An exploration of new methods for metabolic syndrome examination by infrared thermography and knowledge mining.

Metabolic syndrome (MS) is a clinical syndrome with multiple metabolic disorders. As the diagnostic criteria for MS still lacking of imaging laboratory method, this study aimed to explore the differences between healthy people and MS patients through infrared thermography (IRT). However, the observation region of the IRT image is uncertain, and the research tried to solve this problem with the help of knowledge mining technology. 43 MS participants were randomly included through a cross-sectional method, and 43 healthy participants were recruited through number matching. The IRT image of each participant was segmented into the region of interest (ROI) through the preprocessing method proposed in this research, and then the ROI features were granulated by the K-means algorithm to generate the formal background, and finally, the two formal background were separately built into a knowledge graph through the knowledge mining method based on the attribute partial order structure. The baseline data shows that there is no difference in age, gender, and height between the two groups (P > 0.05). The image preprocessing method can segment the IRT image into 18 ROI. Through the K-means method, each group of data can be separately established with a 43 × 36 formal background and generated a knowledge graph. It can be found through knowledge mining and independent-samples T test that the average temperature and maximum temperature difference between the chest and face of the two groups are statistically different (P < 0.01). IRT could reflect the difference between healthy people and MS people. The measurement regions were found by the method of knowledge mining on the premise of unknown. The method proposed in this paper may add a new imaging method for MS laboratory examinations, and at the same time, through knowledge mining, it can also expand a new idea for clinical research of IRT.

[A preliminary study on the diagnostic value of infrared thermography in children with idiopathic thrombocytopenic purpura].

Idiopathic thrombocytopenic purpura (ITP) is a common bloody disease with a high incidence in children, but its diagnostic method is exclusive diagnosis, and the existing detection techniques are mostly invasive, which may cause secondary injury to patients and also may increase the risk of disease. In order to make up for the lack of the detection method, this study made a preliminary exploration on the diagnosis of children's ITP from the perspective of infrared thermography. In this study, a total of 11 healthy children and 22 ITP children's frontal infrared thermal images were collected, and the pattern characteristic (PFD), average temperature (Troi) and maximum temperature (MAX) characteristics of 7 target areas were extracted. The weighted PFD parameters were correlated with the platelet count commonly used in clinical diagnosis, and the sensitivity and specificity of the weighted PFD parameters for children's ITP were calculated through the receiver operating characteristic curve (ROC). The final results showed that the difference of the weighted PFD parameters between healthy children and ITP children was statistically significant, and the parameters negatively correlated with platelet count. Under the ROC curve, the area under the curve (AUC) of this parameter is as high as 92.1%. Based on the research results of this paper, infrared thermography can clearly show the difference between ITP children and healthy children. It is hoped that the methods proposed in this paper can non-invasively and objectively describe the characteristics of ITP infrared thermal imaging of children, and provide a new ideas for ITP diagnosis.

A research on syndrome element differentiation based on phenomenology and mathematical method.

BACKGROUND: As an empirical medical system independent of conventional Western medicine (CWM), over thousands of years, traditional Chinese medicine (TCM) has established its own unique method of diagnosis and treatment. The perspective of holism and system in TCM is essentially different from the view of Reductionism in CWM. With the development of modern science and technology, the restriction of reductionism is more and more prominent, and researchers begin to pay more attention to holistic thinking in TCM. Confronted with the above situation, there is an urgent need to explore the diagnosis of TCM by the techniques of modern science. METHODS: To explore the feasibility of using modern science to describe and realize the diagnosis of TCM, in this paper, a method of syndrome element differentiation based on phenomenology is proposed. The proposed method is implemented by mathematical mapping, and then it is testified through analysis of 670 medical records: Based on the original mapping data between two data sets (set of syndrome elements and set of clinical manifestations), new mapping data is generated, and thus the corresponding quantitative diagnostic results are calculated and evaluated. Finally, knowledge discovery of the diagnosis results based on attribute partial-ordered structure diagram is conducted. RESULTS: The value order's matching results between original and new results show that the matched degree of each record is no less than 65%, while there are at least 87% records whose matched degree is more than 80%. In addition, the knowledge discoveries of new results are basically identical with the ones of original results as well. CONCLUSION: Using phenomenology to describe syndrome differentiation should be feasible, and further research on mapping relations between various sets (symptoms, formulas, drugs) of TCM should be conducted and evaluated through clinical trials in future.

