Chained Deep Learning Using Generalized Cross-Entropy for Multiple Annotators Classification.

Supervised learning requires the accurate labeling of instances, usually provided by an expert. Crowdsourcing platforms offer a practical and cost-effective alternative for large datasets when individual annotation is impractical. In addition, these platforms gather labels from multiple labelers. Still, traditional multiple-annotator methods must account for the varying levels of expertise and the noise introduced by unreliable outputs, resulting in decreased performance. In addition, they assume a homogeneous behavior of the labelers across the input feature space, and independence constraints are imposed on outputs. We propose a Generalized Cross-Entropy-based framework using Chained Deep Learning (GCECDL) to code each annotator's non-stationary patterns regarding the input space while preserving the inter-dependencies among experts through a chained deep learning approach. Experimental results devoted to multiple-annotator classification tasks on several well-known datasets demonstrate that our GCECDL can achieve robust predictive properties, outperforming state-of-the-art algorithms by combining the power of deep learning with a noise-robust loss function to deal with noisy labels. Moreover, network self-regularization is achieved by estimating each labeler's reliability within the chained approach. Lastly, visual inspection and relevance analysis experiments are conducted to reveal the non-stationary coding of our method. In a nutshell, GCEDL weights reliable labelers as a function of each input sample and achieves suitable discrimination performance with preserved interpretability regarding each annotator's trustworthiness estimation.

Transesophageal Echocardiographic Assessment in Patients with Severe Respiratory Distress due to COVID-19 in the Prone Position: A Feasibility Study.

Background and aim: Our aim was to assess the feasibility, safety, and utility of implementing transesophageal echocardiographic screening in patients with coronavirus disease-2019 (COVID-19)-related acute respiratory distress syndrome (ARDS), receiving mechanical ventilation (MV) and in prone position (PP). Methods: Prospective observational study performed in an intensive care unit; patients 18 years, with ARDS, invasive MV, in PP were included. A total of 87 patients were included. Results: There was no need to change ventilator settings, hemodynamic support, or any difficulties with the insertion of the ultrasonographic probe. Mean duration of transesophageal echocardiography (TEE) was 20 minutes. No displacement of the orotracheal tube, vomiting, or gastrointestinal bleeding was observed. Frequent complication was displacement of the nasogastric tube in 41 (47%) patients. Severe right ventricular (RV) dysfunction was detected in 21 (24%) patients and acute cor pulmonale was diagnosed in 36 (41%) patients. Conclusion: Our results show the importance of assessing RV function during the course of severe respiratory distress and the value of TEE for hemodynamic assessment in PP. How to cite this article: Sosa FA, Wehit J, Merlo P, Matarrese A, Tort B, Roberti JE, et al. Transesophageal Echocardiographic Assessment in Patients with Severe Respiratory Distress due to COVID-19 in the Prone Position: A Feasibility Study. Indian J Crit Care Med 2023;27(2):132-134.

Posthoc Interpretability of Neural Responses by Grouping Subject Motor Imagery Skills Using CNN-Based Connectivity.

Motor Imagery (MI) refers to imagining the mental representation of motor movements without overt motor activity, enhancing physical action execution and neural plasticity with potential applications in medical and professional fields like rehabilitation and education. Currently, the most promising approach for implementing the MI paradigm is the Brain-Computer Interface (BCI), which uses Electroencephalogram (EEG) sensors to detect brain activity. However, MI-BCI control depends on a synergy between user skills and EEG signal analysis. Thus, decoding brain neural responses recorded by scalp electrodes poses still challenging due to substantial limitations, such as non-stationarity and poor spatial resolution. Also, an estimated third of people need more skills to accurately perform MI tasks, leading to underperforming MI-BCI systems. As a strategy to deal with BCI-Inefficiency, this study identifies subjects with poor motor performance at the early stages of BCI training by assessing and interpreting the neural responses elicited by MI across the evaluated subject set. Using connectivity features extracted from class activation maps, we propose a Convolutional Neural Network-based framework for learning relevant information from high-dimensional dynamical data to distinguish between MI tasks while preserving the post-hoc interpretability of neural responses. Two approaches deal with inter/intra-subject variability of MI EEG data: (a) Extracting functional connectivity from spatiotemporal class activation maps through a novel kernel-based cross-spectral distribution estimator, (b) Clustering the subjects according to their achieved classifier accuracy, aiming to find common and discriminative patterns of motor skills. According to the validation results obtained on a bi-class database, an average accuracy enhancement of 10% is achieved compared to the baseline EEGNet approach, reducing the number of "poor skill" subjects from 40% to 20%. Overall, the proposed method can be used to help explain brain neural responses even in subjects with deficient MI skills, who have neural responses with high variability and poor EEG-BCI performance.

