trials has demonstrated excellent activity as a single agent and in combination with other therapies, particularly in patients carrying the t(11;14) translocation involving CCND1 (Kumar et al, Lancet Oncol 2020; Ehsan et al, J Hematol 2021). In this study, we sought to investigate the genomic determinants of response to venetoclax in a real-world setting outside of clinical trials. In an IRB-approved retrospective review of the Mount Sinai Electronic Medical Record, we identified 58 MM patients who received Venetoclax between 2017 and 2022. Most of these patients received Venetoclax in combination with other therapeutics, including the monoclonal antibody Daratumumab, proteasome inhibitors (PI), immune-modulatory drugs (IMID) and the HDAC inhibitor Panobinostat, and only 5 received Venetoclax as single agent. Patients had received a median of 4 previous lines of therapy (range 1-18). The median progression-free survival (PFS) was 7.13 months, with an ORR of 53% (defined as PR or better). Most patients exhibited the t(11;14) translocation of CCND1 (n=48, 83%), which was likely used as a biomarker for patient selection, given its association with better response to the drug as suggested by previous literature. Median PFS in t(11;14) patients was 7.41 months vs 4 months in patients in the non-t(11;14) group (p=0.07). Further stratification based on gain of 1q revealed that patients with t(11;14) and concurrent gain of 1q (n=19; 39.5%) had significantly worse PFS than patients with t(11;14) alone (HR=5.4; 95% CI: 1.9-15.1; p<0.001) (Fig. 1A). These findings were confirmed also in multivariate analysis including potential confounding variables such as age, sex, race, previous lines of therapy, and ISS. While t(11;14) was associated with a more durable response, we observed cases of fast progression in the t(11;14) group, as well as cases with durable response in the non-t(11;14) group, indicating that other markers should be investigated for better identification of patients who are more likely to benefit from this treatment. RNA-seq data was available for 46 of the 58 patients, which we analyzed to determine potential gene expression markers of response. First, we evaluated markers proposed in previous studies, such as BCL2, MCL1 and the BCL2/BCL2L1 and BCL2/MCL1 ratios, stratifying patients based on median PFS. Our analysis showed a trend towards higher expression of BCL2 (p=0.07) and the BCL2/MCL1 ratio (p=0.07), as well as significant up-regulation of the BCL2/BCL2L1 ratio in patients with higher PFS (p<0.05). No significant difference was observed in the expression of MCL1. To further determine potential novel markers of response, we performed elastic-net regularized regression to predict PFS, which identified a predictive signature of 6 genes (ATP1B3, MYL2, CNR1, FKBPL, LRRK2-DT, LINC02541). The Kaplan-Meier estimator showed significant stratification of patients according to the signature, where up-regulation corresponded to significantly shorter PFS compared with medium expression and down-regulation (p<0.0001) (Fig. 1B). Furthermore, the signature was significantly associated with depth of response, where up-regulation identified non-responders (less than PR; n=22) vs responders (PR and above; n=23) (p<0.05). To validate the predictive power of this signature, we analyzed a dataset with 20 RNA-seq samples from patients who received Venetoclax monotherapy from a recent independent study (Gupta et al., Blood 2021). Since PFS data was not available, we evaluated the signature using Best Response to stratify patients in responders (PR and above; n=10) and non-responders (less than PR; n=10). Concordantly with the results obtained on our dataset, up-regulation of the signature significantly identified non-responders (p=0.01). In conclusion, here we report that gain of 1q is associated with shorter response to venetoclax in MM, including patients with t(11;14), and the identification of a novel six-gene signature that predicts response to the drug in terms of both duration and depth of response. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal

Identifying and predicting posttraumatic stress symptom states in adults with posttraumatic stress disorder.

