CW_ICA: an efficient dimensionality determination method for independent component analysis.

Independent component analysis (ICA) is a widely used blind source separation method for signal pre-processing. The determination of the number of independent components (ICs) is crucial for achieving optimal performance, as an incorrect choice can result in either under-decomposition or over-decomposition. In this study, we propose a robust method to automatically determine the optimal number of ICs, named the column-wise independent component analysis (CW_ICA). CW_ICA divides the mixed signals into two blocks and applies ICA separately to each block. A quantitative measure, derived from the rank-based correlation matrix computed from the ICs of the two blocks, is utilized to determine the optimal number of ICs. The proposed method is validated and compared with the existing determination methods using simulation and scalp EEG data. The results demonstrate that CW_ICA is a reliable and robust approach for determining the optimal number of ICs. It offers computational efficiency and can be seamlessly integrated with different ICA methods.

Understanding post-surgical decline in left ventricular function in primary mitral regurgitation using regression and machine learning models.

Background: Class I echocardiographic guidelines in primary mitral regurgitation (PMR) risks left ventricular ejection fraction (LVEF) < 50% after mitral valve surgery even with pre-surgical LVEF > 60%. There are no models predicting LVEF < 50% after surgery in the complex interplay of increased preload and facilitated ejection in PMR using cardiac magnetic resonance (CMR). Objective: Use regression and machine learning models to identify a combination of CMR LV remodeling and function parameters that predict LVEF < 50% after mitral valve surgery. Methods: CMR with tissue tagging was performed in 51 pre-surgery PMR patients (median CMR LVEF 64%), 49 asymptomatic (median CMR LVEF 63%), and age-matched controls (median CMR LVEF 64%). To predict post-surgery LVEF < 50%, least absolute shrinkage and selection operator (LASSO), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM) were developed and validated in pre-surgery PMR patients. Recursive feature elimination and LASSO reduced the number of features and model complexity. Data was split and tested 100 times and models were evaluated via stratified cross validation to avoid overfitting. The final RF model was tested in asymptomatic PMR patients to predict post-surgical LVEF < 50% if they had gone to mitral valve surgery. Results: Thirteen pre-surgery PMR had LVEF < 50% after mitral valve surgery. In addition to LVEF (P = 0.005) and LVESD (P = 0.13), LV sphericity index (P = 0.047) and LV mid systolic circumferential strain rate (P = 0.024) were predictors of post-surgery LVEF < 50%. Using these four parameters, logistic regression achieved 77.92% classification accuracy while RF improved the accuracy to 86.17%. This final RF model was applied to asymptomatic PMR and predicted 14 (28.57%) out of 49 would have post-surgery LVEF < 50% if they had mitral valve surgery. Conclusions: These preliminary findings call for a longitudinal study to determine whether LV sphericity index and circumferential strain rate, or other combination of parameters, accurately predict post-surgical LVEF in PMR.

Classification of EEG signals: An interpretable approach using functional data analysis.

Electroencephalography (EEG) is a noninvasive method to record electrical activity of the brain. The EEG data is continuous flow of voltages, in this paper, we consider them as functional data, and propose a three-stage algorithm based on functional data analysis, with the advantage of interpretability. Specifically, the time and frequency information are extracted by wavelet transform in the first stage. Then, functional testing is utilized to select EEG channels and frequencies that show significant differences for different human behaviors. In the third stage, we propose to use penalized multiple functional logistic regression to interpretably classify human behaviors. With simulation and a scalp EEG data as validation set, we show that the proposed three-stage algorithm provides an interpretable classification of the scalp EEG signals.

Evaluation of methods for adjusting population stratification in genome-wide association studies: Standard versus categorical principal component analysis.

Unaccounted population stratification can lead to false-positive findings and can mask the true association signals in identification of disease-related genetic variants. The computational simplicity of principal component analysis (PCA) makes it a widely used method for population stratification adjustment. However, given that genotype data are generally represented by numerical values 0, 1, and 2, corresponding to the number of minor alleles, it is more reasonable to consider genotype data as categorical data. Because PCA is inherently only suitable for continuous variables, it is not appropriate to directly apply PCA on genotype data. Second, although common variants have been extensively studied, little is known about the stratification of rare variants and its impact on association tests. Over the last decade, there has been a shift in the genome-wide association studies toward studying low-frequency (minor allele frequency [MAF] between 0.01 and 0.05) and rare (MAF less than 0.01) variants, which are now widely reputed as complex trait determinants. The fact that rare variants are not stratified in the same way as common variants necessitates the development of statistical methods that can capture stratification patterns for low-frequency and rare variants. To address these limitations, we investigate performances of generalized PCA and similarity-matrix-based PCA methods to detect underlying structures for rare and common variants. We demonstrate, through simulated and real datasets, that a special case of generalized PCA (i.e., logistic PCA) is able to adjust for population stratification in rare variants much more effectively than standard PCA while their performances are comparable for common variants.