KCS-FCnet: Kernel Cross-Spectral Functional Connectivity Network for EEG-Based Motor Imagery Classification.

This paper uses EEG data to introduce an approach for classifying right and left-hand classes in Motor Imagery (MI) tasks. The Kernel Cross-Spectral Functional Connectivity Network (KCS-FCnet) method addresses these limitations by providing richer spatial-temporal-spectral feature maps, a simpler architecture, and a more interpretable approach for EEG-driven MI discrimination. In particular, KCS-FCnet uses a single 1D-convolutional-based neural network to extract temporal-frequency features from raw EEG data and a cross-spectral Gaussian kernel connectivity layer to model channel functional relationships. As a result, the functional connectivity feature map reduces the number of parameters, improving interpretability by extracting meaningful patterns related to MI tasks. These patterns can be adapted to the subject's unique characteristics. The validation results prove that introducing KCS-FCnet shallow architecture is a promising approach for EEG-based MI classification with the potential for real-world use in brain-computer interface systems.

Frailty and clinical outcomes in critically ill patients with cancer: A cohort study.

INTRODUCTION: Our aim was to assess impact of frailty on short-term clinical outcomes in critically ill patients with cancer. MATERIALS AND METHODS: We conducted a cohort study at a medical and surgical intensive care unit (ICU) in Argentina. We included 269 consecutive patients, ≥18 years old, with diagnosis of cancer. We recorded demographic and clinical characteristics, Clinical Frailty Scale (CFS, ≥5 defined a patient as frail), and the number and duration of organ support therapies during ICU stay. Primary outcome was ICU and hospital mortality. RESULTS: Median age 69 (range 20-90); 152 (56%) patients were male. Sixty-eight (25.2%) patients presented frailty at admission. Older adults (≥65 years old) made up 62.8% of patients. Frail patients were 69.7 years versus 64.4 years for non-frail, P = 0.007, with higher Acute Physiology and Chronic Health Evaluation II (APACHE II) 14.7 ± 7 versus 10.8 ± 6, P = 0.001 and Simplified Acute Physiology Score (SAPS II) 40.1 ± 17 versus 28.7 ± 14, P = 0.001, respectively. After adjusting by age, severity score, type of admission, and type of cancer, frailty was independently associated with hospital mortality, odds ratio (OR) 4.87 (95% confidence interval [CI], 2.19-11.19, P ≤0.001). Median ICU length of stay was five days (interquartile range [IQR] 3-7) versus six days (IQR 3.8-9), in non-frail versus frail patients, respectively (P = 0.100), and hospital stay was nine days (IQR 6-17) versus 11.5 days (IQR 7-19.5) in non-frail versus frail patients, respectively (P = 0.085). DISCUSSION: Frailty as a medical condition was strongly associated with worse clinical outcomes among oncologic critically ill patients.

