Application of near infrared spectroscopy to predict contents of various lactones in chromatographic process of Ginkgo Folium / 中国中药杂志

This study established a method for rapid quantification of terpene lactone, bilobalide, ginkgolide C, ginkgolide A and ginkgolide B in the chromatographic process of Ginkgo Folium based on near infrared spectroscopy(NIRS). The effects of competitive adaptive reweighting sampling(CARS), random frog(RF), and synergy interval partial least squares(siPLS) on the performance of partial least squares regression(PLSR) model were compared to the reference values measured by HPLC. Among them, the correlation coefficients of prediction(Rp) of validation sets of terpene lactone, bilobalide, and ginkgolide C were all higher than 0.98, and the relative standard errors of prediction(RSEPs) were 5.87%, 6.90% and 6.63%, respectively. Aiming at ginkgolide A and ginkgolide B with relatively low content, the genetic algorithm joint extreme learning machine(GA-ELM) was used to establish the optimized quantitative analysis model. Compared with CARS-PLSR model, the CARS-GA-ELM models of ginkgolide A and ginkgolide B exhibited a reduction in RSEP from 15.65% to 8.52% and from 21.28% to 10.84%, respectively, which met the needs of quantitative ana-lysis. It has been proved that NIRS can be used for the rapid detection of various lactone components in the chromatographic process of Ginkgo Folium.

Application of an extreme learning machine network with particle swarm optimization in syndrome classification of primary liver cancer / 中西医结合学报

OBJECTIVE@#By optimizing the extreme learning machine network with particle swarm optimization, we established a syndrome classification and prediction model for primary liver cancer (PLC), classified and predicted the syndrome diagnosis of medical record data for PLC and compared and analyzed the prediction results with different algorithms and the clinical diagnosis results. This paper provides modern technical support for clinical diagnosis and treatment, and improves the objectivity, accuracy and rigor of the classification of traditional Chinese medicine (TCM) syndromes.@*METHODS@#From three top-level TCM hospitals in Nanchang, 10,602 electronic medical records from patients with PLC were collected, dating from January 2009 to May 2020. We removed the electronic medical records of 542 cases of syndromes and adopted the cross-validation method in the remaining 10,060 electronic medical records, which were randomly divided into a training set and a test set. Based on fuzzy mathematics theory, we quantified the syndrome-related factors of TCM symptoms and signs, and information from the TCM four diagnostic methods. Next, using an extreme learning machine network with particle swarm optimization, we constructed a neural network syndrome classification and prediction model that used "TCM symptoms + signs + tongue diagnosis information + pulse diagnosis information" as input, and PLC syndrome as output. This approach was used to mine the nonlinear relationship between clinical data in electronic medical records and different syndrome types. The accuracy rate of classification was used to compare this model to other machine learning classification models.@*RESULTS@#The classification accuracy rate of the model developed here was 86.26%. The classification accuracy rates of models using support vector machine and Bayesian networks were 82.79% and 85.84%, respectively. The classification accuracy rates of the models for all syndromes in this paper were between 82.15% and 93.82%.@*CONCLUSION@#Compared with the case of data processed using traditional binary inputs, the experiment shows that the medical record data processed by fuzzy mathematics was more accurate, and closer to clinical findings. In addition, the model developed here was more refined, more accurate, and quicker than other classification models. This model provides reliable diagnosis for clinical treatment of PLC and a method to study of the rules of syndrome differentiation and treatment in TCM.