Prevention of Trastuzumab and Anthracycline-induced Cardiotoxicity Using Angiotensin-converting Enzyme Inhibitors or ß-blockers in Older Adults With Breast Cancer.

PURPOSE: Although clinical trials have provided some data on the benefit of angiotensin-converting enzyme inhibitors (ACEIs) or ß-blockers (BBs) in patients with chemotherapy-induced cardiotoxicity, evidence of ACEIs/BBs on prevention of trastuzumab and/or anthracycline-induced cardiotoxicity outside trials is limited. MATERIALS AND METHODS: A cohort study of 142,990 women (66 y and above) newly diagnosed with breast cancer from 2001 to 2009 was conducted using the Surveillance, Epidemiology, and End Results-Medicare-linked database. The ACEI/BB exposure was defined as filled prescription(s) before or after the initiation of trastuzumab/anthracyclines. The nonexposed group was defined as those who had never been prescribed ACEIs/BBs. Cumulative rates of cardiotoxicity and all-cause mortality were estimated and marginal structural Cox models were used to determine factors associated with cardiotoxicity and all-cause mortality adjusting for baseline covariates and use of chemotherapy. All statistical tests were 2 sided. RESULTS: The final sample included 6542 women. Adjusted hazard ratio for cardiotoxicity and all-cause mortality for the ACEI/BB exposed group were 0.77 (95% confidence interval, 0.62-0.95) and 0.79 (95% confidence interval, 0.70-0.90) compared with the nonexposed group, respectively. Starting ACEIs/BBs≤6 months after the initiation of trastuzumab/anthracyclines and having exposed duration≥6 months were also associated with decreased risk of cardiotoxicity and all-cause mortality. Baseline characteristics, including age, non-Hispanic black, advanced cancer, region, comorbidity, preexisting cardiovascular conditions, lower socioeconomic status, and concomitant treatment were significantly associated with an elevated risk of all-cause mortality and/or cardiotoxicity (all P<0.05). CONCLUSIONS: ACEIs/BBs show favorable effects on preventing cardiotoxicity and improving survival in female breast cancer patients undergoing trastuzumab/anthracycline treatment.

Chemometric modeling of thermogravimetric data for the compositional analysis of forest biomass.

The objective of this study was to investigated the use of chemometric modeling of thermogravimetric (TG) data as an alternative approach to estimate the chemical and proximate (i.e. volatile matter, fixed carbon and ash contents) composition of lignocellulosic biomass. Since these properties affect the conversion pathway, processing costs, yield and / or quality of products, a capability to rapidly determine these for biomass feedstock entering the process stream will be useful in the success and efficiency of bioconversion technologies. The 38-minute long methodology developed in this study enabled the simultaneous prediction of both the chemical and proximate properties of forest-derived biomass from the same TG data. Conventionally, two separate experiments had to be conducted to obtain such information. In addition, the chemometric models constructed with normalized TG data outperformed models developed via the traditional deconvolution of TG data. PLS and PCR models were especially robust in predicting the volatile matter (R2-0.92; RPD- 3.58) and lignin (R2-0.82; RPD- 2.40) contents of the biomass. The application of chemometrics to TG data also made it possible to predict some monomeric sugars in this study. Elucidation of PC loadings obtained from chemometric models also provided some insights into the thermal decomposition behavior of the chemical constituents of lignocellulosic biomass. For instance, similar loadings were noted for volatile matter and cellulose, and for fixed carbon and lignin. The findings indicate that common latent variables are shared between these chemical and thermal reactivity properties. Results from this study buttresses literature that have reported that the less thermally stable polysaccharides are responsible for the yield of volatiles whereas the more recalcitrant lignin with its higher percentage of elementary carbon contributes to the yield of fixed carbon.

Identifying Plant Part Composition of Forest Logging Residue Using Infrared Spectral Data and Linear Discriminant Analysis.

