Regularized Regression Research Articles

Abstract 6648: Prediction of anti-PD-1 efficacy based on immune marker densities and their spatial distribution in colorectal cancer

Abstract Background: Immune checkpoint inhibitors (ICIs) have revolutionized the treatment of patients with deficient DNA mismatch repair (d-MMR) metastatic colorectal cancer (CRC), yet less than half of patients receive clinical benefit. We hypothesized that immune contexture including spatial distribution of cells expressing immune molecules in the tumor microenvironment may predict immunotherapy outcome. Methods: Primary CRC tissues from consecutive patients with d-MMR metastatic CRC (N=33) were treated with anti-PD-1 antibodies at Mayo Clinic Comprehensive Cancer Center (2015-2018). Tumors were stained for PD-L1, PD-1, CD8, CD3, CD68, LAG3, TGFβR2, MHC-I, CD14, B2M, DAPI and pan-cytokeratin in 5 compartments (overall tumor, tumor epithelia, tumor stroma, peritumor inside vs outside) by multiplex immunofluorescence with digital image analysis. Features computed within each image analysis region included positive cell density, fraction of positive cell types, intensity of positive cells, and spatial distribution between distinct cell types (distances measured using image analysis software). Prior to model fitting, feature selection was performed using regularized Cox regression with LASSO. Regularization parameter was chosen based on 5-fold cross validation. A Cox proportional hazards model was fitted to predict patient progression-free survival (PFS). Results: Among patients with d-MMR CRCs, 16/33 (48.4%) were female, 10 received first-line ICI therapy, and 23 had received > 1 prior chemotherapy regimen. Median age was 61.6 years (IQR of 49.4, 73.7). Eight patients (24.2%) harbored BRAFV600E, 9 (27.2%) had mutant KRAS, and median PFS was 22.2 months (95% CI: 11.8, NR) with 20 events. PD-L1 was expressed in tumor cells, CD68+ macrophages, and CD3+ T lymphocytes. PD-1 expression on CD8+ T lymphocytes was also observed. By univariate analysis, only cell-cell distance readouts achieved statistical significance. Multivariable feature selection identified the mean number of PD-1+ cells within 10 microns of a PD-L1+ cell in the overall tumor as the strongest predictor of anti-PD-1 efficacy, and was significantly associated with PFS (HR=0.87, 95% CI: 0.79-0.95, p< 0.001). In contrast, the ratio of PD-1+/PD-L1+ cells was not predictive of treatment efficacy (p= 0.47), thereby underscoring the importance of spatial distribution for PFS prediction. Conclusion: The mean number of PD-1+ cells in proximity to PD-L1+ cells in tumors was a predictive biomarker of anti-PD-1 efficacy. Confirmatory studies are warranted. Citation Format: Bahar Saberzadeh-Ardestani, Rondell P. Graham, Qian Shi, Eze Ahanonu, Sara McMahon, Crystal Williams, Antony Hubbard, Wenjun Zhang, Andrea Muranyi, Dongyao Yan, Kandavel Shanmugam, Frank A. Sinicrope. Prediction of anti-PD-1 efficacy based on immune marker densities and their spatial distribution in colorectal cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 6648.

An Algorithm of Nonparametric Quantile Regression.

Extreme events, such as earthquakes, tsunamis, and market crashes, can have substantial impact on social and ecological systems. Quantile regression can be used for predicting these extreme events, making it an important problem that has applications in many fields. Estimating high conditional quantiles is a difficult problem. Regular linear quantile regression uses an L 1 loss function [Koenker in Quantile regression, Cambridge University Press, Cambridge, 2005], and the optimal solution of linear programming for estimating coefficients of regression. A problem with linear quantile regression is that the estimated curves for different quantiles can cross, a result that is logically inconsistent. To overcome the curves crossing problem, and to improve high quantile estimation in the nonlinear case, this paper proposes a nonparametric quantile regression method to estimate high conditional quantiles. A three-step computational algorithm is given, and the asymptotic properties of the proposed estimator are derived. Monte Carlo simulations show that the proposed method is more efficient than linear quantile regression method. Furthermore, this paper investigates COVID-19 and blood pressure real-world examples of extreme events by using the proposed method.