[MicroRNA Target Prediction Based on Support Vector Machine Ensemble Classification Algorithm of Under-sampling Technique].

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.

[Automatic Classification of Epileptic Electroencephalogram Signal Based on Improved Multivariate Multiscale Entropy].

Traditional sample entropy fails to quantify inherent long-range dependencies among real data. Multiscale sample entropy (MSE) can detect intrinsic correlations in data, but it is usually used in univariate data. To generalize this method for multichannel data, we introduced multivariate multiscale entropy into multiscale signals as a reflection of the nonlinear dynamic correlation. But traditional multivariate multiscale entropy has a large quantity of computation and costs a large period of time and space for more channel system, so that it can not reflect the correlation between variables timely and accurately. In this paper, therefore, an improved multivariate multiscale entropy embeds on all variables at the same time, instead of embedding on a single variable as in the traditional methods, to solve the memory overflow while the number of channels rise, and it is more suitable for the actual multivariate signal analysis. The method was tested in simulation data and Bonn epilepsy dataset. The simulation results showed that the proposed method had a good performance to distinguish correlation data. Bonn epilepsy dataset experiment also showed that the method had a better classification accuracy among the five data set, especially with an accuracy of 100% for data collection of Z and S.

Deep first formal concept search.

The calculation of formal concepts is a very important part in the theory of formal concept analysis (FCA); however, within the framework of FCA, computing all formal concepts is the main challenge because of its exponential complexity and difficulty in visualizing the calculating process. With the basic idea of Depth First Search, this paper presents a visualization algorithm by the attribute topology of formal context. Limited by the constraints and calculation rules, all concepts are achieved by the visualization global formal concepts searching, based on the topology degenerated with the fixed start and end points, without repetition and omission. This method makes the calculation of formal concepts precise and easy to operate and reflects the integrity of the algorithm, which enables it to be suitable for visualization analysis.

[Objective assessment of facial paralysis using infrared thermography and formal concept analysis].

This paper presented a novel approach to objective assessment of facial nerve paralysis based on infrared thermography and formal concept analysis. Sixty five patients with facial nerve paralysis on one side were included in the study. The facial temperature distribution images of these 65 patients were captured by infrared thermography every five days during one-month period. First, the facial thermal images were pre-processed to identify six potential regions of bilateral symmetry by using image segmentation techniques. Then, the temperature differences on the left and right sides of the facial regions were extracted and analyzed. Finally, the authors explored the relationships between the statistical averages of those temperature differences and the House-Brackmann score for objective assessment degree of nerve damage in a facial nerve paralysis by using formal concept analysis. The results showed that the facial temperature distribution of patients with facial nerve paralysis exhibited a contralateral asymmetry, and the bilateral temperature differences of the facial regions were greater than 0.2 degrees C, whereas in normal healthy individuals these temperature differences were less than 0.2 degrees C. Spearman correlation coefficient between the bilateral temperature differences of the facial regions and the degree of facial nerve damage was an average of 0.508, which was statistically significant (p < 0.05). Furthermore, if one of the temperature differences of bilateral symmetry on facial regions was greater than 0.2 degrees C, and all were less than 0.5 degrees C, facial nerve paralysis could be determined as for the mild to moderate; if one of the temperature differences of bilateral symmetry was greater than 0.5 degrees C, facial nerve paralysis could be determined as for serious. In conclusion, this paper presents an automated technique for the computerized analysis of thermal images to objectively assess facial nerve related thermal dysfunction by using formal concept analysis theory, which may benefit the clinical diagnosis and treatment of facial nerve paralysis.

[Application of semi-supervised sparse representation classifier based on help training in EEG classification].

Electroencephalogram (EEG) classification for brain-computer interface (BCI) is a new way of realizing human-computer interreaction. In this paper the application of semi-supervised sparse representation classifier algorithms based on help training to EEG classification for BCI is reported. Firstly, the correlation information of the unlabeled data is obtained by sparse representation classifier and some data with high correlation selected. Secondly, the boundary information of the selected data is produced by discriminative classifier, which is the Fisher linear classifier. The final unlabeled data with high confidence are selected by a criterion containing the information of distance and direction. We applied this novel method to the three benchmark datasets, which were BCI I, BCI II_IV and USPS. The classification rate were 97%, 82% and 84.7%, respectively. Moreover the fastest arithmetic rate was just about 0. 2 s. The classification rate and efficiency results of the novel method are both better than those of S3VM and SVM, proving that the proposed method is effective.

