Imbalanced classification has drawn considerable attention in the statistics and machine learning literature. Typically, traditional classification methods often perform poorly when a severely skewed ...class distribution is observed, not to mention under a high‐dimensional longitudinal data structure. Given the ubiquity of big data in modern health research, it is expected that imbalanced classification in disease diagnosis may encounter an additional level of difficulty that is imposed by such a complex data structure. In this article, we propose a nonparametric classification approach for imbalanced data in longitudinal and high‐dimensional settings. Technically, the functional principal component analysis is first applied for feature extraction under the longitudinal structure. The univariate exponential loss function coupled with group LASSO penalty is then adopted into the classification procedure in high‐dimensional settings. Along with a good improvement in imbalanced classification, our approach provides a meaningful feature selection for interpretation while enjoying a remarkably lower computational complexity. The proposed method is illustrated on the real data application of Alzheimer's disease early detection and its empirical performance in finite sample size is extensively evaluated by simulations.
In many applications of hierarchical models, there is often interest in evaluating the inherent heterogeneity in view of observed data. When the underlying hypothesis involves parameters resting on ...the boundary of their support space such as variances and mixture proportions, it is a usual practice to entertain testing procedures that rely on common heterogeneity assumptions. Such procedures, albeit omnibus for general alternatives, may entail a substantial loss of power for specific alternatives such as heterogeneity varying with covariates. We introduce a novel and flexible approach that uses covariate information to improve the power to detect heterogeneity, without imposing unnecessary restrictions. With continuous covariates, the approach does not impose a regression model relating heterogeneity parameters to covariates or rely on arbitrary discretizations. Instead, a scanning approach requiring continuous dichotomizations of the covariates is proposed. Empirical processes resulting from these dichotomizations are then used to construct the test statistics, with limiting null distributions shown to be functionals of tight random processes. We illustrate our proposals and results on a popular class of two-component mixture models, followed by simulation studies and applications to two real datasets in cancer and caries research.
Objective: Substance use is a public health concern and cross-sectional studies have found that impulsivity and drinking motives influence substance use in emerging adults. Despite these findings, ...longitudinal studies with nuanced measures of impulsivity and drinking motives are needed. Participants: The current study investigated the three-year relationship between impulsivity-related traits, drinking motives, sex, and drinking outcomes in a sample of 509 college students (47.47% male; 81% White). Methods: The effects of impulsivity traits and drinking motives on problematic drinking outcomes were evaluated using linear mixed effects models. Results: The results confirmed the hypothesized relationship between traits of impulsivity, drinking motives, and alcohol outcomes over time. Further, sex significantly interacted with drinking motives longitudinally in its relationship with alcohol use outcomes. Conclusions: These results indicate that intervention efforts may need to be tailored to specific individual attributes to target direct correlates of alcohol use behavior to increase effectiveness.
Summary
In many applications of two‐component mixture models such as the popular zero‐inflated model for discrete‐valued data, it is customary for the data analyst to evaluate the inherent ...heterogeneity in view of observed data. To this end, the score test, acclaimed for its simplicity, is routinely performed. It has long been recognised that this test may behave erratically under model misspecification, but the implications of this behaviour remain poorly understood for popular two‐component mixture models. For the special case of zero‐inflated count models, we use data simulations and theoretical arguments to evaluate this behaviour and discuss its implications in settings where the working model is restrictive with regard to the true data‐generating mechanism. We enrich this discussion with an analysis of count data in HIV research, where a one‐component model is shown to fit the data reasonably well despite apparent extra zeros. These results suggest that a rejection of homogeneity does not imply that the underlying mixture model is appropriate. Rather, such a rejection simply implies that the mixture model should be carefully interpreted in the light of potential model misspecifications, and further evaluated against other competing models.
Accurate glioma subtype classification is critical for the treatment management of patients with brain tumors. Developing an automatically computer-aided algorithm for glioma subtype classification ...is challenging due to many factors. One of the difficulties is the label constraint. Specifically, each case is simply labeled the glioma subtype without precise annotations of lesion regions information. In this paper, we propose a novel hybrid fully convolutional neural network (CNN)-based method for glioma subtype classification using both whole slide imaging (WSI) and multiparametric magnetic resonance imagings (mpMRIs). It is comprised of two methods: a WSI-based method and a mpMRIs-based method. For the WSI-based method, we categorize the glioma subtype using a 2D CNN on WSIs. To overcome the label constraint issue, we extract the truly representative patches for the glioma subtype classification in a weakly supervised fashion. For the mpMRIs-based method, we develop a 3D CNN-based method by analyzing the mpMRIs. The mpMRIs-based method consists of brain tumor segmentation and classification. Finally, to enhance the robustness of the predictions, we fuse the WSI-based and mpMRIs-based results guided by a confidence index. The experimental results on the validation dataset in the competition of CPM-RadPath 2020 show the comprehensive judgments from both two modalities can achieve better performance than the ones by solely using WSI or mpMRIs. Furthermore, our result using the proposed method ranks the third place in the CPM-RadPath 2020 in the testing phase. The proposed method demonstrates a competitive performance, which is creditable to the success of weakly supervised approach and the strategy of label agreement from multi-modality data.
This comparative effectiveness trial examined the effects of a behavior change intervention supplemented by a general or specific exercise recommendation on physical activity among postpartum ...mothers. Participants (N = 49) attended three workshop sessions that provided the exercise recommendation and taught self-regulatory skills. Physical activity, self-efficacy, planning, and barriers were assessed at baseline, post-intervention, and 6-month follow-up. Self-reported physical activity increased significantly in both groups (p < .001), but the increase was larger in the general condition (p = .03). Both groups reported increased planning and decreased barriers. Postpartum mothers may benefit from interventions that teach strategies for overcoming barriers while allowing them to choose preferred activities.