Sub-resolution modeling of the apparent mass loss in quantitative broadband X-ray radiography

The quantitative impact of image blur on calculated object mass in X-ray radiography is explored. Radiographed object masses are initially estimated through experimental calibration and compared against their known true mass, with the deviation, or “apparent mass loss”. Apparent mass loss occurs due to the effect of spatial blur on X-ray transmission images that reduces the measured mass because while the image intensity is conserved with spatial blur, the nonlinear conversion to path length is not. A synthetic model is proposed where an object’s apparent mass loss is estimated through the amount of blur present within the radiograph image. The image blur is inferred through a combination of readily available image parameters related to the signal levels, object shape, and experimental extrinsics. A regularized regression model is built that correlates these blur parameters to the expected mass loss. The model is first trained on 2100 and tested on 140 synthetically created objects, and then later verified on two separate experimental setups of type 304 stainless steel objects imaged with a portable tube source at 150 kVp and type 6061 aluminum objects at 80 kVp. The proposed model allows for a simple post hoc reduction in errors of approximately 20% in object mass through X-ray radiography.

Predictive performance for prognosis of aneurysmal subarachnoid hemorrhage with ventricular hemorrhage by imaging combined with clinical and laboratory quantitative index model

Objective: To explore the predictive performance of image quantitative index model, clinical-laboratory index model and image-clinical multi-dimensional fusion model in predicting the prognosis of patients with aneurysmal subarachnoid hemorrhage (aSAH) with intraventricular hemorrhage (IVH). Methods: A total of 349 patients with aSAH and IVH, including 122 males and 227 females, aged 22 to 85 (59±11) years underwent CT scan in the General Hospital of Eastern Theater Command from January 2010 to December 2019 were used as dataset 1 to construct a prognostic model. A prognostic model was constructed for data set 1, and the functional recovery of patients 12 months after discharge was evaluated using the modified Rankin Scale (mRS). According to the results, those patients were divided into two groups: good outcome group (n=267) and poor outcome group (n=82). In addition, 63 aSAH patients with IVH, including 27 males and 36 females, aged 32 to 87 (61±12) years who were admitted to the General Hospital of Eastern Theater Command from January 2020 to December 2021 were collected as dataset 2 for independent verification of the model, including 30 patients with poor prognosis. Clinical information (age and gender), laboratory indicators (blood routine and blood biochemistry), and imaging quantitative indicators (such as volume, density, shape of each ventricle hemorrhage area outlined and extracted on head CT scan etc.) were recorded for all patients (dataset 1 and 2). The clinical, laboratory and imaging quantitative indicators of dataset 1 were screened by using L1 regularization and multiple logistic regression method was used to construct the clinical-laboratory index model, image quantitative index model and image-clinical multi-dimensional fusion model, according to the weight coefficient of features in the clinical-laboratory index model and image quantitative index model, screen out the main features. The model was trained and internally validated by 5-fold cross-validation. The model was validated independently in dataset 2. Results: The AUC (area under the ROC curve) of clinical-laboratory index model, image quantitative index model and multidimensional fusion model constructed based on dataset 1 were 0.75 (95%CI: 0.69-0.81), 0.68 (95%CI: 0.61-0.74) and 0.86 (95%CI: 0.82-0.91). The Delong test showed that there were statistically significant differences between the performance of the multi-dimensional fusion model and the clinical-laboratory index model or image quantitative index model (all P<0.05). The AUC of clinical-laboratory index model, image quantitative index model and multidimensional fusion model of dataset 2 were 0.79 (95%CI: 0.68-0.91), 0.70 (95%CI: 0.57-0.83) and 0.81 (95%CI: 0.70-0.92). In addition, in the clinical-laboratory index model and imaging quantitative index model constructed based on data 1, age, Hunt-Hess grade on admission, Neutrophil/Lymphocyte (N/L) (the weight coefficients in the clinical-laboratory index model were 1.00, -0.59 and 0.44) and the standard deviation of third ventricle hemorrhage density, minimum hemorrhage density of the fourth ventricle, and left ventricle hemorrhage sphericity (the weight coefficients in the image quantitative index model were -1.00, 0.85 and -0.84) were the main features of the screening. Conclusions: Quantitative imaging indicators of ventricular hemorrhage (standard deviation of third ventricular hemorrhage density, minimum density of fourth ventricular hemorrhage, and left ventricular sphericity) are helpful to predict the poor prognosis of patients with aSAH with ventricular hemorrhage. Dimensional fusion model has greater value in predicting poor prognosis of patients.