Rapid determination of active components in Ginkgo biloba leaves by near infrared spectroscopy combined with genetic algorithm joint extreme learning machine / 中国中药杂志

Near-infrared spectroscopy(NIRS) combined with band screening method and modeling algorithm can be used to achieve the rapid and non-destructive detection of the traditional Chinese medicine(TCM) production process. This paper focused on the ginkgo leaf macroporous resin purification process, which is the key technology of Yinshen Tongluo Capsules, in order to achieve the rapid determination of quercetin, kaempferol and isorhamnetin in effluent. The abnormal spectrum was eliminated by Mahalanobis distance algorithm, and the data set was divided by the sample set partitioning method based on joint X-Y distances(SPXY). The key information bands were selected by synergy interval partial least squares(siPLS); based on that, competitive adaptive reweighted sampling(CARS), successive projections algorithm(SPA) and Monte Carlo uninformative variable(MC-UVE) were used to select wavelengths to obtain less but more critical variable data. With selected key variables as input, the quantitative analysis model was established by genetic algorithm joint extreme learning machine(GA-ELM) algorithm. The performance of the model was compared with that of partial least squares regression(PLSR). The results showed that the combination with siPLS-CARS-GA-ELM could achieve the optimal model performance with the minimum number of variables. The calibration set correlation coefficient R_c and the validation set correlation coefficient R_p of quercetin, kaempferol and isorhamnetin were all above 0.98. The root mean square error of calibration(RMSEC), the root mean square error of prediction(RMSEP) and the relative standard errors of prediction(RSEP) were 0.030 0, 0.029 2 and 8.88%, 0.041 4, 0.034 8 and 8.46%, 0.029 3, 0.027 1 and 10.10%, respectively. Compared with the PLSR me-thod, the performance of the GA-ELM model was greatly improved, which proved that NIRS combined with GA-ELM method has a great potential for rapid determination of effective components of TCM.

Single-modal neuroimaging computer aided diagnosis for schizophrenia based on ensemble learning using privileged information / 生物医学工程学杂志

Neuroimaging technologies have been applied to the diagnosis of schizophrenia. In order to improve the performance of the single-modal neuroimaging-based computer-aided diagnosis (CAD) for schizophrenia, an ensemble learning algorithm based on learning using privileged information (LUPI) was proposed in this work. Specifically, the extreme learning machine based auto-encoder (ELM-AE) was first adopted to learn new feature representation for the single-modal neuroimaging data. Random project algorithm was then performed on the learned high-dimensional features to generate several new feature subspaces. After that, multiple feature pairs were built among these subspaces to work as source domain and target domain, respectively, which were used to train multiple support vector machine plus (SVM+) classifier. Finally, a strong classifier is learned by combining these SVM+ classifiers for classification. The proposed algorithm was evaluated on a public schizophrenia neuroimaging dataset, including the data of structural magnetic resonance imaging (sMRI) and functional MRI (fMRI). The results showed that the proposed algorithm achieved the best diagnosis performance. In particular, the classification accuracy, sensitivity and specificity of the proposed algorithm were 72.12% ± 8.20%, 73.50% ± 15.44% and 70.93% ± 12.93%, respectively, on the sMRI data, and it also achieved the classification accuracy of 72.33% ± 8.95%, sensitivity of 68.50% ± 16.58% and specificity of 75.73% ± 16.10% on the fMRI data. The proposed algorithm overcomes the problem that the traditional LUPI methods need the additional privileged information modality as source domain. It can be directly applied to the single-modal data for classification, and also can improve the classification performance. Therefore, it suggests that the proposed algorithm will have wider applications.

Kernel extreme learning machine in diagnosis of benign and malignant mass-like breast lesions / 中国医学影像技术

Objective To classify benign and malignant breast mass-like lesions by using kernel extreme learning machine (KELM), and to evaluate its effectiveness in differential diagnosis. Methods Totally 93 patients with 103 breast mass-like lesions confirmed by postoperative pathology or long-term follow-up underwent MRI. According to the breast imaging report and data system (BI-RADS) scoring guidelines, 12 MR imaging features and clinical features were selected. Then benign and malignant lesions were classified by one junior and one senior radiologist independently. The diagnostic efficacy was calculated. Results The sensitivity, specificity and accuracy of KELM in differential diagnosis of benign and malignant breast mass-like lesions were 0.88, 0.89, 0.91 and 0.93, 0.91, 0.92 for junior and senior doctor respectively, and AUC was 0.84 and 0.89. The sensitivity, specificity and accuracy of independent diagnosis of junior and senior doctor were 0.91, 0.74, 0.86 and 0.90, 0.85, 0.92, respectively, and AUC was 0.83 and 0.90, respectively. Conclusion KELM based on imaging features and clinical data can be used as asssitant in differential diagnosis of benign and malignant mass-like breast lesions, which has ideal sensitivity, specificity and accuracy.

