Dysgeusia increases the risk for death and other side effects during antineoplastic systemic treatment for solid tumors: a cross-sectional study.

BACKGROUND: Chemotherapy (CT) is a systemic treatment using a combination of antineoplastic drugs, orally or intravenously, that inhibit tumor growth and fast-growing normal cells. Due to its nonspecificity, chemotherapy can cause a series of adverse effects, such as altered taste (dysgeusia), associated with malnutrition and, consequently, other adverse effects in the gastrointestinal tract and increased mortality risk. This study aimed to evaluate the influence of dysgeusia on the incidence of other adverse effects and overall survival during antineoplastic chemotherapy. MATERIAL AND METHODS: An observational, retrospective, cross-sectional study was conducted using data from the Electronic Health Record system of the Cancer Institute of Ceará over two years. Before the CT session, the multi-professional team evaluated the patient for the presence and severity of adverse effects (AE), using scores from the CTCAE v5.0 scale. Dysgeusia scores were collected and associated with clinical pathological data, with other adverse effects (nausea, vomiting, diarrhea, oral mucositis, anorexia, constipation), and with overall survival. Chi-square and Mantel-Cox log-rank tests were used. RESULTS: Of 5744 patients evaluated, dysgeusia presented a frequency of 50.6%, being directly associated with female gender (p=0.001), overweight (p=0.022), high tumor stages (p=0.009), a combination of adjuvant and neoadjuvant (p=0.010) and four-year survival (p=0.030). Dysgeusia frequency was directly associated with diarrhea (p<0.001), anorexia (p<0.001), oral mucositis (p<0.001), nausea (p<0.001), constipation (p<0.001) and vomiting (p<0.001), and inversely associated with fatigue (p=0.035). CONCLUSIONS: Dysgeusia during CT increases the risk of other adverse effects and negatively impacts prognosis.

Identification and control of dynamical systems using the self-organizing map.

In this paper, we introduce a general modeling technique, called vector-quantized temporal associative memory (VQTAM), which uses Kohonen's self-organizing map (SOM) as an alternative to multilayer perceptron (MLP) and radial basis function (RBF) neural models for dynamical system identification and control. We demonstrate that the estimation errors decrease as the SOM training proceeds, allowing the VQTAM scheme to be understood as a self-supervised gradient-based error reduction method. The performance of the proposed approach is evaluated on a variety of complex tasks, namely: i) time series prediction; ii) identification of SISO/MIMO systems; and iii) nonlinear predictive control. For all tasks, the simulation results produced by the SOM are as accurate as those produced by the MLP network, and better than those produced by the RBF network. The SOM has also shown to be less sensitive to weight initialization than MLP networks. We conclude the paper by discussing the main properties of the VQTAM and their relationships to other well established methods for dynamical system identification. We also suggest directions for further work.

Unsupervised learning and temporal context to recall complex robot trajectories.

An unsupervised neural network is proposed to learn and recall complex robot trajectories. Two cases are considered: (i) A single trajectory in which a particular arm configuration (state) may occur more than once, and (ii) trajectories sharing states with each other. Ambiguities occur in both cases during recall of such trajectories. The proposed model consists of two groups of synaptic weights trained by competitive and Hebbian learning laws. They are responsible for encoding spatial and temporal features of the input sequences, respectively. Three mechanisms allow the network to deal with repeated or shared states: local and global context units, neurons disabled from learning, and redundancy. The network reproduces the current and the next state of the learned sequences and is able to resolve ambiguities. The model was simulated over various sets of robot trajectories in order to evaluate learning and recall, trajectory sampling effects and robustness.