Análisis epidemiológico de bacteriemias asociadas a catéter en una terapia intensiva médico-quirúrgica / Epidemiological analysis of catheter-related bloodstream infections in medical-surgical intensive care units

Resumen Se realizó un estudio observacional retrospectivo analítico que evaluó la epidemiología de las bacteriemias asociadas a catéter central (BAC) en 773 adultos internados en la unidad de cuidados intensivos (UCI) del Hospital Alemán de Buenos Aires entre diciembre de 2018 y junio de 2020. Durante el pe riodo de estudio, la incidencia fue 8.7 eventos cada 1000 días catéter. El desarrollo de BAC se asoció con mala evolución clínica, que fue puesta en evidencia por una duración de la internación en UCI significativamente mayor que la de los pacientes sin BAC (mediana: 21.5 días vs. 4 días, p < 0.001). La mortalidad también fue mayor, pero sin significancia estadística (24% vs. 20%, OR 1.26 [0.61-2.63]). Los microorganismos más frecuentemente aislados fueron bacterias Gram positivas (73%) y, entre ellas, Staphylococcus epidermidis fue la más frecuente (40%). De los 47 aislamientos de microorganismos relevados, 8 (17%) fueron gérmenes multirresistentes. El análisis multivariado identificó el tiempo de permanencia del catéter como factor de riesgo para desarrollar BAC (OR 1.10 [1.05 - 1.15], p < 0.001). En dicho análisis, una mayor tasa de BAC no fue influida por el sitio anatómico de inserción del catéter, el servicio donde se realizó el procedimiento (UCI o quirófano/servicio de emergencias), la experiencia previa del médico en el procedimiento, ni el uso de ultrasonido para guiar la cateterización. Con cluimos que las BAC son una complicación frecuente en nuestro servicio con consecuencias clínicas relevantes. Conocer la epidemiología y la problemática de cada servicio permite programar intervenciones dirigidas a corregir problemas concretos de salud pública.

Abstract A retrospective-observational analytical study was carried out to evaluate the epidemiology of catheter-related bloodstream infections (CRBSI) in 773 adult patients hospitalized in the inten sive care unit (ICU) of the Hospital Alemán of Buenos Aires, Argentina, between 1 December 2018 and 30 June 2020. During the study period, the incidence of CRBSI was 8.7 cases per 1000 catheter days. The occurrence of CRBSI was found associated with a poor clinical evolution, as evidenced by a stay in the ICU significantly longer than the stay of patients without CRBSI (median: 21.5 days vs. 4 days, p < 0.001). CRBSI-associated mortality was not statistically higher (24% vs. 20%, OR 1.26 [0.61-2.63]). Gram-positive bacteria were the most frequently identified microorganisms (73%), being Staphylococcus epidermidis the most frequent (40%). Of the 47 isolates of microorganisms surveyed, 8 (17%) were multi-resistant germs. The permanence time of the catheter was identified as a risk factor for developing CRBSI (OR 1.10 [1.05 - 1.15], p < 0.001) in a multivariate analysis. In this analysis, the risk of infection was not influenced by the anatomical site of insertion of the catheter, the ward where the procedure was performed (ICU vs. operating room/external ward), the skill of the medical practitioner, or the use of ultrasound to guide vascular accesses. We conclude that CRBSIs are a frequent complication in our department with relevant clinical consequences. Knowing the epidemiology and the problems of each service allows programming interventions aimed to correct specific public health problems.

[Epidemiological analysis of catheter-related bloodstream infections in medical-surgical intensive care units]. / Análisis epidemiológico de bacteriemias asociadas a catéter en una terapia intensiva médico-quirúrgica.

A retrospective-observational analytical study was carried out to evaluate the epidemiology of catheter-related bloodstream infections (CRBSI) in 773 adult patients hospitalized in the intensive care unit (ICU) of the Hospital Alemán of Buenos Aires, Argentina, between 1 December 2018 and 30 June 2020. During the study period, the incidence of CRBSI was 8.7 cases per 1000 catheter days. The occurrence of CRBSI was found associated with a poor clinical evolution, as evidenced by a stay in the ICU significantly longer than the stay of patients without CRBSI (median: 21.5 days vs. 4 days, p < 0.001). CRBSI-associated mortality was not statistically higher (24% vs. 20%, OR 1.26 [0.61-2.63]). Gram-positive bacteria were the most frequently identified microorganisms (73%), being Staphylococcus epidermidis the most frequent (40%). Of the 47 isolates of microorganisms surveyed, 8 (17%) were multi-resistant germs. The permanence time of the catheter was identified as a risk factor for developing CRBSI (OR 1.10 [1.05 - 1.15], p < 0.001) in a multivariate analysis. In this analysis, the risk of infection was not influenced by the anatomical site of insertion of the catheter, the ward where the procedure was performed (ICU vs. operating room/external ward), the skill of the medical practitioner, or the use of ultrasound to guide vascular accesses. We conclude that CRBSIs are a frequent complication in our department with relevant clinical consequences. Knowing the epidemiology and the problems of each service allows programming interventions aimed to correct specific public health problems.