As new markets, technologies and economies evolve in the low carbon bioeconomy, forest logging residue, a largely untapped renewable resource will play a vital role. The feedstock can however be variable depending on plant species and plant part component. This heterogeneity can influence the physical, chemical and thermochemical properties of the material, and thus the final yield and quality of products. Although it is challenging to control compositional variability of a batch of feedstock, it is feasible to monitor this heterogeneity and make the necessary changes in process parameters. Such a system will be a first step towards optimization, quality assurance and cost-effectiveness of processes in the emerging biofuel/chemical industry. The objective of this study was therefore to qualitatively classify forest logging residue made up of different plant parts using both near infrared spectroscopy (NIRS) and Fourier transform infrared spectroscopy (FTIRS) together with linear discriminant analysis (LDA). Forest logging residue harvested from several Pinus taeda (loblolly pine) plantations in Alabama, USA, were classified into three plant part components: clean wood, wood and bark and slash (i.e., limbs and foliage). Five-fold cross-validated linear discriminant functions had classification accuracies of over 96% for both NIRS and FTIRS based models. An extra factor/principal component (PC) was however needed to achieve this in FTIRS modeling. Analysis of factor loadings of both NIR and FTIR spectra showed that, the statistically different amount of cellulose in the three plant part components of logging residue contributed to their initial separation. This study demonstrated that NIR or FTIR spectroscopy coupled with PCA and LDA has the potential to be used as a high throughput tool in classifying the plant part makeup of a batch of forest logging residue feedstock. Thus, NIR/FTIR could be employed as a tool to rapidly probe/monitor the variability of forest biomass so that the appropriate online adjustments to parameters can be made in time to ensure process optimization and product quality.

Treatment patterns among breast cancer patients in the United States using two national surveys on visits to physicians' offices and hospital outpatient departments.

BACKGROUND: Despite the availability of previous studies, little research has examined how types of anti-neoplastic agents prescribed differ among various populations and health care characteristics in ambulatory settings, which is a primary method of providing care in the U.S. Understanding treatment patterns can help identify possible disparities and guide practice or policy change. OBJECTIVES: To characterize patterns of anti-neoplastic agents prescribed to breast cancer patients in ambulatory settings and identify factors associated with receipt of treatment. METHODS: A cross-sectional analysis using the National Ambulatory Medical Care Survey data in 2006-2010 was conducted. Breast cancer treatments were categorized by class and further grouped as chemotherapy, hormone, and targeted therapy. A visit-level descriptive analysis using visit sampling weights estimated national prescribing trends (n = 2746 breast cancer visits, weighted n = 28,920,657). Multiple logistic regression analyses identified factors associated with anti-neoplastic agent used. RESULTS: The proportion of visits in which anti-neoplastic agent(s) was/were documented remained stable from 2006 to 2010 (20.47% vs. 24.56%; P > 0.05). Hormones were commonly prescribed (29.69%) followed by mitotic inhibitors (9.86%) and human epidermal growth factor receptor2 inhibitors (5.34%). Patients with distant stage were more likely than patients with in-situ stage to receive treatment (Adjusted Odds Ratio [OR] = 2.79; 95% CI, 1.04-7.77), particularly chemotherapy and targeted therapy. Patients with older age, being ethnic minorities, having comorbid depression, and having U.S. Medicaid insurance were less likely to receive targeted therapy (P < 0.05). Patients with older age, having comorbid obesity and osteoporosis were less likely to receive chemotherapy, while patients seen in hospital-based settings and settings located in metropolitan areas were more likely to receive chemotherapy (P < 0.05). CONCLUSIONS: Anti-neoplastic treatment patterns differ among breast cancer patients treated in ambulatory settings. Factors predicting treatment include certain socio-demographics, cancer stages, comorbidities, metropolitan areas, and setting.

Finding multivariate outliers in fMRI time-series data.

A fundamental challenge for researchers studying the brain is to explain how distributed patterns of brain activity relate to a specific representation or computation. Multivariate techniques are therefore becoming increasingly popular for pattern localization of functional magnetic resonance imaging (fMRI) data. The increased power of these techniques can be offset by their susceptibility to multivariate outliers, a problem not directly encountered when fMRI data are analyzed in more common univariate analysis techniques. We test how two algorithms, High Dimensional Blocked Adaptive Computationally Efficient Outlier Nominators (HD BACON) and Principal Component based Outlier detection (PCOut), can detect multivariate outliers in high-dimensional fMRI data, in which the number of variables is larger than the number of observations. We show how these methods can be applied to individual, voxel time-series to identify outlying voxels within a region of interest. Finally, we compare these methods with simulated data to identify which aspects of the data each method is most sensitive to. Voxels identified by both algorithms were primarily on the edges of univariate activation clusters and near the boundaries between different tissue types. Simulation results showed the PCOut outperformed HD BACON, maintaining both high sensitivity and specificity across a wide range of outlier contamination percentages. Our results suggest that multivariate analysis of fMRI can benefit from including multivariate outlier detection as a routine data quality check prior to model fitting.