Falling is a major cause of personal injury and accidental death worldwide, in particular for the elderly. For aged care, a falling alarm system is highly demanded so that medical aid can be obtained ...immediately when the fall accidents happen. Previous studies on fall detection lacked practical considerations to deal with real-world situations, including the camera's mounting angle, lighting differences between day and night, and the privacy protection for users. In our experiments, IR-depth images and thermal images were used as the input source for fall detection; as a result, detailed facial information is not captured by the system for privacy reasons, and it is invariant to the lighting conditions. Due to the different occurrence rates between fall accidents and other normal activities, supervised learning approaches may suffer from the problem of data imbalance in the training phase. Accordingly, in this study, anomaly detection is performed using unsupervised learning approaches so that the models were trained only with the normal cases while the fall accident was defined as an anomaly event. The proposed system takes sequential frames as the inputs to predict future frames based on a GAN structure, and it provides (1) multi-subject detection, (2) real-time fall detection triggered by motion, (3) a solution to the situation that subjects were occluded after falling, and (4) a denoising scheme for depth images. The experimental results show that the proposed system achieves the state-of-the-art performance and copes with the real-world cases successfully.
Focal therapy (FT) has been gaining popularity as a treatment option for localized intermediate-risk prostate cancer (PCa) due to the associated lower morbidity compared to whole-gland treatment. ...However, there is an increased risk of local cancer recurrence requiring subsequent treatment in a small proportion of patients.
To conduct a systematic review and meta-analysis to better describe and analyze patient postoperative, oncologic, and functional outcomes for those who underwent salvage radical prostatectomy (sRP) to manage their primary FT failure.
A systematic review was completed using three databases (PubMed, Embase, and CINAHL) from October to December 2021 to identify data on outcomes in patients who received sRP for cancer recurrence after prior focal treatment.
12 articles (482 patients) were included. Median time to sRP was 24 months. Median follow-up time was 27 months. A meta-analysis revealed a postoperative complication rate of 15% (95% CI: 0.09, 0.24), with 4.6% meeting criteria for a major complication Clavien (CG) grade ≥3. Severe GU toxicity was seen in 3.6% of the patients, and no patients had severe GI toxicity. Positive surgical margins (PSM) were found in 27% (95% CI: 0.19, 0.37). Biochemical recurrence (BCR) after sRP occurred in 23% (95% CI: 0.17, 0.30), indicating a BCR-free probability of 77% at 2 years. Continence (pad-free) and potency (ability to have penetrative sex) were maintained in 67% (95% CI: 0.53, 0.78) and 37% (95% CI: 0.18, 0.62) at 12 months, respectively.
Our evidence shows acceptable complication rates and oncologic outcomes; however, with suboptimal functional outcomes for patients undergoing sRP for recurrent PCa after prior FT. Inferior outcomes were observed for salvage treatment compared to primary radical prostatectomy (pRP). More high-quality studies are needed to better characterize outcomes after this sequence of PCa treatments.
We looked at treatment outcomes and toxicity for men treated with sRP for prior FT failure. We conclude that these patients will have significant detriment to genitourinary function, with outcomes being worse than those for pRP patients.
Zero-inflated regression models have emerged as a popular tool within the parametric framework to characterize count data with excess zeros. Despite their increasing popularity, much of the ...literature on real applications of these models has centered around the latent class formulation where the mean response of the so-called at-risk or susceptible population and the susceptibility probability are both related to covariates. While this formulation in some instances provides an interesting representation of the data, it often fails to produce easily interprétable covariate effects on the overall mean response. In this article, we propose two approaches that circumvent this limitation. The first approach consists of estimating the effect of covariates on the overall mean from the assumed latent class models, while the second approach formulates a model that directly relates the overall mean to covariates. Our results are illustrated by extensive numerical simulations and an application to an oral health study on low income African-American children, where the overall mean model is used to evaluate the effect of sugar consumption on caries indices.
A cesarean section pregnancy (CSP) indicated the gestational sac (GS) implanted in the previous cesarean scar. The clinical manifestations of CSP present a wide range of variations, and the optimal ...management is yet to be defined. We retrospectively enrolled 109 patients with the diagnosis of CSP from our department and categorized them into four grades based on the ultrasound presentation. Grade I CSP indicated the GS embedded in less than one-half thickness of the lower anterior corpus; and grade II CSP represented the GS extended to more than one-half thickness of overlying myometrium. Grade III CSP implied the GS bulged out of the cesarean scar; and grade IV CSP denoted that GS became an amorphous tumor with rich vascularity at the cesarean scar. Seventy-eight women received surgery, and the complication rate was 14.1% (11/78). Linear regression analysis demonstrated a significant association between the invasiveness of the surgery and their ultrasound gradings. The mainstream operation for grade I CSP was transcervical resection, while the majority of grade III and IV patients required hysterotomy or hysterectomy. Another 31 women received chemotherapy with methotrexate as their initial treatment. The success rate for chemotherapy was 61.3%; the remaining patients required further surgery due to persistent CSP or heavy bleeding during or after chemotherapy. Fifteen patients (48.3%) receiving chemotherapy suffered from complications (mostly bleeding). Among them, 7 (22.6%) patients experienced bleeding of more than 1,000 mL, and 9 (29.0%) of these 31 patients required blood transfusions. Our novel ultrasound grading system for CSP may help to communicate between physicians, and determine the optimal surgical strategy. Chemotherapy with methotrexate for CSP is not satisfactory and is associated with a higher rate of complications.
PDF
