Sportive Fashion Trend Reports: A Hybrid Style Analysis Based on Deep Learning Techniques

This study aimed to use quantitative methods and deep learning techniques to report sportive fashion trends. We collected sportive fashion images from fashion collections of the past decades and utilized the multi-label graph convolutional network (ML-GCN) model to detect and explore hybrid styles. Based on the literature review, we proposed a theoretical framework to investigate sportive fashion trends. The ML-GCN was designed to classify five style categories, “street,” “retro,” “sexy,” “modern,” and “sporty,” and the predictive probabilities of the five styles of fashion images were extracted. We statistically validated the hybrid style results derived from the ML-GCN model and suggested an application method of deep learning-based trend reports in the fashion industry. This study reported sportive fashion by hybrid style dependency, forecasting, and brand clustering. We visualized the predicted probability for a hybrid style to a three-dimensional scale expected to help designers and researchers in the field of fashion to achieve digital design innovation cooperating with deep learning techniques.

Bayesian Sequential Monitoring of Single-Arm Trials: A Comparison of Futility Rules Based on Binary Data

In clinical trials, futility rules are widely used to monitor the study while it is in progress, with the aim of ensuring early termination if the experimental treatment is unlikely to provide the desired level of efficacy. In this paper, we focus on Bayesian strategies to perform interim analyses in single-arm trials based on a binary response variable. Designs that exploit both posterior and predictive probabilities are described and a slight modification of the futility rules is introduced when a fixed historical response rate is used, in order to add uncertainty in the efficacy probability of the standard treatment through the use of prior distributions. The stopping boundaries of the designs are compared under the same trial settings and simulation studies are performed to evaluate the operating characteristics when analogous procedures are used to calibrate the probability cut-offs of the different decision rules.

Protocol of Interim Analysis Study for Repeated Transcranial Magnetic Stimulation for improving cognition in Alzheimer’s Disease (Preprint)

BACKGROUND Many clinical trials investigating treatment efficacy require an interim analysis. Recently we have been running a large multi-site randomized placebo controlled double-blind clinical trial investigating the effect of repetitive transcranial magnetic stimulation (rTMS) treatment for improving or stabilizing the cognition of patients diagnosed with Alzheimer’s disease (AD). OBJECTIVE The objectives of this paper are to report on recruitment, adherence, and adverse events to date, and to describe in detail the protocol for interim analysis of the clinical trial data. The protocol will investigate whether the trial is likely to reach its objectives if continued to the planned maximum sample size. METHODS The specific requirements of the analytic protocol are to: 1) Ensure the double-blind nature of the data while doing the analysis, 2) re-estimate the predictive probabilities of success, 3) re-estimate the numbers needed to evaluate treatment given the so-far standard deviations for each of the output variables. The initial estimate of sample size was 208. The interim analysis will be based on 150 patients who will be enrolled in the study and finish at least 8 weeks of the study. Our protocol for interim analysis, at the very first stage, is to determine the response rate for each participant to the treatment (either sham or active), while ensuring the double-blind nature of the data. The blinded data will be analyzed by a statistician to investigate the treatment efficacy. We will use Bayesian predictive probabilities of success (PPOS) to predict the success rate and determine whether the study should continue. RESULTS The enrollment has been slowed significantly due to COVID-19 pandemic and lockdown. Nevertheless, so far 133 participants have been enrolled, while 22 of these have been withdrawn or dropped out for various reasons. In general, rTMS has been found tolerable with no serious adverse event. Only two patients dropped out of the study due to their intolerability to rTMS pulses. CONCLUSIONS Overall the study with the same protocol is going as expected with no serious adverse event or any major protocol deviation. CLINICALTRIAL https://clinicaltrials.gov/ct2/show/NCT02908815

Exploring Officer-Involved Shootings With Interaction Effects: A Deeper Understanding of How Race/Ethnicity Interacts With Other Factors in the Use of Deadly Force

There has been a substantial body of research examining the reasons behind the police officers’ use of deadly force. Little research has been done to examine how race and ethnicity interact with other factors in the use of deadly force. With data collected in Dallas, Texas, the present study examines the influence of individual, situational, and neighborhood characteristics on officers’ decision to use deadly force. The present study also provides an alternative approach to logistic regression models by estimating predictive probabilities of officers shooting at citizens. The results show that when officers make decisions to shoot at citizens, situational factors are more important than demographic and neighborhood factors. Interactive effects constructed based on the race/ethnicity of the police officer and citizen showed almost no influence on the decision to shoot at a citizen. Finally, the present study concludes with a discussion of implications for policy development and future research.

Predicting Gleason sum upgrading from biopsy to radical prostatectomy pathology: a new nomogram and its internal validation

Background To explore the rate of Gleason sum upgrading (GSU) from biopsy to radical prostatectomy pathology and to develop a nomogram for predicting the probability of GSU in a Chinese cohort. Methods We retrospectively reviewed our prospectively maintained prostate cancer (PCa) database from October 2012 to April 2020. 198 patients who met the criteria were enrolled. Multivariable logistic regression analysis was performed to determine the predictors. Nomogram was constructed based on independent predictors. The receiver operating curve was undertaken to estimate the discrimination. Calibration curve was used to assess the concordance between predictive probabilities and true risks. Results The rate of GSU was 41.4%, whilst GS concordance rate was 44.4%. The independent predictors are prostate specific antigen (PSA), greatest percentage of cancer (GPC), clinical T-stage and Prostate Imaging Reporting and Data System (PI-RADS) score. Our model showed good discrimination (AUC of 0.735). Our model was validated internally with good calibration with bias-corrected C-index of 0.726. Conclusions Utilization of basic clinical variables (PSA and T-stage) combined with imaging variable (PI-RADS) and pathological variable (GPC) could improve performance in predicting actual probabilities of GSU in the 24-core biopsy scheme. Our nomogram could help to assess the true risk and make optimal treatment decisions for PCa patients.