[Research on the methods for inter-class distinctive feature selection for leucocyte recognition based on attribute hierarchical relationship].

To increase efficiency of automated leucocyte pattern recognition using lower feature dimensions, a novel inter-class distinctive feature selection method for chromatic leucocyte images was proposed based on attribute hierarchical relationship. According to the attribute constraints in formal concept analysis, we established a knowledge representation and discovery method based on the hierarchical optimal diagram by defining attribute value and visual representation of optimized hierarchical relationship. It was applied to human peripheral blood leucocytes classification and 12 distinctive attributes were simplified from 60 inter-class attributes, which contributes significantly to reduced feature dimensions and efficient inter-class feature classification. Compared with the classical experimental data, the inter-class distinctive feature selection method based on hierarchical optimal diagram was proved to be usable and effective for six leucocyte pattern recognition.

[Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

[Research on compatibility of prescription of TCP based on the principle of attribute hierarchical graph].

On the basis of the theory of formal concept analysis (FCA), a new method for generation of an attribute hierarchical graph is proposed in this paper. This method can solve the problems of how to mine and express classification knowledge and rules in compatibility of prescription. In this paper, we view prescriptions as objects that possess certain attributes of the named drugs. First, the formal context is established based on theory. Then optimization of the original formal context and extracts the connotation and extension of the concept are followed, constructing attribute hierarchical graph. Finally, useful knowledge from the hierarchical diagram of attributes based on the way of knowledge representation is mined. The result showed that the method for discovering Traditional Chinese Prescription (TCP) diagnostic knowledge is feasible and effectual for small samples. The research of large samples is 13th open question of FCA. It is an international subject to be studied urgently.

[Objective assessment of facial paralysis using local binary pattern in infrared thermography].

Facial paralysis is a frequently-occurring disease, which causes the loss of the voluntary muscles on one side of the face due to the damages the facial nerve and results in an inability to close the eye and leads to dropping of the angle of the mouth. There have been few objective methods to quantitatively diagnose it and assess this disease for clinically treating the patients so far. The skin temperature distribution of a healthy human body exhibits a contralateral symmetry. Facial paralysis usually causes an alteration of the temperature distribution of body with the disease. This paper presents the use of the histogram distance of bilateral local binary pattern (LBP) in the facial infrared thermography to measure the asymmetry degree of facial temperature distribution for objective assessing the severity of facial paralysis. Using this new method, we performed a controlled trial to assess the facial nerve function of the healthy subjects and the patients with Bell's palsy respectively. The results showed that the mean sensitivity and specificity of this method are 0.86 and 0.89 respectively. The correlation coefficient between the asymmetry degree of facial temperature distribution and the severity of facial paralysis is an average of 0.657. Therefore, the histogram distance of local binary pattern in the facial infrared thermography is an efficient clinical indicator with respect to the diagnosis and assessment of facial paralysis.

[A leukocyte pattern recognition based on feature fusion in multi-color space].

To solve the ineffective problem of leukocytes classification based on multi-feature fusion in a single color space, we proposed an automatic leukocyte pattern recognition by means of feature fusion with color histogram and texture granular in multi-color space. The interactive performance of three color spaces (RGB, HSV and Lab), two features (color histogram and texture granular) and four similarity measured distance metrics (normalized intersection, Euclidean distance, chi2-metric distance and Mahalanobis distance) were discussed. The optimized classification modes of high precision, extensive universality and low cost to different leukocyte types were obtained respectively, and then the recognition system of tree-integration of the optimized modes was established. The experimental results proved that the performance of the fusion classification was improved by 12.3% at least.

[Research on automatic external defibrillator based on DSP].

Electrical defibrillation is the most effective way to treat the ventricular tachycardia (VT) and ventricular fibrillation (VF). An automatic external defibrillator based on DSP is introduced in this paper. The whole design consists of the signal collection module, the microprocessor controlingl module, the display module, the defibrillation module and the automatic recognition algorithm for VF and non VF, etc. This automatic external defibrillator has achieved goals such as ECG signal real-time acquisition, ECG wave synchronous display, data delivering to U disk and automatic defibrillate when shockable rhythm appears, etc.

