[Drug Discrimination Method Based on Near Infrared Reflectance Spectrum and Balance Cascading Sparse Representation Based Classification].

The combination of near infrared spectrum and pattern recognition methods has a wide application prospect in rapid and nondestructive supervision and management of drugs. The traditional identification methods regard the smallest error rate as the goal while the imbalance of classes is ignored. This makes the positive class is overwhelming covered by the negative class and reduces its effect for the classifier, so that the classification results tend to recognize the negative class correctly, which severely affects the identification accuracy. In this paper, we mainly studied the class imbalance problems of true or false drugs via infrared spectral data of its, and then propose a balance cascading and sparse representation based classification method (BC-SRC) by combining the Balance Cascading with SRC. We sampling majority samples from the majority class for several times, which has the same size as minority samples and the majority samples we sampled can contain all the majority class samples entirely (sampling times is ceiling the result of majority samples number divide minority samples number). We can get sets of results, and then obtain the final predict labels form those results. Experiments of three databases achieved on Matlab2012a shows that the method is effective. From the experimental results, it can be seen that the method is superior to the commonly used Partial Least Squares (PLS), Extreme Learning Machine (ELM) and BP. Particularly, for the imbalanced databases, when the imbalance factor is greater than 10, the proposed method has more stable performance with higher classification accuracy than the existing ones mentioned above.

Remote ischemic precondition prevents radial artery endothelial dysfunction induced by ischemia and reperfusion based on a cyclooxygenase-2-dependent mechanism.

Ischemic preconditioning (IPC) and remote ischemic precondition (RIPC) are resistance to ischemia-reperfusion (IR) injury. They have common protective mechanism. Cyclooxygenase (COX)-2 participate in the mechanism of IPC. So, the purpose of this study was to determine whether RIPC protects endothelial function of radial artery in human against IR and whether COX-2 involves in this effect. Endothelial IR injury was induced by arm ischemia (20 min) and reperfusion. Flow-mediated dilation (FMD) of the radial artery was measured before and after IR. RIPC (three 5-min cycles of ischemia of the contralateral arm) was applied immediately and 24 h before IR. All volunteers received the COX-2 inhibitor celecoxib (200 mg orally twice daily) for 5 days. On day 6, all subjects experienced the same studies as described. FMD was reduced by IR without administration of RIPC (P<0.0001). RIPC prevent this impairment of FMD immediately (P=NS) and at 24 h (P=NS). Nevertheless, the COX-2 inhibiter abolished protective effect of RIPC at 24 h (P=NS), but not immediately (P=0.001). After administration of the COX-2 inhibiter, post-IR FMD after RIPC performed immediately had significant increase than after RIPC performed at 24 h (P=0.001) and without administration of RIPC (P=0.003). The COX-2 inhibiter made post-IR FMD evidently decrease after RIPC performed at 24 h (P=0.002). RIPC prevents radial artery endothelial dysfunction induced by IR. This protective effect of RIPC in the late phase is mediated by a COX-2-dependent mechanism.

Cytochrome c release in acute myocardial infarction predicts poor prognosis and myocardial reperfusion on contrast-enhanced magnetic resonance imaging.

BACKGROUND: Myocardial ischemia and reperfusion injury in ST-segment elevation myocardial infarction (STEMI) can trigger no-flow, resulting in myocardial necrosis and apoptosis, even a poor prognosis. Cytochrome c can induce an apoptotic process. The aim of our study was to assess the relationship between systemic cytochrome c levels and the occurrence of no-reflow in STEMI. METHODS: One hundred and sixty patients with STEMI undergoing a primary percutaneous coronary intervention (PPCI) were randomly chosen. Patients were divided into two groups defined by the mean cytochrome c peak level after PPCI. No-reflow was assessed using three different methods after PPCI: myocardial blush grade, electrocardiographic ST-resolution, and microvascular obstruction (MO) assessed by cardiovascular magnetic resonance imaging. The primary clinical end points were major adverse cardiovascular events (defined as cardiac death, reinfarction, or new congestive heart failure). Clinical follow-up was carried out for 1 year. RESULTS: Patients with a cytochrome c level of at least the mean peak level had a greater creatine kinase-MB isoenzyme peak level (P=0.044), a lower left ventricular ejection fraction (P=0.029), a significantly higher occurrence of early MO (P=0.008), and a significantly larger extent of early MO (P=0.020). The cytochrome c peak level was elevated in patients with early MO (P=0.025), myocardial blush grade 0-1 (P=0.002), and ST-resolution less than 30% (P=0.003) after PPCI. A higher incidence of cardiac death at the 1-year follow-up was found in the patients with cytochrome c levels of at least the mean peak level (log rank, P=0.029). CONCLUSION: Cytochrome c levels above the mean peak level were related to no-reflow and mortality in patients with STEMI.

[Drug discrimination by near infrared spectroscopy based on summation wavelet extreme learning machine].

As an effective technique to identify counterfeit drugs, Near Infrared Spectroscopy has been successfully used in the drug management of grass-roots units, with classifier modeling of Pattern Recognition. Due to a major disadvantage of the characteristic overlap and complexity, the wide bandwidth and the weak absorption of the Spectroscopy signals, it seems difficult to give a satisfactory solutions for the modeling problem. To address those problems, in the present paper, a summation wavelet extreme learning machine algorithm (SWELM(CS)) combined with Cuckoo research was adopted for drug discrimination by NIRS. Specifically, Extreme Learning Machine (ELM) was selected as the classifier model because of its properties of fast learning and insensitivity, to improve the accuracy and generalization performances of the classifier model; An inverse hyperbolic sine and a Morlet-wavelet are used as dual activation functions to improve convergence speed, and a combination of activation functions makes the network more adequate to deal with dynamic systems; Due to ELM' s weights and hidden layer threshold generated randomly, it leads to network instability, so Cuckoo Search was adapted to optimize model parameters; SWELM(CS) improves stability of the classifier model. Besides, SWELM(CS) is based on the ELM algorithm for fast learning and insensitivity; the dual activation functions and proper choice of activation functions enhances the capability of the network to face low and high frequency signals simultaneously; it has high stability of classification by Cuckoo Research. This compact structure of the dual activation functions constitutes a kernel framework by extracting signal features and signal simultaneously, which can be generalized to other machine learning fields to obtain a good accuracy and generalization performances. Drug samples of near in- frared spectroscopy produced by Xian-Janssen Pharmaceutical Ltd were adopted as the main objects in this paper. Experiments for binary classification and multi-label classification were conducted, and the conclusion proved that the proposed method has more stable performance, higher classification accuracy and lower sensitivity to training samples than the existing ones, such as the BP neural network, ELM and-ELM by particle swarm optimization.