Fetal electrocardiogram signal extraction and analysis method combining fast independent component analysis algorithm and convolutional neural network / 生物医学工程学杂志

Fetal electrocardiogram (ECG) signals provide important clinical information for early diagnosis and intervention of fetal abnormalities. In this paper, we propose a new method for fetal ECG signal extraction and analysis. Firstly, an improved fast independent component analysis method and singular value decomposition algorithm are combined to extract high-quality fetal ECG signals and solve the waveform missing problem. Secondly, a novel convolutional neural network model is applied to identify the QRS complex waves of fetal ECG signals and effectively solve the waveform overlap problem. Finally, high quality extraction of fetal ECG signals and intelligent recognition of fetal QRS complex waves are achieved. The method proposed in this paper was validated with the data from the PhysioNet computing in cardiology challenge 2013 database of the Complex Physiological Signals Research Resource Network. The results show that the average sensitivity and positive prediction values of the extraction algorithm are 98.21% and 99.52%, respectively, and the average sensitivity and positive prediction values of the QRS complex waves recognition algorithm are 94.14% and 95.80%, respectively, which are better than those of other research results. In conclusion, the algorithm and model proposed in this paper have some practical significance and may provide a theoretical basis for clinical medical decision making in the future.

Similar Drug Proposals Based on Package Inserts Using Latent Semantic Analysis / 医薬品情報学

Objective:The topic model is a well-known method used in the field of natural language processing (NLP)that defines adocument as constructed of topics that combine specific t erms. This method is used to model topic co-occurrencemathematically. In this study,we extracted topics from featu re vectors of explicit documents called medical package insertsby using cluster analysis. Methods:We counted the terms(nouns)recognized by the morphological analysis engine MeCab and created a documentterm matrix. A value of“tf・idf”was calculated in this matrix for term weighting to avoid the effect of term frequency. We reduced the dimensionality of the matrix using singular v alue decomposition,which removed unnecessary data,and weextracted feature vectors attributed to each medical package insert. The distance between feature vectors was calculatedusing cosine distance,and cluster analysis was performed based on the distance between the vectors.Results:Cluster analysis on our document-term matrix show ed that medical package inserts of drugs that have the sameefficacy or active ingredient were included in the same cl uster. Moreover, using term weighting and dimensionalityreduction,we could extract topics from medical package inserts.Conclusion:We obtained a foothold to apply our findings t o the recommendation of similar drugs. Cluster analysis ofmedical package inserts using NLP can contribute to the pro per application of drugs. In addition,our study revealed thesimilarities of drugs and suggested possibilities for new applications from several points of view.

Study on TCM Pathogenesis of Nonalcoholic Fatty Liver Disease Based on Multivariate Statistical Analysis / 中国中医药信息杂志

Objective To explore the TCM pathogenesis regularity of nonalcoholic fatty liver disease (NAFLD);To provide basis for clinical syndrome differentiation and treatment. Methods A cross-sectional study was used. The clinical observation form of NAFLD was used to collect the patient data. Factor analysis and singular value decomposition methods were used to study the internal factors of the four diagnostic characteristics. The differences between the various analytical methods were compared. Results Factor analysis used the α factor analysis method, the principal component method, and the image factor method. The results of α-factor analysis were the best. The first three factors had the highest explanatory rates of data, namely spleen-dampness factor, kidney deficiency factor and qi deficiency factor, which constituted the basic pathogenesis factor of NAFLD. The singular value decomposition method obtained 3 singular values, namely spleen and kidney qi deficiency, liver and kidney yin deficiency, and qi and yin deficiency, also highlighted the spleen and kidney deficiency in the pathogenesis of NAFLD. Conclusion Spleen-kidney deficiency plays an important role in the pathogenesis of NAFLD. Treatment based on deficiency for nonalcoholic fatty liver disease has great clinical significance.