Se realizó un estudio observacional retrospectivo analítico que evaluó la epidemiología de las bacteriemias asociadas a catéter central (BAC) en 773 adultos internados en la unidad de cuidados intensivos (UCI) del Hospital Alemán de Buenos Aires entre diciembre de 2018 y junio de 2020. Durante el periodo de estudio, la incidencia fue 8.7 eventos cada 1000 días catéter. El desarrollo de BAC se asoció con mala evolución clínica, que fue puesta en evidencia por una duración de la internación en UCI significativamente mayor que la de los pacientes sin BAC (mediana: 21.5 días vs. 4 días, p < 0.001). La mortalidad también fue mayor, pero sin significancia estadística (24% vs. 20%, OR 1.26 [0.61-2.63]). Los microorganismos más frecuentemente aislados fueron bacterias Gram positivas (73%) y, entre ellas, Staphylococcus epidermidis fue la más frecuente (40%). De los 47 aislamientos de microorganismos relevados, 8 (17%) fueron gérmenes multirresistentes. El análisis multivariado identificó el tiempo de permanencia del catéter como factor de riesgo para desarrollar BAC (OR 1.10 [1.05 - 1.15], p < 0.001). En dicho análisis, una mayo r tasa de BAC no fue influida por el sitio anatómico de inserción del catéter, el servicio donde se realizó el procedimiento (UCI o quirófano/servicio de emergencias), la experiencia previa del médico en el procedimiento, ni el uso de ultrasonido para guiar la cateterización. Concluimos que las BAC son una complicación frecuente en nuestro servicio con consecuencias clínicas relevantes. Conocer la epidemiología y la problemática de cada servicio permite programar intervenciones dirigidas a corregir problemas concretos de salud pública.

Current Phthalocyanines Delivery Systems in Photodynamic Therapy: An Updated Review.

Photodynamic therapy has emerged as an effective therapeutic alternative to treat oncological, cardiovascular, dermatological, infectious, and ophthalmic diseases. Photodynamic therapy combines the action of a photosensitizer with light in the presence of oxygen to generate reactive oxygen species, capable of reacting with cellular components, resulting in injury and, consequently, inducing cellular death. Phthalocyanines are considered good photosensitizers, although most of them are lipophilic, difficulting their administration for clinical use. A strategy to overcome the lack of solubility of phthalocyanines in aqueous media is to incorporate them into different delivery systems. The present review aimed to summarize the current status of the main drug delivery systems used for Zn and Al phthalocyanines and their effect in photodynamic therapy, reported in the last five years. Liposomes, polymeric micelles, polymeric nanoparticles, and goldnanoparticles constituted some of the most used carriers and were discussed in this review. The latest studies reported strongly suggest that the application of nanotechnologies as delivery systems allows an increase in photodynamic therapy efficacy and reduces side-effects associated with the phthalocyanine administration, which represents a hope for cancer treatments.

The moonlighting protein c-Fos activates lipid synthesis in neurons, an activity that is critical for cellular differentiation and cortical development.