Seaport Network Efficiency Measurement Using Triangular and Trapezoidal Fuzzy Data Envelopment Analyses with Liner Shipping Connectivity Index Output

Seaport network efficiency is very crucial for global maritime economic trades and growth. In this work, data of three years (2018–2020) with input variables (time in port, age of vessels, size of vessels, cargo carrying capacity of vessels) and output variables (Liner Shipping Connectivity Index (LSCI) and Gross Domestic Product (GDP)) are collected. Few screening tests are performed to ensure the data are fit for further analyses. Since none of the existing studies has ever considered LSCI as an output variable, the main purpose of this study is to measure seaport network efficiency based on LSCI using data envelopment analysis (DEA), both classical and fuzzy. In fuzzy DEA, triangular fuzzy number (TrFN) and trapezoidal fuzzy number (TpFN) are used to construct the fuzzy sets of efficiency scores with DEA. The comparison between DEA and triangular fuzzy data envelopment analysis (TrFDEA) shows the range of differences in the results ranges from −0.0274 to 0.0105, while the comparison between DEA and trapezoidal fuzzy data envelopment analysis (TpFDEA) yields the differences within the range of −0.0307 to 0.0106. Using DEA as the relative reference, it is further revealed that the TpFDEA has smaller standard deviations and variances than the TrFDEA in 2018 and 2019, whereas the opposites hold true during the pandemic year of 2020. With the use of fuzzy numbers, the uncertainty levels in the seaport network efficiency measurement can further be investigated as the minimum, mean, median and maximum values are taken into consideration. Moreover, the proposed TrFDEA and TpFDEA lead new insights on the boundedness concept of the efficiency scores, which were never reported before by any researcher, especially in the maritime industry research. Fuzzy regression modelling based on the Possibilistic Linear Regression Least Squares (PLRLS) method was also performed to determine the interval of minimum and maximum connectivity efficiencies, which gave a better estimation than the regular regression model.

A New Quantile-Based Approach for LASSO Estimation

Regularization regression techniques are widely used to overcome a model’s parameter estimation problem in the presence of multicollinearity. Several biased techniques are available in the literature, including ridge, Least Angle Shrinkage Selection Operator (LASSO), and elastic net. In this work, we study the performance of the classical LASSO, adaptive LASSO, and ordinary least squares (OLS) methods in high-multicollinearity scenarios and propose some new estimators for estimating the LASSO parameter “k”. The performance of the proposed estimators is evaluated using extensive Monte Carlo simulations and real-life examples. Based on the mean square error criterion, the results suggest that the proposed estimators outperformed the existing estimators.

