This paper studies the generalized functional linear model with a scalar response and a functional predictor. The response given the functional predictor is assumed to come from the distribution of an exponential family. A penalized likelihood approach is proposed to estimate the unknown intercept and coefficient function in the model. Inference tools such as point-wise confidence intervals of the coefficient function and the prediction intervals are derived. The minimax rate of convergence for the error in predicting the mean response is established. It is shown that the penalized likelihood estimator attains the optimal rate of convergence. Our simulations demonstrate a competitive performance against the existing approach. The method is further illustrated by an application of using the DTI tractography to distinguish corpus callosum tracts with multiple sclerosis from normal tracts.
Smart manufacturing, which integrates a multi-sensing system with physical manufacturing processes, has been widely adopted in the industry to support online and real-time decision making to improve manufacturing quality. A multi-sensing system for each specific manufacturing process can efficiently collect the in situ process variables from different sensor modalities to reflect the process variations in real-time. However, in practice, we usually do not have enough budget to equip too many sensors in each manufacturing process due to the cost consideration. Moreover, it is also important to better interpret the relationship between the sensing modalities and the quality variables based on the model. Therefore, it is necessary to model the quality-process relationship by selecting the most relevant sensor modalities with the specific quality measurement from the multi-modal sensing system in smart manufacturing. In this research, we adopted the concept of best subset variable selection and proposed a new model called Multi-mOdal beSt Subset modeling (MOSS). The proposed MOSS can effectively select the important sensor modalities and improve the modeling accuracy in quality-process modeling via functional norms that characterize the overall effects of individual modalities. The significance of sensor modalities can be used to determine the sensor placement strategy in smart manufacturing. Moreover, the selected modalities can better interpret the quality-process model by identifying the most correlated root cause of quality variations. The merits of the proposed model are illustrated by both simulations and a real case study in an additive manufacturing (i.e., fused deposition modeling) process.
Gap time hazard estimation is of particular interest in recurrent event data. This article proposes a fully nonparametric approach for estimating the gap time hazard. Smoothing spline analysis of variance (ANOVA) decompositions are used to model the log gap time hazard as a joint function of gap time and covariates, and general frailty is introduced to account for between-subject heterogeneity and within-subject correlation. We estimate the nonparametric gap time hazard function and parameters in the frailty distribution using a combination of the Newton-Raphson procedure, the stochastic approximation algorithm (SAA), and the Markov chain Monte Carlo (MCMC) method. The convergence of the algorithm is guaranteed by decreasing the step size of parameter update and/or increasing the MCMC sample size along iterations. Model selection procedure is also developed to identify negligible components in a functional ANOVA decomposition of the log gap time hazard. We evaluate the proposed methods with simulation studies and illustrate its use through the analysis of bladder tumor data.
Abstract Disaster exposure is often followed by acute illness and injuries requiring hospital admission in the weeks after the disaster. It is not known whether disaster exposure is associated with hospitalization in the years after the disaster. We examined the extent to which disaster exposure is associated with hospitalization two years after Hurricane Sandy. The analyses fill a gap in our understanding of long-term physical health consequences of disaster exposure by identifying older adults at greatest risk for hospitalization two years after disaster exposure. Older adults (n=909) who participated in a longitudinal panel study provided data before and after Hurricane Sandy. These data were linked with Medicare inpatient files to assess the impact of Hurricane Sandy on hospital admissions after the post-hurricane interview. Those who reported experiencing a lot of fear and distress in the midst of Hurricane Sandy were at an increased risk of being hospitalized in the second or third years after the hurricane [Hazard Ratio=1.81 (1.15 – 2.85)]. Findings held after controlling for pre-hurricane demographics, social risks, chronic conditions, and decline in physical functioning after the hurricane. These findings are the first to show that disaster exposure increases risk for hospital admissions two years after a disaster, and that older adults’ appraisal of their emotional distress during the disaster has prognostic significance that is not explained by known risks for hospital admissions. The findings suggest that interventions during the storm and after the storm, may reduce long-term health consequences of disaster exposure among older adults.