Differentiation of neuronal cells is crucial for the development and function of the nervous system. This process involves high rates of membrane expansion, during which the synthesis of membrane lipids must be tightly regulated. In this work, using a variety of molecular and biochemical assays and approaches, including immunofluorescence microscopy and FRET analyses, we demonstrate that the proto-oncogene c-Fos (c-Fos) activates cytoplasmic lipid synthesis in the central nervous system and thereby supports neuronal differentiation. Specifically, in hippocampal primary cultures, blocking c-Fos expression or its activity impairs neuronal differentiation. When examining its subcellular localization, we found that c-Fos co-localizes with endoplasmic reticulum markers and strongly interacts with lipid-synthesizing enzymes, whose activities were markedly increased in vitro in the presence of recombinant c-Fos. Of note, the expression of c-Fos dominant-negative variants capable of blocking its lipid synthesis-activating activity impaired neuronal differentiation. Moreover, using an in utero electroporation model, we observed that neurons with blocked c-Fos expression or lacking its AP-1-independent activity fail to initiate cortical development. These results highlight the importance of c-Fos-mediated activation of lipid synthesis for proper nervous system development.

Fra-1 and c-Fos N-Terminal Deletion Mutants Impair Breast Tumor Cell Proliferation by Blocking Lipid Synthesis Activation.

Tumor cells require high rates of lipid synthesis to support membrane biogenesis for their exacerbated growth. The only two proteins known that activate phospholipid synthesis are Fra-1 and c-Fos, two members of the AP-1 family of transcription factors. These proteins that are overexpressed in human breast malignant tumors increase the rate of phospholipid synthesis at the endoplasmic reticulum through a mechanism independent of their nuclear function. The aim of this study was to inhibit breast tumor cell proliferation by modulating c-Fos and Fra-1 and regulate membrane biogenesis by controlling lipid synthesis rates. The molecular mechanism by which Fra-1 and c-Fos activate phospholipid synthesis was examined. Both proteins physically associate with the rate limiting enzyme CDP-DAG synthase through their N-terminus domain and activate it through their basic domain; neither protein associates to or activates the enzyme phosphatidylinositol synthase as determined through in vitro enzymatic reactions and FRET experiments. The N-terminus domain of both proteins act as negative dominant peptides that physically associate with CDP-DAG synthase but do not activate it. Proliferation of MDA-MB231 and 4T1 cells was impaired in vitro after inducing them to proliferate in the presence of the negative dominant peptides derived from Fra-1 and c-Fos. When tumors generated in Balb/c mice with the breast tumor cell line 4T1 were treated with these negative dominant peptides, a significant reduction in tumor growth was observed. Consequently, these Fra-1 and c-Fos negative dominant peptides can be exploited as a new therapeutic strategy to impair breast tumor cell proliferation.

Nanomateriales: un acercamiento a lo básico / Nanomaterials: Being Closer to Basics

El término nanomaterial se refiere a una sustancia o conjunto de sustancias en la escala de los nanómetros donde los constituyentes son átomos y/o moléculas. Varios países comprometidos con iniciativas en nanotecnología ya han formulado una definición para nanomateriales, aunque aún no existe un amplio consenso frente a una única definición. Actualmente se debate sobre la conveniencia o no de contar con una definición consensuada y estandarizada a nivel global. Se puede argumentar que esta falta de consenso puede dificultar la tarea regulatoria y normativa, así como la búsqueda de acuerdos y estándares internacionales. En este trabajo, se realiza una revisión de las definiciones existentes sobre nanomateriales, su incorporación en la industria y los factores de riesgo por exposición ocupacional a estas entidades. Finalmente, se ofrecen algunas recomendaciones para adoptar criterios de evaluación del impacto de los nanomateriales en la salud humana y el medio ambiente

The concept of nanomaterial refers to a substance or group of substances on the nanometer scale where the components are atoms and/or molecules. Although there is not a broad consensus on a single definition of them yet, many countries committed to nanotechnology initiatives have already proposed a definition for nanomaterial. The need of a worldwide agreed and standardized definition is nowadays being discussed. It can be argued that this lack of consensus can obstruct the regulatory and normative enforcement, as well as the search for agreements and international standards. In this paper, a review is made based on the existing definitions of nanomaterial, their incorporation into the industry and the risk factors for occupational exposure to these agents. Finally, some recommendations are given in order to adopt criteria for evaluating the impact of nanomaterials on human health and the environment

Identification and monitoring of brain activity based on stochastic relevance analysis of short-time EEG rhythms.