Important Correlates of Purpose in Life in a Diverse Population-Based Cohort: A Machine Learning Approach

BackgroundPurpose-in-life (PiL) refers to the tendency to derive meaning and purpose from daily life experiences. Individuals with higher PiL were more likely to have better physical, mental, and cognitive health in prospective studies. Here, we aimed to identify important correlates of PiL among people of diverse backgrounds. MethodsParticipants were recruited by the population-based Health and Retirement Study and provided information on 34 different sociodemographic and psychosocial factors through psychometrically validated measures. To identify important correlates of PiL, we employed regularized regression implemented by Elastic Net on the entire cohort as well as among self-identified black participants only and white participants only, respectively. ResultsA total of 6,620 participants were included in this study, among whom 913 were black and 5,707 were white. We identified 12 and 23 important sociodemographic and psychosocial correlates of PiL among black and white participants, respectively. Notably, all the 12 correlates in black participants were also correlates among white participants. Interestingly, when we examined both black and white participants together, being black was associated with having higher PiL. The correlates with the largest effect on PiL that were shared among black and white participants were hopelessness, perceived constraint on personal control, and self-mastery. ConclusionSeveral sociodemographic and psychosocial factors most strongly associated with PiL were shared among black and white participants. Future studies should investigate whether interventions targeting correlates of PiL can lead to higher sense of life purpose in participants of diverse backgrounds.

Bayesian group bridge composite quantile regression

Bayesian regularized composite quantile regression (CQR) method with group bridge penalty is adopted to conduct covariate selection and estimation in CQR. MCMC algorithm was improved for posterior inference employing a scale mixture of normal of the asymmetric Laplace distribution (ALD). The suggested algorithm uses priors for the coefficients of regression, which are scale mixtures of multivariate uniform distributions with a particular Gamma distribution as a mixing distribution. Simulation results and analyses of real data show that the suggested MCMC sampler has excellent mixing feature and outperforms the current approaches in terms of prediction accuracy and model selection.

DNA Damage Response (DDR) Is Associated With Treatment-free Remission in Chronic Myeloid Leukemia Patients.

DNA Damage Response (DDR) Is Associated With Treatment-free Remission in Chronic Myeloid Leukemia Patients.

Robust variable selection and estimation via adaptive elastic net S-estimators for linear regression

Heavy-tailed error distributions and predictors with anomalous values are ubiquitous in high-dimensional regression problems and can seriously jeopardize the validity of statistical analyses if not properly addressed. For more reliable variable selection and prediction under these adverse conditions, adaptive PENSE, a new robust regularized regression estimator, is proposed. Adaptive PENSE yields reliable variable selection and coefficient estimates even under aberrant contamination in the predictors or residuals. It is shown that the adaptive penalty leads to more robust and reliable variable selection than other penalties, particularly in the presence of gross outliers in the predictor space. It is further demonstrated that adaptive PENSE has strong variable selection properties and that it possesses the oracle property even under heavy-tailed errors and without the need to estimate the error scale. Numerical studies on simulated and real data sets highlight the superior finite-sample performance in a vast range of settings compared to other robust regularized estimators in the case of contaminated samples. An R package implementing a fast algorithm for computing the proposed method and additional simulation results are provided in the supplementary materials.

Neural network-based parking system object detection and predictive modeling

&lt;span lang="EN-US"&gt;A neural network-based parking system with real-time license plate detection and vacant space detection using hyper parameter optimization is presented. When number of epochs increased from 30, 50 to 80 and learning rate tuned to 0.001, the validation loss improved to 0.017 and training object loss improved to 0.040. The model mean average precision mAP_0.5 is improved to 0.988 and the precision is improved to 99%. The proposed neural network-based parking system also uses a regularization technique for effective predictive modeling. The proposed modified lasso ridge elastic (LRE) regularization technique provides a 5.21 root mean square error (RMSE) and an R-square of 0.71 with a 4.22 mean absolute error (MAE) indicative of higher accuracy performance compared to other regularization regression models. The advantage of the proposed modified LRE is that it enables effective regularization via modified penalty with the feature selection characteristics of both lasso and ridge.&lt;/span&gt;

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.

