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.     

ANT-colony based disjoint set assortment in wireless sensor networks

Wireless Networks - Wireless sensor network (WSN) consists of small sized devices containing different sensors to monitor physical, environmental and medical conditions during surveillance of...     

Role of Nd-Ni on structural,spectral and dielectric properties of strontium-barium based nano-sized X-type ferrites

The influence of neodymium and nickel substitution on structural and dielectric parameters was investigated in strontium-barium X-type hexagonal ferrites having composition SrBaCu_2?xNi_xNd_yFe_28?yO₄₆ (x = 0, 0.2, 0.4, 0.6, 0.8, 1 and y = 0, 0.02, 0.04, 0.06, 0.08, 0.1). Sol-gel method was employed for synthesizing these hexagonal ferrites. The XRD plots of all studied materials which were annealed at 1250 °C show single phase characteristics. Lattice parameter ‘c’ increased as a consequence of larger radius of rare earth ion (Nd³⁺) as compared to (Fe³⁺), while lattice parameter ‘a’ showed very small variation. The cell volume was obtained in the range 2508.32–2523.75 (ų). The inclusion of Nd-Ni also affected X-ray density, bulk density and porosity. The FTIR spectroscopy indicated the particular absorption peaks of hexagonal ferrites and it was performed in the range of 500–700 cm^?1. On account of Nd-Ni doping, the dielectric constant, dielectric loss and AC-conductivity showed decreasing trend. The occupancy of Nd³⁺ ions at octahedral site impedes the valence alternation of Fe³⁺; therefore there was decrease in dielectric permittivity. Ac conductivity has been decreased from 9.14 to 6.49 (Ω cm)^?1 at frequency of 2.7 GHz. The Cole-Cole plots of synthesized materials noticeably revealed grain boundary contribution. The appearance of single semi-circle in impedance Cole-Cole graphs confirms the exceptional role of grain boundaries in the conduction process. The considerably lower dielectric parameters of investigated nano X-type ferrites propose their feasibility for high-frequency applications (phase shifters, dielectric resonators, stealth technology etc).     

A novel method based on convolutional neural networks for deriving standard 12-lead ECG from serial 3-lead ECG

Frontiers of Information Technology & Electronic Engineering - Reconstruction of a 12-lead electrocardiogram (ECG) from a serial 3-lead ECG has been researched in the past to satisfy the need...     

Extending orthogonal block codes with partial feedback

During the last few years a number of space-time block codes have been proposed for use in multiple transmit antennas systems. We propose a method to extend any space-time code constructed for m transmit antennas to m p transmit antennas through group-coherent codes (GCCs). GCCs make use of very limited feedback from the receiver (as low as 1 bit). In particular the scheme can be used to extend any orthogonal code (e.g., Alamouti code) to more than two antennas while preserving low decoding complexity, full diversity benefits, and full data rate.     

Crystallization of amorphous Ni60 Nb40−x Cr x alloys

Crystallization behaviour of amorphous Ni₆₀ Nb_40-x Cr _x (x = 0, 5, 10 and 13 at%) alloys was studied by differential Scanning calorimetry and X-ray diffraction measurements. It is shown that the addition of chromium reduces the crystallization temperature, stages of crystallization and activation energies associated with the crystallization sages of the Ni₆₀Nb₄₀ glass. Crystallization of the Ni₆₀Nb₄₀ glass occurred in three stages; in the initial stage a metastable M-phase formed in the amorphous matrix as reported earlier [1] . However, contrary to earlier observation [1], M -phase was not very stable and transformed together with some amorphous phase to the equilibrium Ni₃Nb phase in the second stage of crystallization. In the third stage, the remaining amorphous matrix transformed to the equilibrium NiNb phase. On addition of chromium the formation/stability of the M-phase was found to be suppressed and equilibrium NbCr₂ phase precipitated preferentially in the first stage. The second stage, corresponding to the formation of Ni₃Nb phase, remained almost unaltered. The third stage corresponding to the crystallization of NiNb phase disappeared completely at 13 at% Cr. In the fully crystallized samples the proportion of the NiNb phase decreased and that of NbCr₂ phase increased continuously with chromium concentration.     

