05) improved AUPRC to moderate level. The presented results highlight the importance of making a practical machine learning system for sepsis prediction by considering the availability of dominant features as well as personalizing sepsis prediction by configuring it to the specific demographics of a targeted population.Sleep disorders are extremely common in today's society and are greatly affecting the health and safety of every person suffering from one. Over the last decades, Automatic Sleep Stage Classification (ASSC) systems have been developed to assist specialists in the sleep stage scoring process and therefore in the diagnosis of sleep disorders. Binaural beats are auditory phenomena that have been shown to have a positive impact in sleep quality and mental state. This paper introduces a framework that combines an ASSC system and a binaural beats generator in real time. Our goal is to pave the way for developing systems which could reproduce specific binaural beats depending on the detected sleep stage, in order to entrain the brain into a more efficient sleep. For the ASSC stage, different classifiers were evaluated using data signals retrieved from a public sleep stage signals database, corresponding to ten subjects. The complete framework was tested using the database signals and signals from a test subject, captured and processed in real time. Our proposed framework may lead to a fully automated system to improve sleep quality without the need of medication.We investigated whether a statistical model could predict mean arterial pressure (MAP) during uncontrolled hemorrhage; such a model could be used for automated decision support, to help clinicians decide when to provide intravascular volume to achieve MAP goals. This was a secondary analysis of adult swine subjects during uncontrolled splenic bleeding. By protocol, after developing severe hypotension (MAP less then 60 mmHg), subjects were resuscitated with either saline (NS) or fresh frozen plasma (FFP), determined randomly. Vital signs were documented at quasi-regular time-step intervals, until either subject death or 300 min. Subjects were randomly separated 50%/50% into training/validation sets, and regression models were developed to predict MAP for each subsequent (i.e., future) time-step. Median time-steps for serially recorded vital signs were +15 min. 5 subjects survived the protocol; 17 died after a median time of 87 min (IQR 78 - 134). The final model consisted of current MAP; heart rate (HR); prior NS; imminent NS; and imminent FFP. The 95% limits-of-agreement between true subsequent MAP vs. predicted subsequent MAP were +10/-11 mmHg for the 79 time-steps in the training set; and +14/-13 for the 64 time-steps in the validation set. A total of 10 sudden death events (i.e., rapid, fatal MAP decrease within one single time-step) were excluded from analysis. In conclusion, for uncontrolled hemorrhage in a swine model, it was possible to estimate the next documented MAP value on the basis of the subject's current documented MAP; HR; prior NS; and the volume of resuscitation about to be administered. However, the model was unable to predict "sudden death" events. The applicability to populations with wider heterogeneity of hemorrhage patterns and with comorbidities requires further investigation.Yttrium-90 (90Y) radioembolization is a liver cancer therapy based on 90Y microspheres injected into the hepatic artery. Current dosimetry methods used to estimate the absorbed dose in order to prescribe the 90Y activity to inject are not accurate, which can affect the treatment effectiveness. A new dosimetry based on the hemodynamics simulation of the hepatic arterial tree, CFDose, aimed at overcoming some of the limitations of the current methods. TRULI However, due to the expensive computational cost of computational fluid dynamics (CFD) simulations, this method needs to be accelerated before it can be used in real-time during treatment planning. In this paper, we introduce a convolutional neural network model trained with the CFD results of a patient with hepatocellular carcinoma to predict the 90Y distribution under different downstream vasculature resistance conditions. The model performance was evaluated using two metrics, the mean squared error and prediction accuracy. The prediction accuracy showed that the average difference between the actual and predicted data was less than 1%. The proposed model could estimate the 90Y distribution significantly faster than a CFD simulation.An understanding of healing processes for different tissues and organs, along with the development of appropriate therapeutic devices and treatment protocols, requires an appreciation for the mechanisms-of-action and sequencing of many interconnected chemical, electrical, mechanical, and optical activities. Unfortunately, the substantial contributions that endogenous electrical mechanisms-of-action provide in healing and regulation are often overlooked, resulting in a poor transfer of knowledge from science, to engineering, and finally, to therapy. The wide variety of healing processes, their therapeutic implications, and the devices and protocol designs that are most effective cannot be understood or addressed adequately without an understanding of the endogenous electrical mechanisms-of-action associated with wound healing. Achieving this level of understanding can be enhanced by the use of appropriate models and simulations that are based on physiological/biochemical system response characteristics.Prosthetic hands are developed to replace lost hands. However, it has been hard to ensure the same level grasping and manipulating objects as human hands and the cosmetic appearance is also important. In a previous work, Rehand II an electric and cosmetic prosthetic hand was developed. Its function is limited to simple object grasping, but it has the cosmetic appearance and is relatively light. This paper aimed to improve Rehand II by introducing tactile sense. Tactile sense is available to detect physical contact, recognize physical attributes of objects such as their softness and texture, and ensure delicate operation while handling the objects. Additionally, tactile sense is relevant to build the body recognition. We focused on vibrotactile sense from the aspects of a wide receptive field, contribution to contact detection and various frequency information involved. A simple electric and cosmetic prosthetic hand with vibrotactile sense was developed by improving Rehand II with polyvinylidene difluoride film sensors for detecting skin-propagated vibrations and soft vibrators for the feedback.