Sampling constrained continuous probability distributions: A review

AbstractThe problem of sampling constrained continuous distributions has frequently appeared in many machine/statistical learning models. Many Markov Chain Monte Carlo (MCMC) sampling methods have been adapted to handle different types of constraints on random variables. Among these methods, Hamilton Monte Carlo (HMC) and the related approaches have shown significant advantages in terms of computational efficiency compared with other counterparts. In this article, we first review HMC and some extended sampling methods, and then we concretely explain three constrained HMC‐based sampling methods, reflection, reformulation, and spherical HMC. For illustration, we apply these methods to solve three well‐known constrained sampling problems, truncated multivariate normal distributions, Bayesian regularized regression, and nonparametric density estimation. In this review, we also connect constrained sampling with another similar problem in the statistical design of experiments with constrained design space.This article is categorized under: Applications of Computational Statistics &gt; Computational Mathematics Statistical and Graphical Methods of Data Analysis &gt; Bayesian Methods and Theory Statistical and Graphical Methods of Data Analysis &gt; Markov Chain Monte Carlo (MCMC) Statistical and Graphical Methods of Data Analysis &gt; Sampling

Long Noncoding RNA Expression Independently Predicts Outcome in Pediatric Acute Myeloid Leukemia.

Optimized strategies for risk classification are essential to tailor therapy for patients with biologically distinctive disease. Risk classification in pediatric acute myeloid leukemia (pAML) relies on detection of translocations and gene mutations. Long noncoding RNA (lncRNA) transcripts have been shown to associate with and mediate malignant phenotypes in acute myeloid leukemia (AML) but have not been comprehensively evaluated in pAML. To identify lncRNA transcripts associated with outcomes, we evaluated the annotated lncRNA landscape by transcript sequencing of 1,298 pediatric and 96 adult AML specimens. Upregulated lncRNAs identified in the pAML training set were used to establish a regularized Cox regression model of event-free survival (EFS), yielding a 37 lncRNA signature (lncScore). Discretized lncScores were correlated with initial and postinduction treatment outcomes using Cox proportional hazards models in validation sets. Predictive model performance was compared with standard stratification methods by concordance analysis. Training set cases with positive lncScores had 5-year EFS and overall survival rates of 26.7% and 42.7%, respectively, compared with 56.9% and 76.3% with negative lncScores (hazard ratio, 2.48 and 3.16; P < .001). Pediatric validation cohorts and an adult AML group yielded comparable results in magnitude and significance. lncScore remained independently prognostic in multivariable models, including key factors used in preinduction and postinduction risk stratification. Subgroup analysis suggested that lncScores provide additional outcome information in heterogeneous subgroups currently classified as indeterminate risk. Concordance analysis showed that lncScore adds to overall classification accuracy with at least comparable predictive performance to current stratification methods that rely on multiple assays. Inclusion of the lncScore enhances predictive power of traditional cytogenetic and mutation-defined stratification in pAML with potential, as a single assay, to replace these complex stratification schemes with comparable predictive accuracy.

Active and Happy? Physical Activity and Life Satisfaction among Young Educated Women.