The coating of cadmium compounds with copper compounds

Fine particles of cadmium carbonate (CdCO₃) were prepared by heating aqueous solutions containing dissolved urea and cadmium sulfate at 85°C for 1 h. Effect of the composition of the reactant mixture on the morphology of the precipitated particles was investigated. It was found that the cadmium sulfate content of the reactant mixture significantly affected the shape and size of the precipitated particles. At certain range of reactant mixture composition, cauliflower-shaped uniform particles were obtained. The later particles were coated with basic copper carbonate (Cu₂(OH)₂CO₃) by heating aqueous dispersions, containing CdCO₃ particles, copper (II) nitrate, and urea at 85°C for various periods of time with constant stirring. The coating process was found sensitive to the experimental conditions and in most of the trials; mixtures of the coated and coating precursor particles were obtained. As such, extensive optimizations were carried out and conditions were established for the production of uniformly coated particles.On calcination at 700°C for 1 h, the CdCO₃ particles converted into CdO, whereas the coated particles (CdCO_{3 (core)}/Cu₂(OH)₂CO_{3 (coating)} transformed into CdO_(core)/CuO_(coating)) without sintering. In the coated particles, the core and coating materials stayed mutually inert during the calcination reaction and independently converted into their respective oxides.All the calcined and uncalcined products were characterized by various physical and chemical methods.     

A Device-Level Vacuum-Packaging Scheme for Microbolometers on Rigid and Flexible Substrates

This paper reports on the design, fabrication, and characterization of device-level vacuum-packaged microbolometers on rigid Si wafers and flexible polyimide substrates. Semiconducting yttrium barium copper oxide (commonly referred to as YBCO) serves as the bolometric material. Operating micromachined bolometers in vacuum reduces the thermal conductance G_th from the detector to the substrate. If flexibility of the substrate is not to be sacrificed, then the vacuum packaging needs to be done at the device level. Here, the microbolometers are fabricated on a silicon nitride support membrane, isolated from the substrate using surface micromachining. Suitable materials as well as various dimensions in the vacuum cavity are determined using finite-element method (FEM)-based CoventorWARE. A vacuum cavity made of Al₂O₃ has been designed. The thermal conductance G_th of bolometers with the geometry implemented in this work is the same for devices on rigid and flexible substrates. The theoretical value of G_th was calculated to be 4.0 x 10^-6 W/K for devices operating in vacuum and 1.4 x 10^-4 W/K for devices operating at atmospheric pressure. Device-level vacuum-packaged microbolometers on both rigid Si and flexible polyimide substrates have been fabricated and characterized for optical and electrical properties. A low thermal conductance of 1.1 X 10^-6 W/K has been measured six months after fabrication, which implies an intact vacuum cavity.     

The effect of biphasic waveform tilt in transvenous atrial defibrillation

Atrial defibrillation can be accomplished using low energy shocks and transvenous catheters. The biphasic waveform tilt required to achieve optimal atrial defibrillation thresholds (ADFTs) is, however, not known. The effect of single capacitor biphasic waveform tilt modification on ADFT was assessed in 20 patients. Following AF induction the defibrillation pulses were delivered between the catheters positioned in the coronary sinus and the right atrium. The single capacitor biphasic waveform shocks, delivered over the same pathways, consisted of 65% tilt (65/65 biphasic waveform) to produce an overall tilt of 88%, or 50% tilt (50/50 biphasic waveform) to produce an overall tilt of 75%. Although 65/65 biphasic waveform delivers more energy, the shorter duration 50/50 biphasic waveform reduced stored energy ADFT 21%, from 1.34 +/- 0.82 J with 65/65 biphasic to 1.06 +/- 0.81 J. These differences were not statistically significant. Nine patients had lower ADFT with 50/50 biphasic waveform while five patients had lower ADFT with 65/65 biphasic waveform. Equivalent reduction in ADFT was seen in the remaining six patients. The ADFT was 0.83 +/- 0.65 J when both tilts were considered. In conclusion, biphasic waveform tilt modification may affect the ADFT in an individual patient. The optimal biphasic waveform for ADFT is not known.