Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters

Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections.     

Electrochemical impedance spectroscopy of poly{pyrrole-trans-[(RuCl2(pmp)4]} copolymer films deposited on platinum electrodes

The present study focuses on the electronic and electrochemical features of a copolymer electrochemically grown from pyrrole and trans-[RuCl₂(pmp)₄] monomers, where pmp = 3-(pyrrol-1-ylmethyl)pyridine. The results from electrochemical impedance spectroscopy analyses revealed the redox behavior of the poly{pyrrole-trans-[RuCl₂(pmp)₄]} compound as well as the non-homogeneous nature of the extremely thin polymeric layers. An equivalent circuit is proposed for an optimized film produced under the scope of the work. Received: 4 May 1998 / Accepted: 24 August 1998     

Snake Venom Components: Tools and Cures to Target Cardiovascular Diseases

Cardiovascular diseases (CVDs) are considered as a major cause of death worldwide. Therefore, identifying and developing therapeutic strategies to treat and reduce the prevalence of CVDs is a major medical challenge. Several drugs used for the treatment of CVDs, such as captopril, emerged from natural products, namely snake venoms. These venoms are complex mixtures of bioactive molecules, which, among other physiological networks, target the cardiovascular system, leading to them being considered in the development and design of new drugs. In this review, we describe some snake venom molecules targeting the cardiovascular system such as phospholipase A2 (PLA2), natriuretic peptides (NPs), bradykinin-potentiating peptides (BPPs), cysteine-rich secretory proteins (CRISPs), disintegrins, fibrinolytic enzymes, and three-finger toxins (3FTXs). In addition, their molecular targets, and mechanisms of action—vasorelaxation, inhibition of platelet aggregation, cardioprotective activities—are discussed. The dissection of their biological effects at the molecular scale give insights for the development of future snake venom-derived drugs.     

A method for calibration and validation subset partitioning

This paper proposes a new method to divide a pool of samples into calibration and validation subsets for multivariate modelling. The proposed method is of value for analytical applications involving complex matrices, in which the composition variability of real samples cannot be easily reproduced by optimized experimental designs. A stepwise procedure is employed to select samples according to their differences in both x (instrumental responses) and y (predicted parameter) spaces. The proposed technique is illustrated in a case study involving the prediction of three quality parameters (specific mass and distillation temperatures at which 10 and 90% of the sample has evaporated) of diesel by NIR spectrometry and PLS modelling. For comparison, PLS models are also constructed by full cross-validation, as well as by using the Kennard-Stone and random sampling methods for calibration and validation subset partitioning. The obtained models are compared in terms of prediction performance by employing an independent set of samples not used for calibration or validation. The results of F-tests at 95% confidence level reveal that the proposed technique may be an advantageous alternative to the other three strategies.     

The Influence of Hydrogen Loading Temperature on the Mechanical Strength of Optical Fibers

The influence of hydrogen loading temperature on the mechanical strength of optical fibers is investigated. Fibers subjected to high-pressure hydrogen loading at different temperatures were submitted to bend tests, and the results compared with those for pristine fibers. The Weibull probability distribution function was used to analyze the data of the mechanical bending strength of the fibers. Fiber strength is reduced by the presence of hydrogen, and this decrease is greater for higher hydrogen loading temperatures. The mechanical properties of the polymers used to coat fibers are affected by the hydrogen loading process and also by the increase in temperature. However, there is no evidence of cracks formation that might allow water to penetrate to the surface of the glass. Observation using scanning electron microscopy revealed that the morphology of fractures in nonhydrogen-loaded fibers have distinct fracture characteristics to that of fibers that are hydrogen loaded at 90°C and 120°C.     

Environmentally friendly sonocatalysis promoted preparation of 1-thiocarbamoyl-3,5-diaryl-4,5-dihydro-1H-pyrazoles

An efficient and green synthesis of thiocarbamoyl-3,5-diaryl-4,5-dihydro-1H-pyrazoles via the condensation of chalcones with thiosemicarbazide in ethanol and KOH under ultrasound irradiation is reported. The products were isolated in good yields after short reaction times.     

Asymptotics of Sobolev embeddings and singular perturbations for the -Laplacian

We consider the best constant for the embedding of into where , . Here with a smooth, bounded domain in and a large positive number. It is proven by the validity of the expansion

as , where is a positive constant depending on and . The behavior of associated extremals, which satisfy an equation involving the -Laplacian operator, is also analyzed.

     

Fractal scattering of microwaves from soils

Using a combination of laboratory experiments and computer simulation we show that microwaves reflected from and transmitted through soil have a fractal dimension correlated to that of the soil's hierarchic permittivity network. The mathematical model relating the ground-penetrating radar record to the mass fractal dimension of soil structure is also developed. The fractal signature of the scattered microwaves correlates well with some physical and mechanical properties of soils.