Physical activity belongs to the group of health-promoting behaviors. It also affects emotional well-being, which is linked to a higher quality of life. Individuals who participate in physical activity practice regardless of age reap several positive health benefits that affect both body and mind. The aim of this study was to assess the life satisfaction of young adults in the context of physical activity undertaken. Study material was collected via anonymous questionnaire surveys among 328 young women (between the ages of 18 and 30 with secondary or higher education) in Poland. Satisfaction with life was assessed using The Satisfaction with Life Scale (SWLS). Statistical calculations were performed using the STATISTICA 13.3 program, Stat Soft Poland. Interdependence of unmeasured characteristics was assessed using the X2 test. Multivariate analysis for the direct effect of physical activity on life satisfaction (LS) and the influence of frequency of physical fitness on life satisfaction was performed based on regular OLS multiple regression. The majority of respondents (74.7%) reported engaging in physical exercise. The mean level of life satisfaction was 4.5 ± 1.1 (on a scale of 1 to 7). Multivariate analysis showed no statistically significant relationship with life satisfaction in the physically active and inactive groups. It was observed that significantly higher levels of life satisfaction were found among respondents: married 5.1 ± 1.1, median = 5.2 (4.5-5.9) compared to single 4.4 ± 1.2, median = 4.6 (3.6-5.2) and in informal relationships 4.5 ± 1.0, median = 4.4 (3.8-5.2); p = 0.02; declaring rather good 4.5 ± 1.0, median = 4.6 (3.8-5.2) or very good health 4.8 ± 1.1, median = 5.0 (4.2-5.6) compared to rather poor 4.1 ± 1.0, median = 4.1 (3.4-4.8) and poor health 3.6 ± 1.4, median = 3.1 (2.6-4.4); p = 0.0006; rating their physical condition moderately 4.7 ± 1.1, median = 4.8 (4.0-5.6) or highly 4.9 ± 1.0, median = 5.0 (4.3-5.4) compared to rating their fitness low 4.2 ± 0.9, median = 4.2 (3.6-4.8); p < 0.0001. Multivariate analyses confirmed a significant effect of marital status and subjective assessment of physical condition on the average level of life satisfaction. Physical activity does not differentiate the level of life satisfaction in the studied group of young women. Marital status and the subjective assessment of physical condition are factors that have a significant impact on the level of satisfaction with the life of young women. Given the beneficial effect of physical activity on the sense of satisfaction with life, which can lead to an increase in its quality, physical activity should be promoted, not only among children but also in the group of young adults.

Estimation of Leaf Nitrogen Content in Rice Using Vegetation Indices and Feature Variable Optimization with Information Fusion of Multiple-Sensor Images from UAV

LNC (leaf nitrogen content) in crops is significant for diagnosing the crop growth status and guiding fertilization decisions. Currently, UAV (unmanned aerial vehicles) remote sensing has played an important role in estimating the nitrogen nutrition of crops at the field scale. However, many existing methods of evaluating crop nitrogen based on UAV imaging techniques usually have used a single type of imagery such as RGB or multispectral images, seldom considering the usage of information fusion from different types of UAV imagery for assessing the crop nitrogen status. In this study, GS (Gram–Schmidt Pan Sharpening) was utilized to fuse images from two sensors of digital RGB and multispectral cameras mounted on UAV, and the specific bands of the multispectral cameras are blue, green, red, rededge and NIR. The color space transformation method, HSV (Hue-Saturation-Value), was used to separate soil background noise from crops due to the high spatial resolution of UAV images. Two methods of optimizing feature variables, the Successive Projection Algorithm (SPA) and the Competitive Adaptive Reweighted Sampling method (CARS), combined with two regularization regression algorithms, LASSO and RIDGE, were adopted to estimate the LNC, compared to the commonly used Random Forest algorithm. The results showed that: (1) the accuracy of LNC estimation using the fusion image is improved distinctly by a comparison to the original multispectral image; (2) the denoised images performed better than the original multispectral images in evaluating LNC in rice; (3) the RIDGE-SPA combined method, using SPA to select the MCARI, SAVI and OSAVI, had the best performance for LNC in rice, with an R2 of 0.76 and an RMSE of 10.33%. It can be demonstrated that the information fusion of multiple-sensor imagery from UAV coupling with the methods of optimizing feature variables can estimate the rice LNC more effectively, which can also provide a reference for guiding the decision making of fertilization in rice fields.

