Establishment of Prognostic Nomogram for Male Breast Cancer Patients: A Surveillance, Epidemiology and End Results Database Analysis.

BACKGROUND: Male breast cancer (MBC) represents a rare subtype of breast cancer, with limited prognostic factor studies available. The purpose of this research was to develop a unique nomogram for predicting MBC patient overall survival (OS) and breast cancer-specific survival (BCSS). METHODS: From 2010 to 2020, clinical characteristics of male breast cancer patients were obtained from the Surveillance, Epidemiology and End Results (SEER) database. Following univariate and multivariate analyses, nomograms for OS and BCSS were created. Kaplan-Meier plots were further generated to illustrate the relationship between independent risk variables and survival. The nomogram's ability to discriminate was measured by employing the area under a time-dependent receiver operating characteristic curve (AUC) and calibration curves. Additionally, when the nomogram was used to direct clinical practice, we also used decision curve analysis (DCA) to evaluate the clinical usefulness and net clinical benefits. RESULTS: A total of 2143 patients were included in this research. Univariate and multivariate analysis showed that age, grade, surgery, chemotherapy status, brain metastasis status, subtype, marital status, race, and AJCC-T, AJCC-N, and AJCC-M stages were significantly correlated with OS. Lung metastasis, age, marital status, grade, surgery, and AJCC-T, AJCC-N, and AJCC-M stages were significantly correlated with BCSS. By comprising these variables, a predictive nomogram was constructed in the SEER cohort. Then, it could be validated well in the validation cohort by receiver operating characteristics (ROCs) curve and calibration plot. Furthermore, the nomogram demonstrated better decision curve analysis (DCA) results, indicating the ability to forecast survival probability with greater accuracy. CONCLUSION: We created and validated a unique nomogram that can assist clinicians in identifying MBC patients at high risk and forecasting their OS/BCSS.

Impedance Sliding-Mode Control Based on Stiffness Scheduling for Rehabilitation Robot Systems.

Rehabilitation robots can reproduce the rehabilitation movements of therapists by designed rehabilitation robot control methods to achieve the goal of training the patients' motion abilities. This paper proposes an impedance sliding-mode control method based on stiffness-scheduled law for the rehabilitation robot, which can be applied to rehabilitation training with both active and passive modes. A free-model-based sliding-mode control strategy is developed to avoid model dependence and reduce the system uncertainty caused by limb shaking. Additionally, the stiffness scheduling rule automatically regulates the impedance parameter of the rehabilitation robot based on the force exerted by the patient on the robot such that the rehabilitation training caters to the patient's health condition. The proposed method is compared with the fixed stiffness and variable stiffness impedance methods, and the superiority of the proposed method is proved. Rehabilitation training experiments on an actual rehabilitation robot are provided to demonstrate the feasibility and stability of the proposed method.

A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding.

Anomaly detection has wide applications to help people recognize false, intrusion, flaw, equipment failure, etc. In most practical scenarios, the amount of the annotated data and the trusted labels is low, resulting in poor performance of the detection. In this paper, we focus on the anomaly detection for the text type data and propose a detection network based on biological immunity for few-shot detection, by imitating the working mechanism of the immune system of biological organisms. This network enabling the protected system to distinguish the aggressive behavior of "nonself" from the legitimate behavior of "self" by embedding characters. First, it constructs episodic task sets and extracts data representations at the character level. Then, in the pretraining phase, Word2Vec is used to embed the representations. In the meta-learning phase, a dynamic prototype containing encoder, routing, and relation is designed to identify the data traffic. Compare to the mean-based prototype, the proposed prototype applies a dynamic routing algorithm that assigns different weights to samples in the support set through multiple iterations to obtain a prototype that combines the distribution of samples. The proposed method is validated on 2 real traffic datasets. The experimental results indicate that (a) the proposed anomaly detection prototype outperforms state-of-the-art few-shot techniques with 1.3% to 4.48% accuracy and 0.18% to 4.55% recall; (b) under the premise of ensuring the accuracy and recall, the number of training samples is reduced to 5 or 10; (c) ablation experiments are designed for each module, and the results show that more accurate prototypes can be obtained by using the dynamic routing algorithm.