BACKGROUND: The extraction of physiological rhythms from electroencephalography (EEG) data and their automated analyses are extensively studied in clinical monitoring, to find traces of interictal/ictal states of epilepsy. METHODS: Because brain wave rhythms in normal and interictal/ictal events, differently influence neuronal activity, our proposed methodology measures the contribution of each rhythm. These contributions are measured in terms of their stochastic variability and are extracted from a Short Time Fourier Transform to highlight the non-stationary behavior of the EEG data. Then, we performed a variability-based relevance analysis by handling the multivariate short-time rhythm representation within a subspace framework. This maximizes the usability of the input information and preserves only the data that contribute to the brain activity classification. For neural activity monitoring, we also developed a new relevance rhythm diagram that qualitatively evaluates the rhythm variability throughout long time periods in order to distinguish events with different neuronal activities. RESULTS: Evaluations were carried out over two EEG datasets, one of which was recorded in a noise-filled environment. The method was evaluated for three different classification problems, each of which addressed a different interpretation of a medical problem. We perform a blinded study of 40 patients using the support-vector machine classifier cross-validation scheme. The obtained results show that the developed relevance analysis was capable of accurately differentiating normal, ictal and interictal activities. CONCLUSIONS: The proposed approach provides the reliable identification of traces of interictal/ictal states of epilepsy. The introduced relevance rhythm diagrams of physiological rhythms provides effective means of monitoring epileptic seizures; additionally, these diagrams are easily implemented and provide simple clinical interpretation. The developed variability-based relevance analysis can be translated to other monitoring applications involving time-variant biomedical data.

Predictability of gene ontology slim-terms from primary structure information in Embryophyta plant proteins.

BACKGROUND: Proteins are the key elements on the path from genetic information to the development of life. The roles played by the different proteins are difficult to uncover experimentally as this process involves complex procedures such as genetic modifications, injection of fluorescent proteins, gene knock-out methods and others. The knowledge learned from each protein is usually annotated in databases through different methods such as the proposed by The Gene Ontology (GO) consortium. Different methods have been proposed in order to predict GO terms from primary structure information, but very few are available for large-scale functional annotation of plants, and reported success rates are much less than the reported by other non-plant predictors. This paper explores the predictability of GO annotations on proteins belonging to the Embryophyta group from a set of features extracted solely from their primary amino acid sequence. RESULTS: High predictability of several GO terms was found for Molecular Function and Cellular Component. As expected, a lower degree of predictability was found on Biological Process ontology annotations, although a few biological processes were easily predicted. Proteins related to transport and transcription were particularly well predicted from primary structure information. The most discriminant features for prediction were those related to electric charges of the amino-acid sequence and hydropathicity derived features. CONCLUSIONS: An analysis of GO-slim terms predictability in plants was carried out, in order to determine single categories or groups of functions that are most related with primary structure information. For each highly predictable GO term, the responsible features of such successfulness were identified and discussed. In addition to most published studies, focused on few categories or single ontologies, results in this paper comprise a complete landscape of GO predictability from primary structure encompassing 75 GO terms at molecular, cellular and phenotypical level. Thus, it provides a valuable guide for researchers interested on further advances in protein function prediction on Embryophyta plants.

[Review by expert group in the diagnosis and treatment of anemia in pregnant women. Federación Mexicana de Colegios de Obstetricia y Ginecología]. / Opinión de un grupo de expertos en diagnóstico y tratamiento de la anemia en la mujer embarazada.

