No abstract

Objectives To assess the presence of self‐reactive immune responses to seminal and prostate antigens (PAg), biomarkers of inflammation of the male genital tract, and semen quality parameters in patients with chronic prostatitis/chronic pelvic pain syndrome (CP/CPPS). Patients, Subjects and Methods Peripheral blood and semen samples were collected from patients with CP/CPPS and age‐matched healthy control volunteers. We analysed the lymphoproliferative responses of peripheral blood mononuclear cells (PBMC) to different seminal plasma (SP)‐derived and purified PAg, serum autoantibodies specific to PAg, leucocyte subpopulations, and inflammatory cytokines in semen, sperm apoptosis/necrosis, and semen quality parameters. Results Significantly greater PBMC proliferative responses specific to PAg, with elevated secretion of interferon (IFN)γ and interleukin (IL)‐17, were detected in the patients with CP/CPPS vs the controls. Moreover, the patients with CP/CPPS had significantly greater serum immunoglobulin G immune reactivity to SP proteins, such as prostate‐specific antigen and prostatic acid phosphatase, than the controls. Inflammation of the male genital tract was exemplified by high levels of IFNγ, IL‐17, IL‐1β and IL‐8, as well as higher counts of leukocytes, mainly CD4 T lymphocytes and macrophages, in the semen. In addition, this local inflammation was associated with an overall diminished semen quality, i.e., reduced sperm concentration, motility and viability; and higher levels of sperm apoptosis/necrosis in patients with CP/CPPS vs controls. Conclusion Patients with CP/CPPS show T helper type 1 (Th1) and Th17 immune responses specific to PAg associated with chronic inflammation of the male genital tract and reduced semen quality. These immune responses may underlie the induction and development of chronic pelvic pain and inflammation of the male genital tract, which in turn could alter normal prostate functioning and impair semen quality.

This study shows that chronic prostatitis patients with cellular autoimmune response to prostate antigens present important alterations in their semen quality parameters. We speculate that an autoimmune response against prostate antigens and the inflammatory process involved may affect male fertility.

No abstract

Deep learning (DL) models are very useful for human activity recognition (HAR); these methods present better accuracy for HAR when compared to traditional, among other advantages. DL learns from unlabeled data and extracts features from raw data, as for the case of time-series acceleration. Sliding windows is a feature extraction technique. When used for preprocessing time-series data, it provides an improvement in accuracy, latency, and cost of processing. The time and cost of preprocessing can be beneficial especially if the window size is small, but how small can this window be to keep good accuracy? The objective of this research was to analyze the performance of four DL models: a simple deep neural network (DNN); a convolutional neural network (CNN); a long short-term memory network (LSTM); and a hybrid model (CNN-LSTM), when variating the sliding window size using fixed overlapped windows to identify an optimal window size for HAR. We compare the effects in two acceleration sources’: wearable inertial measurement unit sensors (IMU) and motion caption systems (MOCAP). Moreover, short sliding windows of sizes 5, 10, 15, 20, and 25 frames to long ones of sizes 50, 75, 100, and 200 frames were compared. The models were fed using raw acceleration data acquired in experimental conditions for three activities: walking, sit-to-stand, and squatting. Results show that the most optimal window is from 20–25 frames (0.20–0.25s) for both sources, providing an accuracy of 99,07% and F1-score of 87,08% in the (CNN-LSTM) using the wearable sensors data, and accuracy of 98,8% and F1-score of 82,80% using MOCAP data; similar accurate results were obtained with the LSTM model. There is almost no difference in accuracy in larger frames (100, 200). However, smaller windows present a decrease in the F1-score. In regard to inference time, data with a sliding window of 20 frames can be preprocessed around 4x (LSTM) and 2x (CNN-LSTM) times faster than data using 100 frames.