[Symbolic dynamics analysis of epileptic EEG signals of the rat].

Epilepsy is a common chronic neurological disease, which is caused by excessive brain neuron discharge. The epileptic seizure has the characteristic of abruptness and reiteration. Prediction of seizures has great significance for patients to take timely and effective clinical measures. The symbolic dynamics method was introduced to analyze absence epilepsy EEG. The key parameters affecting the symbolic statistical quantities were discussed. The symbolic entropy and time irreversebility were calculated in different epilepsy stages. It was found that the symbolic entropy and the time irreversebility were rather big in interictal stage. The two parameters declined significantly during the transformation process from interictal stage to ictal stage and maintained lower value during ictal stage. The results showed that the symbolic dynamics method could reflect the changes of epilepsy EEG. The symbolic entropy and time irreversebility are sensitive features indicating different stages of seizures and have potential important clinical applications.

[Using infrared thermal asymmetry analysis for objective assessment of the lesion of facial nerve function].

The skin temperature distribution of a healthy human body exhibits a contralateral symmetry. Some lesions of facial nerve function are associated with an alteration of the thermal distribution of the human body. Since the dissipation of heat through the skin occurs for the most part in the form of infrared radiation, infrared thermography is the method of choice to capture the alteration of the infrared thermal distribution. This paper presents a new method of analysis of the thermal asymmetry named effective thermal area ratio, which is a product of two variables. The first variable is mean temperature difference between the specific facial region and its contralateral region. The second variable is a ratio, which is equal to the area of the abnormal region divided by the total area. Using this new method, we performed a controlled trial to assess the facial nerve function of the healthy subjects and the patients with Bell's palsy respectively. The results show: that the mean specificity and sensitivity of this method are 0.90 and 0.87 respectively, improved by 7% and 26% compared with conventional methods. Spearman correlation coefficient between effective thermal area ratio and the degree of facial nerve function is an average of 0.664. Hence, concerning the diagnosis and assessment of facial nerve function, infrared thermography is a powerful tool; while the effective ther mal area ratio is an efficient clinical indicator.

[Application of the quality evaluation of traditional Chinese herbal medicines using chromatography of fingerprints].

Chromatography of fingerprint as an important tool has been used in identification and quality control of herbal medicines, and it is gaining more and more attention. Among the various methods, chromatography gradually becomes the mainstream for its characteristics. This paper describes the techniques of chromatography of fingerprint including pretreatments for sample data set, the establishment of chromatographic fingerprint and fingerprint visualization. It emphasizes several analysis methods and their scope of application. Visualization technology combined with fingerprint makes analysis more intuitive. Finally, existing key problems and future works were also discussed.

[Research progress in using functional near-infrared spectroscopy for monitoring depth of anesthesia].

Intra-operation monitoring depth of anesthesia is an important method to insure the quality and safety of clinical anesthesia. As a noninvasive brain function monitoring technology, functional near-infrared spectroscopy can provide objective and reliable brain activity monitoring and imaging in real time. The characteristic of this technique is highly suitable for interrelated research on depth of anesthesia monitoring. The present paper briefly introduced the fundamental and instruments of functional near-infrared spectroscopy, reviewed the current situation about the application of functional near-infrared spectroscopy in research on depth of anesthesia monitoring, pointed out the possible way of using functional near-infrared spectroscopy in depth of anesthesia monitoring research, and expounded the unsolved problems and future prospects.

[Extraction method of the visual graphical feature from biomedical data].

The vector space transformations such as principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (ICA) or the kernel-based methods may be applied on the extracted feature from the field, which could improve the classification performance. A barycentre graphical feature extraction method of the star plot was proposed in the present study based on the graphical representation of multi-dimensional data. The feature order question of the graphical representation methods affecting the star plot was investigated and the feature order method was proposed based on the improved genetic algorithm (GA). For some biomedical datasets, such as breast cancer and diabetes, the obtained classification error of barycentre graphical feature of star plot in the GA based optimal feature order is very promising compared to the previously reported classification methods, and is superior to that of traditional feature extraction method.