Browsing by Author "Karas, Marta"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Adaptive empirical pattern transformation (ADEPT) with application to walking stride segmentation
    (Oxford University Press, 2021-04-10) Karas, Marta; Czkiewicz, Marcin Stra; Fadel, William; Harezlak, Jaroslaw; Crainiceanu, Ciprian M.; Urbanek, Jacek K.; Biostatistics, School of Public Health
    Quantifying gait parameters and ambulatory monitoring of changes in these parameters have become increasingly important in epidemiological and clinical studies. Using high-density accelerometry measurements, we propose adaptive empirical pattern transformation (ADEPT), a fast, scalable, and accurate method for segmentation of individual walking strides. ADEPT computes the covariance between a scaled and translated pattern function and the data, an idea similar to the continuous wavelet transform. The difference is that ADEPT uses a data-based pattern function, allows multiple pattern functions, can use other distances instead of the covariance, and the pattern function is not required to satisfy the wavelet admissibility condition. Compared to many existing approaches, ADEPT is designed to work with data collected at various body locations and is invariant to the direction of accelerometer axes relative to body orientation. The method is applied to and validated on accelerometry data collected during a equation M1-m outdoor walk of equation M2 study participants wearing accelerometers on the wrist, hip, and both ankles. Additionally, all scripts and data needed to reproduce presented results are included in supplementary material available at Biostatistics online.
  • Thumbnail Image
    Item
    Association of structural brain imaging markers with alcoholism incorporating structural connectivity information: a regularized statistical approach
    (Office of the Vice Chancellor for Research, 2016-04-08) Karas, Marta; Dzemidzic, Mario; Goñi, Joaquin; Kareken, David A.; Harezlak, Jaroslaw
    Abstract: Brain imaging studies collect multiple imaging data types, but most analyses are done for each modality separately. Statistical methods that simultaneously utilize and combine multiple data types can instead provide a more holistic view of brain function. Here we model associations between alcohol abuse phenotypes and imaging data while incorporating prior scientific knowledge. Specifically, we utilize cortical thickness and integrated rectified mean curvature measures obtained by FreeSurfer software [1] to predict the alcoholism-related phenotypes while incorporating prior information from the structural connectivity between cortical regions. The sample consisted of 148 young (21-35 years) social-to-heavy drinking male subjects from several alcoholism risk studies [2,3,4]. Structural connectivity model [5] was used to estimate the density of connections between 66 cortical regions based on Desikan-Killiany atlas [6]. We employed a functional linear model with a penalty operator to quantify the relative contributions of imaging markers obtained from high resolution structural MRI (cortical thickness and curvature) as predictors of drinking frequency and risk-relevant personality traits, while co-varying for age. Model parameters were estimated by a unified approach directly incorporating structural connectivity information into the estimation by exploiting the joint eigenproperties of the predictors and the penalty operator [7]. We found that the best predictive imaging markers of the Alcohol Use Disorders Identification Test (AUDIT) score were the average thickness of left frontal pole (-), right transverse temporal gyrus (+), left inferior parietal lobule (+), right supramarginal gyrus (-), right rostral middle frontal gyrus (+), right precentral gyrus (+), left superior parietal lobule (-), left lateral orbitofrontal cortex (+), left rostral middle frontal gyrus (+), left postcentral gyrus (+) and left supramarginal gyrus (-), where (+) denotes positive and (-) negative association. In summary, the use of structural connectivity information allowed the incorporation of different modalities in associating cortical measures and alcoholism risk.
  • Thumbnail Image
    Item
    Brain Connectivity-Informed Regularization Methods for Regression
    (Springer, 2017-12-06) Karas, Marta; Brzyski, Damian; Dzemidzic, Mario; Goñi, Joaquín; Kareken, David A.; Randolph, Timothy W.; Harezlak, Jaroslaw; Neurology, School of Medicine
    One of the challenging problems in brain imaging research is a principled incorporation of information from different imaging modalities. Frequently, each modality is analyzed separately using, for instance, dimensionality reduction techniques, which result in a loss of mutual information. We propose a novel regularization method to estimate the association between the brain structure features and a scalar outcome within the linear regression framework. Our regularization technique provides a principled approach to use external information from the structural brain connectivity and inform the estimation of the regression coefficients. Our proposal extends the classical Tikhonov regularization framework by defining a penalty term based on the structural connectivity-derived Laplacian matrix. Here, we address both theoretical and computational issues. The approach is first illustrated using simulated data and compared with other penalized regression methods. We then apply our regularization method to study the associations between the alcoholism phenotypes and brain cortical thickness using a diffusion imaging derived measure of structural connectivity. Using the proposed methodology in 148 young male subjects with a risk for alcoholism, we found a negative associations between cortical thickness and drinks per drinking day in bilateral caudal anterior cingulate cortex, left lateral OFC, and left precentral gyrus.
  • Thumbnail Image
    Item
    Connectivity‐informed adaptive regularization for generalized outcomes
    (Wiley, 2021-02) Brzyski, Damian; Karas, Marta; Ances, Beau M.; Dzemidzic, Mario; Goñi, Joaquín; Randolph, Timothy W.; Harezlak, Jaroslaw; Neurology, School of Medicine
    One of the challenging problems in neuroimaging is the principled incorporation of information from different imaging modalities. Data from each modality are frequently analyzed separately using, for instance, dimensionality reduction techniques, which result in a loss of mutual information. We propose a novel regularization method, generalized ridgified Partially Empirical Eigenvectors for Regression (griPEER), to estimate associations between the brain structure features and a scalar outcome within the generalized linear regression framework. griPEER improves the regression coefficient estimation by providing a principled approach to use external information from the structural brain connectivity. Specifically, we incorporate a penalty term, derived from the structural connectivity Laplacian matrix, in the penalized generalized linear regression. In this work, we address both theoretical and computational issues and demonstrate the robustness of our method despite incomplete information about the structural brain connectivity. In addition, we also provide a significance testing procedure for performing inference on the estimated coefficients. Finally, griPEER is evaluated both in extensive simulation studies and using clinical data to classify HIV+ and HIV− individuals.