Between-person heterogeneity of posttraumatic stress disorder (PTSD) is well established. Within-person analyses and the DSM-5 suggest that heterogeneity may also be evident within individuals across time as they move through social contexts and biological cycles. Modeling within-person symptom-level fluctuations may confirm such heterogeneity, elucidate mechanisms of disorder maintenance, and inform time- and person-specific interventions. The present study aimed to identify and predict discrete within-person disorder presentations, or symptom states, and explore group-level patterns of these states. Adults (N = 20, 60.0% male, M age = 38.25 years) with PTSD responded to symptom surveys four times per day for 30 days. We subjected each individual's dataset to Gaussian finite mixture modeling (GFMM) to uncover latent, within-person classes of symptom levels (i.e., states) and predicted those states with idiographic elastic net regularized regression using a set of time-based and behavioral predictors. Next, we conducted a GFMM of the within-person GFMM outputs and tested idiographic prediction models of these states. Multiple within-person states were revealed for 19 of 20 participants (Mdn = 4; 66 for the full sample). Prediction models were moderately successful, M AUC = .66 (d = 0.58), range: .50-1.00. The GFMM of the within-person model outputs revealed two states: one with above-average and one with below-average symptom levels. Prediction models were, again, moderately successful, M AUC = .66; range: .50-.89. The findings provide evidence for within-person heterogeneity of PTSD as well as between-person similarities and suggest that future work should incorporate additional contextual variables as symptom state predictors.

A climate-driven model for predicting the level of Vibrio parahaemolyticus in oysters harvested from Taiwanese farms using elastic net regularized regression

This study aimed at, and developed, a climate-driven model for predicting the abundance of V. parahaemolyticus in oysters based on the local climatological and environmental conditions in Taiwan. The predictive model was constructed using the elastic net machine learning method, and the most influential predictors were evaluated using a permutation-based approach. The abundance of V. parahaemolyticus in oysters in different seasons, time horizons, and representative concentration pathways (RCPs) were predicted using the Elastic-net machine learning model. The results showed: (1) the variation in wind speed or gust wind speed, sea surface temperature, precipitation, and pH influenced the prediction of V. parahaemolyticus concentration in oysters, and (2) the level of V. parahaemolyticus in oysters in Taiwan was projected to be increased by 40–67% in the near future (2046–2065) and by 39–86% by the end of twentieth-century (2081–2100) if the global temperature continues to increase due to climate change. The findings in this study may be used as inputs for quantifying the V. parahaemolyticus infection risk from eating this seafood in Taiwan.

Using supervised machine learning approach to predict treatment outcomes of vedolizumab in ulcerative colitis patients

ABSTRACT With recent advances in machine learning, we demonstrated the use of supervised machine learning to optimize the prediction of treatment outcomes of vedolizumab through iterative optimization using VARSITY and VISIBLE 1 data in patients with moderate-to-severe ulcerative colitis. The analysis was carried out using elastic net regularized regression following a 2-stage training process. The model performance was assessed through AUROC, specificity, sensitivity, and accuracy. The generalizable predictive patterns suggest that easily obtained baseline and medical history variables may be able to predict therapeutic response to vedolizumab with clinically meaningful accuracy, implying a potential for individualized prescription of vedolizumab.

Abstract P108: Metabolic Profile Of Diet Quality In The Multi-Ethnic Study Of Atherosclerosis

Introduction: Poor dietary quality is a well-known risk factor for diabetes and cardiovascular disease (CVD), however metabolites marking adherence to U.S. dietary guidelines are unknown. Our goal was to determine a pattern of metabolites associated with the Healthy Eating Index-2015 (HEI-2015). We hypothesize that there will be metabolites positively and negatively associated with the HEI-2015 score, including those previously linked to diabetes and CVD. Methods: Sample: 2269 adult men and women from the Multi-Ethnic Study of Atherosclerosis (MESA) longitudinal cohort study without known cardiovascular disease or diabetes. Data/specimens: Fasting serum specimens, diet and demographic questionnaires at baseline. Metabolomics: Untargeted 1 H NMR CPMG spectroscopy (600 MHz) annotated by internal and external reference data sets. Statistical analysis: Metabolome-wide association study (MWAS) using linear regression models specifying each spectral feature as the outcome in separate models, HEI-2015 score as the predictor, and adjustment for age, sex, race, and study site, accounting for multiple comparisons. Elastic net regularized regression was used to select an optimal subset of features associated with HEI-2015 score. Separately, hierarchical clustering defined discrete groups of correlated NMR features also tested for association with HEI-2015 score. Results: MWAS identified 1914 spectral features significantly associated with the HEI-2015 diet score. After elastic net regression, 35 metabolomic spectral features remained associated with HEI-2015 diet score. Cluster analysis identified seven clusters, three of which were significantly associated with HEI-2015 score after Bonferroni correction. (Table) Conclusions: Cholesterol moieties, proline betaine, proline/glutamate and fatty acyls chains were significantly associated with higher diet quality in the MESA cohort. Further analysis may clarify the link between dietary quality, metabolites, and pathogenesis of diabetes and CVD.