BACKGROUND: According to data from the World Health Organization and UNICEF from year 2009, iron deficiency is the most widespread nutritional deficiency worldwide. This deficiency causes an imbalance between needs and iron supply, which consequently results in anemia. Around the world, two million people suffer from anemia, half of which is due to iron deficiency. The most impacted groups are children and teenagers, due to their highest requirements derived from the growing process, and women in their reproductive age, due to their loss of iron derived from menstruating or to their highest iron needs during pregnancy. This increase in needs is not satisfied by the regular diet, since it includes an insufficient amount and/or low bioavailability of iron. PURPOSE: To share with the medical community treating pregnant women the experience of an expert group so that they always bear in mind the repercussions caused by anemia during pregnancy, know more about the diagnostic possibilities and have a reference point for prescribing iron supplements. METHOD: The consensus method was used through the expert panel group technique. Two rounds were taken for structuring the clinical questions. The first one was to facilitate working groups their focusing in the clinical topics and the population of interest; the second one was to aid in posing specific questions observing the Patient, Intervention, Compare and Outcome (PICO) structure. The primary and clinical secondary study variables were defined by the working groups from the previously developed questions and during the face-to-face working period, according to the natural history of the disease: risk factors, diagnostic classification, (either pharmacological or non pharmacological) treatment and prognosis. The level of evidence and clinical recommendation was classified based on the Evidence Classification Level and Clinical Recommendation of the Medicine Group based on Evidence from Oxford University. RESULTS: In Mexico, 20.6% of pregnant women suffer from anemia, especially those between 15 and 16 years old, who prevail in 42.4% and 34.3% percent, respectively. Almost half the cases are due to iron deficiency. This type of anemia is associated with a higher risk of pre-term delivery, of low birth weight and perinatal death. The first assessment of an anemic pregnant woman shall include the medical history, a physical examination and the quantification of the erythrocyte indices, serum concentrations of iron and ferritin. The measurement of this last one has the highest sensitivity and specificity for diagnosing iron deficiency. Daily oral iron supplementation, at a 60-to-120 mg dosage, may correct most of mild-to-moderate anemias. The most appropriate treatment is with iron salts (iron sulfate, polimaltose iron complex or iron fumarate). In case of intolerance to iron sulfate or fumarate, polimaltose iron is a better tolerated option. Treatment shall be administered until the hemoglobin values are > 10.5 g and ferritin is between 300 and 360 microg/dL, and such levels shall be observed for at least one year. Parenteral administration is an alternative for patients with a severe intolerance to oral administration; even when the possibility of anaphylaxis shall be considered it is lower when using ferrous sacarate. Transfusion is reserved for patients with hemoglobin lower than 7 g/dL or having an imminent cardio-respiratory decompensation. CONCLUSIONS: Iron deficiency is the highest prevailing nutritional deficiency worldwide and its consequences during pregnancy may be highly risky for both the mother and her child. Anemia diagnosis may easily be achieved through a blood analysis including the serum ferritin determination. Serum iron measurement shall not be used as the only marker to set the diagnosis. It is important to rule out other causes, in addition to the deficiencies, which produce anemia in a patient. It is essential to suggest the administration of iron supplements not only during the antenatal period but also after birth o even after a miscarriage to fulfill the need for depleted iron. In severe anemias (hemoglobin being lower than 9.0 g/L), iron doses higher than 120 mg a day may be required. Treatment shall always begin orally, and if this is not well tolerated, parenteral administration shall be used.

Towards high accuracy classification of MER signals for target localization in Parkinson's disease.

In recent years Microelectrode recording (MER) analysis has proved to be a powerful localization tool of basal ganglia for Parkinson disease's treatment, especially the Subthalamic Nucleus (STN). In this paper, a signal-dependent method is presented for identification of the STN and other brain zones in Parkinsonian patients. The proposed method, refereed as optimal wavelet feature extraction method (OWFE), is constructed by lifting schemes (LS), which are a flexible and fast implementation of the wavelet transform (WT). The operators in the LS are optimized by means of Genetic Algorithms and Lagrange multipliers considering information contained in MER signals. Then a basic Bayesian classifier (LDC) is used to identify STN and other types of basal ganglia nuclei. The proposed method introduced several advantages from similar works reported in literature. First, the method is signal-dependent and non a priori information is required to decompose the MER signal. Second, the classification accuracy is mostly depended on the feature selection stage because it is not enhanced by elaborated classifiers such as support vector machines or hidden Markov models. Finally, the generalization property of the OWFE has been validated with two databases and different types of classifiers such as k-NN classifier and quadratic Bayesian classifier (QDC). Results have shown that proposed method is able to identify the STN with average accuracy superior than 97%.