Evaluation of medication therapy management services for patients with cardiovascular disease in a self-insured employer health plan.

BACKGROUND: Cardiovascular disease (CVD) is a major cause of mortality in the United States, representing the highest total expenditures among major diseases. To improve CVD-associated outcomes, medication therapy management (MTM) services have been included in essential health benefit packages offered by various health plans. Nevertheless, the impact of such MTM services on outcomes is still unclear, especially from the perspective of the self-insured employer.  OBJECTIVES: To (a) compare economic outcomes between patients who received and those who did not receive MTM services from the self-insured employer's perspective and (b) compare clinical outcomes before and after receiving MTM services.  METHODS: This study consisted of 2 pre- and post-retrospective designs: (1) a cohort study with comparison groups and (2) a cohort study within group comparison. Patients were beneficiaries aged 19 years or older who were diagnosed with CVD conditions according to ICD-9-CM codes and continuously enrolled in a public university-sponsored insurance plan between 2008-2010. Patients were divided into MTM and non-MTM groups. The first MTM encounter was assigned as the index date for the MTM group. Match-paired patients who did not receive MTM services were randomly assigned the index date based on age category, gender, and comorbidity. Measures for pharmacy, medical, and total expenditures were obtained from medical and pharmacy claims. Paired t-tests and independent t-tests using data generated from 1000 bootstraps compared mean cost difference within and between groups. The return on investment (ROI) was calculated by dividing the average net benefit from MTM services by the average cost of MTM services. Clinical parameters, including blood pressure (BP) and body mass index (BMI), were retrieved from electronic medical records from a pharmacist-provided clinic where MTM services took place. Paired-t tests were used to compare the mean difference between baseline and endpoint values. Further, this study examined changes in the proportion of patients who achieved an individualized treatment goal for BP and BMI. The study also quantified the improvement in disease stages after the index date using the McNemar's test. Statistical analyses were performed by using SAS software version 9.2 with statistical significance level of 0.05.   RESULTS: A total of 63 patients and 62 match-paired patients were included in the MTM group and the non-MTM group, respectively. The mean cost (SD) per patient in the MTM group during the 6 months post-index period for CVD-related pharmacy, all-cause medical, and total expenditures was lower than the 6 months pre-index period by $22.0 (19.1), $79.2 (99.6), and $75.1 (136.2), respectively. In contrast, the mean cost (SD) for the non-MTM group increased during the 6 months post-index date by $10.7 (24.2), $246.4 (248.4), and $289.0 (269.5) for pharmacy, medical, and total expenditure, respectively. When comparing the 2 groups, the MTM group had statistically significantly lower costs per patient for pharmacy expenditures (difference of -31.9 ± 25.1, P less than 0.0001), medical expenditures (difference of -$325.6 ± 271.2, P less than 0.0001), and total direct expenditures (difference of -$359.3 ± 219.2, P less than 0.0001). Given the net benefit of MTM services ($359.3) and the average cost of MTM service ($134.6), the ROI was $1.67 per $1 in MTM cost. Regarding clinical outcomes, while no statistically significant differences were observed in clinical outcomes, MTM services demonstrated clinical benefits. At the post-index period, the percentage of patients who had achieved their goals increased from 55% to 70% for BP and from 13.0% to 21.7% for normal BMI compared with the pre-index period. In terms of the extent of improvement in disease stages, clinical improvements in the stages of hypertension (χ2 =12.77, P less than 0.05) as well as BMI (χ2 =6.39, P less than 0.05) at the endpoint were observed.  CONCLUSIONS: Cardiovascular-related pharmacy, all-cause medical, and total expenditures were statistically lower among beneficiaries who received MTM services compared with those who did not. In addition, MTM services had a positive ROI and demonstrated clinical significances by the increasing number of patients who achieved treatment goals and improved disease stages for hypertension and BMI.