A hybrid knowledge and ensemble classification approach for prediction of venous thromboembolism

Clinical narratives such as progress summaries, lab reports, surgical reports, and other narrative texts contain key biomarkers about a patient's health. Evidence-based preventive medicine needs accurate semantic and sentiment analysis to extract and classify medical features as the input to appropriate machine learning classifiers. However, the traditional approach of using single classifiers is limited by the need for dimensionality reduction techniques, statistical feature correlation, a faster learning rate, and the lack of consideration of the semantic relations among features. Hence, extracting semantic and sentiment-based features from clinical text and combining multiple classifiers to create an ensemble intelligent system overcomes many limitations and provides a more robust prediction outcome. The selection of an appropriate approach and its interparameter dependency becomes key for the success of the ensemble method. This paper proposes a hybrid knowledge and ensemble learning framework for prediction of venous thromboembolism (VTE) diagnosis consisting of the following components: a VTE ontology, semantic extraction and sentiment assessment of risk factor framework, and an ensemble classifier. Therefore, a component-based analysis approach was adopted for evaluation using a data set of 250 clinical narratives where knowledge and ensemble achieved the following results with and without semantic extraction and sentiment assessment of risk factor, respectively: a precision of 81.8% and 62.9%, a recall of 81.8% and 57.6%, an F measure of 81.8% and 53.8%, and a receiving operating characteristic of 80.1% and 58.5% in identifying cases of VTE.     

LPNN-based approach for LASSO problem via a sequence of regularized minimizations

In compressive sampling theory, the least absolute shrinkage and selection operator (LASSO) is a representative problem. Nevertheless, the non-differentiable constraint impedes the use of Lagrange programming neural networks (LPNNs). We present in this article the -LPNN model, a novel algorithm that tackles the LASSO minimization together with the underlying theory support. First, we design a sequence of smooth constrained optimization problems, by introducing a convenient differentiable approximation to the non-differentiable -norm constraint. Next, we prove that the optimal solutions of the regularized intermediate problems converge to the optimal sparse signal for the LASSO. Then, for every regularized problem from the sequence, the -LPNN dynamic model is derived, and the asymptotic stability of its equilibrium state is established as well. Finally, numerical simulations are carried out to compare the performance of the proposed -LPNN algorithm with both the LASSO-LPNN model and a standard digital method.     

Pilot-plant results of the electro-Fenton treatment of olive mill wastewaters followed by anaerobic digestion.

In this work, we investigated an integrated technology for the treatment of the recalcitrant contaminants of olive mill wastewaters (OMW), allowing water recovery and reuse for agricultural purposes. The method involves an electrochemical pre-treatment step of the wastewater using the electro-Fenton reaction followed by an anaerobic bio-treatment. The electro-Fenton pre-treatment process removed 66% of the total polyphenolic compounds and subsequently decreased the OMW toxicity from 100 to 66.9%, which resulted in improving the performance of the anaerobic digestion. A continuous laboratory-scale methanogenic reactor was operated at a loading rate of 10g COD/L per day without any apparent toxicity. Furthermore, in the combined process, a high overall reduction in COD, suspended solids, polyphenols and lipids content was achieved by the two successive stages. Moreover, this combined process which was experimented at a real scale (25 m3 digester) demonstrated its technical feasibility and opens promising perspectives for industrial application in the Mediterranean countries because of its easy conception and high energy (methane) production.     

Epoxy thermosetting systems based on cycloaliphatic diamines

We have investigated the reaction kinetics of a liquid prepolymer DGEBA with isophorone diamine (IPD) and menthane diamine (MNDA). IPD is 10 times more reactive than MNDA. With mixtures of these two hardeners we have the possibility to control the reactivity of the curing agent and the pot life of the system. The kinetic results can be described with a single conversion temperature-phase diagram and interpreted with the classical autocatalytic epoxyprimary and secondary amine hydrogens addition. The differences between IPD and MNDA can be explained by the steric hindrance around the amine group of MNDA and also by the difficulty to obtain pure MNDA without oxidation.     

Experimental analysis of fuel from fish processing industry waste in a diesel engine

In the present work, biofuel derived from industrial fish processing industry waste is used in diesel engines to study its suitability . Biofuel from industry fish waste is produced through catalytic cracking, and its quality has been improved through distillation. A single cylinder 4.5 kW at 1500 rpm was used to find the suitability of biofuel and undistilled biofuel in diesel engine. Experimental results show that the brake thermal efficiency of biofuel and undistilled biofuel is similar. Brake thermal efficiency for diesel, undistilled biofuel and biofuel is 29.98, 32.12 and 32.4%, respectively, at 80% load. Carbon monoxide, unburnt hydrocarbons, particulate matter and oxides of nitrogen emissions increase with undistilled biofuel compared to biofuel. There is a small reduction in carbon dioxide emission with undistilled biofuel compared to biofuel. Even though the cylinder pressure is high with undistilled biofuel, the intensity of premixed combustion is lower than distilled biofuel. The ignition delay and combustion duration increase with undistilled biofuel. Finally, it is concluded that the fuel derived from fish processing industry waste can be used as a fuel for diesel engine after distillation.     