Decoding Depression Severity From Intracranial Neural Activity

BackgroundDisorders of mood and cognition are prevalent, disabling, and notoriously difficult to treat. Fueling this challenge in treatment is a significant gap in our understanding of their neurophysiological basis. MethodsWe recorded high-density neural activity from intracranial electrodes implanted in depression-relevant prefrontal cortical regions in 3 human subjects with severe depression. Neural recordings were labeled with depression severity scores across a wide dynamic range using an adaptive assessment that allowed sampling with a temporal frequency greater than that possible with typical rating scales. We modeled these data using regularized regression techniques with region selection to decode depression severity from the prefrontal recordings. ResultsAcross prefrontal regions, we found that reduced depression severity is associated with decreased low-frequency neural activity and increased high-frequency activity. When constraining our model to decode using a single region, spectral changes in the anterior cingulate cortex best predicted depression severity in all 3 subjects. Relaxing this constraint revealed unique, individual-specific sets of spatiospectral features predictive of symptom severity, reflecting the heterogeneous nature of depression. ConclusionsThe ability to decode depression severity from neural activity increases our fundamental understanding of how depression manifests in the human brain and provides a target neural signature for personalized neuromodulation therapies.

Factors Associated With False-Positive Recalls in Mammography Screening.

We aimed to identify factors associated with false-positive recalls in mammography screening compared with women who were not recalled and those who received true-positive recalls. We included 29,129 women, aged 40 to 74 years, who participated in the Karolinska Mammography Project for Risk Prediction of Breast Cancer (KARMA) between 2011 and 2013 with follow-up until the end of 2017. Nonmammographic factors were collected from questionnaires, mammographic factors were generated from mammograms, and genotypes were determined using the OncoArray or an Illumina custom array. By the use of conditional and regular logistic regression models, we investigated the association between breast cancer risk factors and risk models and false-positive recalls. Women with a history of benign breast disease, high breast density, masses, microcalcifications, high Tyrer-Cuzick 10-year risk scores, KARMA 2-year risk scores, and polygenic risk scores were more likely to have mammography recalls, including both false-positive and true-positive recalls. Further analyses restricted to women who were recalled found that women with a history of benign breast disease and dense breasts had a similar risk of having false-positive and true-positive recalls, whereas women with masses, microcalcifications, high Tyrer-Cuzick 10-year risk scores, KARMA 2-year risk scores, and polygenic risk scores were more likely to have true-positive recalls than false-positive recalls. We found that risk factors associated with false-positive recalls were also likely, or even more likely, to be associated with true-positive recalls in mammography screening.

Association Between Cannabis and Violence in Community-Dwelling Patients With Severe Mental Disorders: A Cross-sectional Study Using Machine Learning.

The objective of this cross-sectional study was to identify cannabis-related features and other characteristics predictive of violence using a data-driven approach in patients with severe mental disorders (SMDs). A Least Absolute Shrinkage and Selection Operator regularization regression model was used on the database consisting of 97 patients with SMD who completed questionnaires measuring substance use and violence. Cannabis use, particularly related to patients' decision to consume or time spent using, was a key predictor associated with violence. Other patterns of substance use and personality traits were identified as strong predictors. Regular patterns of cannabis use and interpersonal issues related to cannabis/stimulant abuse were inversely correlated to violence. This study identified the effect of several predictors correlated to violence in patients with SMD using a regularization regression model. Findings open the door to better identify the profiles of patients that may be more susceptible to perpetrate violent behaviors.

On inference in high-dimensional regression

Abstract This paper develops an approach to inference in a linear regression model when the number of potential explanatory variables is larger than the sample size. The approach treats each regression coefficient in turn as the interest parameter, the remaining coefficients being nuisance parameters, and seeks an optimal interest-respecting transformation, inducing sparsity on the relevant blocks of the notional Fisher information matrix. The induced sparsity is exploited through a marginal least-squares analysis for each variable, as in a factorial experiment, thereby avoiding penalization. One parameterization of the problem is found to be particularly convenient, both computationally and mathematically. In particular, it permits an analytic solution to the optimal transformation problem, facilitating theoretical analysis and comparison to other work. In contrast to regularized regression, such as the lasso and its extensions, neither adjustment for selection nor rescaling of the explanatory variables is needed, ensuring the physical interpretation of regression coefficients is retained. Recommended usage is within a broader set of inferential statements, so as to reflect uncertainty over the model as well as over the parameters. The considerations involved in extending the work to other regression models are briefly discussed.