Quantification method for MRSI based on Hankel matrix / 国际生物医学工程杂志

Objective To study the quantification method based on Hankel matrix,the water suppression method and the metabolite imaging method for magnetic resonance spectroscopic imaging (MRSI) data.Methods Impact of Hankel data matrix on quantification MRSI methods were analyzed to obtain the most efficient Hankel matrix structure.The maximum amplitude method of the water signal peak was proposed for MRSI data water suppression.The interested metabolites information was extracted from MRSI data,and then metabolite image was obtained through bilinear interpolation algorithm.Results The minimum amplitude error and the minimum frequency error were acquired when columns number was 3/4 sampling points.The amplitude,frequency and the damping factor of the simulation data accuracy was 96.94％,99.72％ and 95.55％ respectively.Hankel lanczos with partial reorthogonalization singular value decomposition (HLSVDPRO) method with 3/4 sampling points was used to form Hankel matrices.The speed of quantification decreased with the increase of sampling points.The error of quantification parameter reached minimum when the number of sampling points was 512.The water suppression degree of simulation data was 99.55％ with the maximum amplitude water suppression method.Conclusions The accuracy and the speed of the quantification are promoted with an optimized Hankel matrix structure for the MRSI quantization method.The optimal length of sampling points is 512.The maximum amplitude method can suppress water perfectly.Doctors can detect the presence of tumor regions in human body at the (super) early stage by metabolite information images.

Using linear algebra for protein structural comparison and classification

In this article, we describe a novel methodology to extract semantic characteristics from protein structures using linear algebra in order to compose structural signature vectors which may be used efficiently to compare and classify protein structures into fold families. These signatures are built from the pattern of hydrophobic intrachain interactions using Singular Value Decomposition (SVD) and Latent Semantic Indexing (LSI) techniques. Considering proteins as documents and contacts as terms, we have built a retrieval system which is able to find conserved contacts in samples of myoglobin fold family and to retrieve these proteins among proteins of varied folds with precision of up to 80 percent. The classifier is a web tool available at our laboratory website. Users can search for similar chains from a specific PDB, view and compare their contact maps and browse their structures using a JMol plug-in.

Cooperative binding interaction of ethidium with allosteric DNA

The specific association of drugs with deoxyoligonucleotides, containing a B-Z junction between left-handed Z-DNA and right-handed B-DNA, was examined by fluorescence and circular dichroism (CD) technique. Ethidium was chosen for a simple DNA binding compound because it binds to right-handed DNA and hybrid B-Z forms containing a B-Z junction in a highly cooperative manner. The binding isotherms were analyzed by an allosteric model in order to describe the cooperativity of association. Binding of ethidium to the DNA that are initially in the hybrid B-Z forms showed over an order of magnitude higher affinity than other DNA which were entirely in the B-form. The conformational transitions of deoxyoligonucleotides containing a B-Z junction as a result of ethidium binding were monitored by CD and the influence of NaCl on the complex formation was also determined by the CD spectra. The singular value decomposition (SVD) analysis was used to characterize a family of CD spectra of the species in binding equilibria. The results of SVD analysis showed a strikingly complex thermodynamic equilibria of cooperative binding of drugs to the allosterically converted DNA forms. The results also showed that these DNA forms in low- and high-salt were different in the absence or presence of drug. These results demonstrate that DNA-binding-drugs can preferentially interact with specific DNA structures and that these interactions are accompanied by allosteric changes of DNA conformations.

Protein secondary structure from circular dichroism spectra.

Circular dichroism spectra of proteins are extremely sensitive to secondary structure. Nevertheless, circular dichroism spectra should not be analyzed for protein secondary structure unless they are measured to at least 184 nm. Even if all the various types of β-turns are lumped together, there are at least 5 different types of secondary structure in a protein (α-helix, antiparallel β-sheet, parallel β-sheet, β-turn, and other structures not included in the first 4 categories). It is not possible to solve for these 5 parameters unless there are 5 equations. Singular value decomposition can be used to show that circular dichroism spectra of proteins measured to 200 nm contain only 2 pieces of information, while spectra measured to 190 nm contain about 4. Adding the constraint that the sum of secondary structures must equal 1 provides another piece of information, but even with this constraint, spectra measured to 190 nm simply do not analyze well for the 5 unknowns in secondary structure. Spectra measured to 184 nm do contain 5 pieces of information and we have used such spectra successfully to analyze a variety of proteins for their component secondary structures.