Background The pathophysiology of delirium is incompletely understood, including what molecular pathways are involved in brain vulnerability to delirium. This study examined whether preoperative plasma neurodegeneration markers were elevated in patients who subsequently developed postoperative delirium through a retrospective case-control study. Methods Inclusion criteria were patients of 65 yr of age or older, undergoing elective noncardiac surgery with a hospital stay of 2 days or more. Concentrations of preoperative plasma P-Tau181, neurofilament light chain, amyloid β1-42 (Aβ42), and glial fibrillary acidic protein were measured with a digital immunoassay platform. The primary outcome was postoperative delirium measured by the Confusion Assessment Method. The study included propensity score matching by age and sex with nearest neighbor, such that each patient in the delirium group was matched by age and sex with a patient in the no-delirium group. Results The initial cohort consists of 189 patients with no delirium and 102 patients who developed postoperative delirium. Of 291 patients aged 72.5 ± 5.8 yr, 50.5% were women, and 102 (35%) developed postoperative delirium. The final cohort in the analysis consisted of a no-delirium group (n = 102) and a delirium group (n = 102) matched by age and sex using the propensity score method. Of the four biomarkers assayed, the median value for neurofilament light chain was 32.05 pg/ml for the delirium group versus 23.7 pg/ml in the no-delirium group. The distribution of biomarker values significantly differed between the delirium and no-delirium groups (P = 0.02 by the Kolmogorov–Smirnov test) with the largest cumulative probability difference appearing at the biomarker value of 32.05 pg/ml. Conclusions These results suggest that patients who subsequently developed delirium are more likely to be experiencing clinically silent neurodegenerative changes before surgery, reflected by changes in plasma neurofilament light chain biomarker concentrations, which may identify individuals with a preoperative vulnerability to subsequent cognitive decline. Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New
The accurate measurement of security metrics is a critical research problem because an improper or inaccurate measurement process can ruin the usefulness of the metrics, no matter how well they are defined. This is a highly challenging problem particularly when the ground truth is unknown or noisy. In contrast to the well perceived importance of defining security metrics, the measurement of security metrics has been little understood in the literature. In this paper, we measure five malware detection metrics in the {\em absence} of ground truth, which is a realistic setting that imposes many technical challenges. The ultimate goal is to develop principled, automated methods for measuring these metrics at the maximum accuracy possible. The problem naturally calls for investigations into statistical estimators by casting the measurement problem as a {\em statistical estimation} problem. We propose statistical estimators for these five malware detection metrics. By investigating the statistical properties of these estimators, we are able to characterize when the estimators are accurate, and what adjustments can be made to improve them under what circumstances. We use synthetic data with known ground truth to validate these statistical estimators. Then, we employ these estimators to measure five metrics with respect to a large dataset collected from VirusTotal. We believe our study touches upon a vital problem that has not been paid due attention and will inspire many future investigations.
Abstract Background and Objectives Among community-living older adults who have limitations in completing Activities of Daily Living (ADLs), unmet need occurs when they cannot complete an ADL task because no one was available to help. Prior research described correlates of existing unmet needs but did not consider which older adults are at risk for new onset of unmet needs. This study assessed health characteristics that increased risk for new onset of unmet needs within a year and subsequent health outcomes. Research Design and Methods Data are from the 2011-2019 annual interviews of the National Health and Aging Trends Study. For each pair of two consecutive annual interviews, we determined whether new onset of unmet needs occurred between the first and second consecutive interviews. Mixed effects logistic regression models were computed to assess risks for new onset of unmet need across 14,890 paired observations from persons who needed help with mobility tasks and 12,514 paired observations from persons who needed help with self-care tasks. Results Although demographic characteristics and chronic conditions had modest associations with new onset of unmet need, hospitalization between the two consecutive interviews was associated with a two-fold increase in risk for new onset of unmet need. New onset of unmet need was associated with hospitalization, nursing home placement, and death in the year following the two consecutive annual interviews. Discussion and Implications The findings inform the need for frequent assessments of ADL care needs with the goal of preventing new onset of unmet needs, especially after hospitalization.
Bladder cancer (BCA) is relatively common and potentially recurrent/progressive disease. It is also costly to detect, treat, and control. Definitive diagnosis is made by examination of urine sediment, imaging, direct visualization (cystoscopy), and invasive biopsy of suspect bladder lesions. There are currently no widely-used BCA-specific biomarker urine screening tests for early BCA or for following patients during/after therapy. Urine metabolomic screening for biomarkers is costly and generally unavailable for clinical use. In response, we developed Raman spectroscopy-based chemometric urinalysis (Rametrix™) as a direct liquid urine screening method for detecting complex molecular signatures in urine associated with BCA and other genitourinary tract pathologies. In particular, the RametrixTM screen used principal components (PCs) of urine Raman spectra to build discriminant analysis models that indicate the presence/absence of disease. The number of PCs included was varied, and all models were cross-validated by leave-one-out analysis. In Study 1 reported here, we tested the Rametrix™ screen using urine specimens from 56 consented patients from a urology clinic. This proof-of-concept study contained 17 urine specimens with active BCA (BCA-positive), 32 urine specimens from patients with other genitourinary tract pathologies, seven specimens from healthy patients, and the urinalysis control SurineTM. Using a model built with 22 PCs, BCA was detected with 80.4% accuracy, 82.4% sensitivity, 79.5% specificity, 63.6% positive predictive value (PPV), and 91.2% negative predictive value (NPV). Based on the number of PCs included, we found the RametrixTM screen could be fine-tuned for either high sensitivity or specificity. In other studies reported here, RametrixTM was also able to differentiate between urine specimens from patients with BCA and other genitourinary pathologies and those obtained from patients with end-stage kidney disease (ESKD). While larger studies are needed to improve RametrixTM models and demonstrate clinical relevance, this study demonstrates the ability of the RametrixTM screen to differentiate urine of BCA-positive patients. Molecular signature variances in the urine metabolome of BCA patients included changes in: phosphatidylinositol, nucleic acids, protein (particularly collagen), aromatic amino acids, and carotenoids.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)