A linear 60 GHz 65 nm-CMOS power amplifier realization and characterization for OFDM signal

A millimeter-wave Power Amplifier (PA) based on a 65nm CMOS technology from STMicroelectronics has been designed. The targeted feature is the unlicensed band around 60 GHz suitable for wireless personal area network application (WPAN). To optimize the linearity, the PA is designed under class A biasing to have an output compression point (OCP₁) close to its saturated Power (P _sat). S-parameters and large signal measurement results are demonstrated and compared with electromagnetic simulations. The PA offers a P _sat of 8.3 dBm, an OCP₁ of 6 dBm and a gain of 6.7 dB. The die area is 0.29 mm² with pads. Considering those results, one-tone simulations are not sufficient to characterize the linearity performances of the PA in its real conditions of use. Consequently, two-tone simulations are firstly performed. After, linearity figures of merit (FoM) are discussed applying an orthogonal frequency-division multiplexing (OFDM) modulated signal. The PA offers an adjacent channel power ratio (ACPR) of 15 dB and an error vector magnitude (EVM) of 20% at PA compression operating mode.     

Brown tumors in dialyzed patients with secondary hyperparathyroidism: Report of 16 cases

Brown tumors (BTs) are relatively uncommon but they are serious complications of renal osteodystrophy. The objective of this study was to analyze the clinical, biological, and radiological characteristics of 16 patients with BTs provoked by secondary hyperparathyroidism (sHPT) and its response to the decrease in parathyroid hormone levels after parathyroidectomy (PTX). The management of that uncommon condition was also reviewed. We conducted a retrospective study including 16 end‐stage renal disease patients who underwent subtotal PTX between 1997 and 2007 for severe sHPT with BTs. Our study included 10 men and 6 women, whose average age was 34 years. All patients were on dialysis. Ten of them were on dialysis for more than 5 years. The median duration on dialysis was 84 months. Patients included suffered from swellings associated with functional limitations. BTs had multiple locations in 7 patients. Jaw was the most frequent location (62%). Radiography and tomodensitometry demonstrated a mixed radio lucent and radio‐opaque lesions with an expansion of the cortical bone. Bone scan demonstrated an increased uptake of lesions. Chirurgical treatment was indicated in all cases because of severe refractory sHPT with functional limitations and/or disfiguring deformities. In all cases, BTs stopped its progression and even decreased in size. However, it was insufficient in four cases, which required a surgical resection. PTX remains an efficacious approach in resistant cases of sHPT with persistent BTs.     

Physicochemical Properties of Spray Dried Drugs: Phenobarbitone and Hydroflumethiazide

The potential of spray drying to produce high energy drug forms was investigated using phenobarbitone and hydroflumethiazide. Whereas commercial phenobarbitone is normally Form II, the product produced by spray drying had a large specific surface area (17m ²/g) and physical properties similar to Form III. The apparent solubility of this spray dried material was 25% greater than that of Form II. An amorphous product was obtained on spray drying phenobarbitone with 10% PVP. Spray dried hydroflumethiazide was amorphous and had an apparent solubility 1.61 times that of the crystalline form. Co-spray drying hydroflumethiazide with 10% PVP also produced an amorphous system. Differential scanning calorimetry suggested that the system contained both amorphous drug and an amorphous drug-PVP complex. The product had an apparent solubility 2.5 times that of the pure crystalline drug. Spray drying, either in the presence or absence of excipients, can result in the formation of high energy drug polymorphs or amorphous phases not normally obtained by conventional precipitation procedures.     

Bias voltage effect on the dielectric properties of organic–inorganic blend SiNWs elaborated via metal assisted chemical etching

The electrical proprieties of poly (3-hexylthiophene): Silicon nanowires (P3HT: SiNWs) nanocomposite was investigated by impedance spectroscopy technique. The effect of bias voltage under and without illumination was discussed. Indeed, the imaginary part of the impedance shows a high relaxation frequency related to Maxwell–Wagner–Sillars (MWS) polarization. The relaxation time was found in the range of ms and it was shifted towards high frequency with increasing the bias voltage especially at 0.6 V At bias voltage equal to V_th and under illumination, the conductivity increases because the trapped charges acquire the necessary energy to escape from the interface and the hopping time found was reduced. This indicates a change of the conduction mechanism. The Cole–Cole diagram was excellently fitted through an equivalent circuit including a chemical capacitance Cµ, a contact electrical resistance Rs and recombination resistance Rp.