The lipid profile for the prediction of prednisolone treatment response in patients with inflammatory hand osteoarthritis: The HOPE study

ObjectiveTo explore the use of lipidomics for prediction of prednisolone treatment response in patients with inflammatory hand osteoarthritis. DesignThe Hand Osteoarthritis Prednisolone Efficacy (HOPE) study included patients (n ​= ​92) with symptomatic inflammatory hand osteoarthritis, fulfilling the ACR criteria. The present analyses comprised only patients randomized to prednisolone treatment (10 ​mg daily, n ​= ​40). Response to prednisolone treatment was defined according to the OARSI-OMERACT responder criteria at six weeks. Baseline blood samples were obtained non-fasted. Lipid species were quantified in erythrocytes with the Lipidyzer™ platform (Sciex). Oxylipins were analyzed in plasma using an in-house LC-MS/MS platform. Elastic net regularized regression was used to predict prednisolone treatment response based on common patient characteristics alone and including the patients’ lipid profile. ROC analyses with 1000 bootstrapped area under the curve (AUC) was used to determine the discriminatory accuracy of the models. ResultsAmong included patients, 78% fulfilled the OARSI-OMERACT responder criteria. From the general patient characteristics, elastic net selected baseline hand function as only predictor of treatment response, with an AUC of 0.78 (0.56; 0.97). Addition of lipidomics resulted in an AUC of 0.92 (0.78; 0.99) and 0.85 (0.65; 0.98) for inclusion of the Lipidyzer™ platform and oxylipin platform, respectively. ConclusionOur results suggest that the patients’ lipid profile may improve the discriminative accuracy of the prediction of prednisolone treatment response in patients with inflammatory hand osteoarthritis compared to prediction by commonly measured patient characteristics alone. Hence, lipidomics may be a promising field for biomarker discovery for prediction of anti-inflammatory treatment response.

Examination of the association between exposure to childhood maltreatment and brain structure in young adults: a machine learning analysis.

Exposure to maltreatment during childhood is associated with structural changes throughout the brain. However, the structural differences that are most strongly associated with maltreatment remain unclear given the limited number of whole-brain studies. The present study used machine learning to identify if and how brain structure distinguished young adults with and without a history of maltreatment. Young adults (ages 18-21, n = 384) completed an assessment of childhood trauma exposure and a structural MRI as part of the IMAGEN study. Elastic net regularized regression was used to identify the structural features that identified those with a history of maltreatment. A generalizable model that included 7 cortical thicknesses, 15 surface areas, and 5 subcortical volumes was identified (area under the receiver operating characteristic curve = 0.71, p < 0.001). Those with a maltreatment history had reduced surface areas and cortical thicknesses primarily in fronto-temporal regions. This group also had larger cortical thicknesses in occipital regions and surface areas in frontal regions. The results suggest childhood maltreatment is associated with multiple measures of structure throughout the brain. The use of a large sample without exposure to adulthood trauma provides further evidence for the unique contribution of childhood trauma to brain structure. The identified regions overlapped with regions associated with psychopathology in adults with maltreatment histories, which offers insights as to how these disorders manifest.