A new method for classification of Alzheimer's disease combined with structural magnetic resonance imaging texture features / 生物医学工程学杂志

In this paper, a new method for the classification of Alzheimer's disease (AD) using multi-feature combination of structural magnetic resonance imaging is proposed. Firstly, hippocampal segmentation and cortical thickness and volume measurement were performed using FreeSurfer software. Then, histogram, gradient, length of gray level co-occurrence matrix and run-length matrix were used to extract the three-dimensional (3D) texture features of the hippocampus, and the parameters with significant differences between AD, MCI and NC groups were selected for correlation study with MMSE score. Finally, AD, MCI and NC are classified and identified by the extreme learning machine. The results show that texture features can provide better classification results than volume features on both left and right sides. The feature parameters with complementary texture, volume and cortical thickness had higher classification recognition rate, and the classification accuracy of the right side (100%) was higher than that of the left side (91.667%). The results showed that 3D texture analysis could reflect the pathological changes of hippocampal structures of AD and MCI patients, and combined with multi-feature analysis, it could better reflect the essential differences between AD and MCI cognitive impairment, which was more conducive to clinical differential diagnosis.

Application of extreme learning machine model in prediction of hand-foot-and-mouth disease incidence in Zhangjiakou city / 第二军医大学学报

Objective To explore the application of extreme learning machine (ELM) model in predicting the incidence of hand-foot-and-mouth disease, and to compare the difference between ELM model and neural network model. Methods The monthly incidence data of hand-foot-and-mouth disease from May 2008 to Jul. 2017 in Zhangjiakou were collected and formed a time series with 111 data. To validate and evaluate the prediction performance of the two models, 75% of the randomly selected dataset were used to train model and the remaining 25% were used as testing data for prediction. Results and conclusion The mean relative errors (MREs) of learning and prediction based on ELM model were 0.05 and 0.07, respectively. The MREs of learning and prediction based on neural network model were 0.09 and 0.12, respectively. The learning and prediction effects of ELM model are better than neural network model. It can improve the accuracy of prediction and has high application value.

Qualitative Prediction of Yeast Growth Process Based on Near Infrared Spectroscopy / 分析化学

To improve the yield of industrial fermentation, a method based on near infrared spectroscopy was presented to predict the growth of yeast.The spectral data of fermentation sample were measured by Fourier-transform near-infrared (FT-NIR) spectrometer in the process of yeast culture.Each spectrum was acquired over the range of 10000-4000 cm1.Meanwhile, the optical density (OD) of fermentation sample was determined with photoelectric turbidity method.After that, a method based on competitive adaptive reweighted sampling (CARS) was used to select characteristic wavelength variables of NIR data, and then extreme learning machine (ELM) algorithm was employed to develop the categorization model about the four growth processes of yeast.Experimental result showed that, only 30 characteristic wavelength variables of NIR data were selected by CRAS algorithms, and the prediction accuracies of training set and test set of the CARS-ELM model were 98.68% and 97.37%, respectively.The research showed that the near infrared spectrum analysis technology was feasible to predict the growth process of yeast.

Classification of BMI Control Commands Using Extreme Learning Machine from Spike Trains of Simultaneously Recorded 34 CA1 Single Neural Signals

A recently developed machine learning algorithm referred to as Extreme Learning Machine (ELM) was used to classify machine control commands out of time series of spike trains of ensembles of CA1 hippocampus neurons (n=34) of a rat, which was performing a target-to-goal task on a two-dimensional space through a brain-machine interface system. Performance of ELM was analyzed in terms of training time and classification accuracy. The results showed that some processes such as class code prefix, redundancy code suffix and smoothing effect of the classifiers' outputs could improve the accuracy of classification of robot control commands for a brain-machine interface system.