Chinese medicine (CM) diagnosis intellectualization is one of the hotspots in the research of CM modernization. The traditional CM intelligent diagnosis models transform the CM diagnosis issues into classification issues, however, it is difficult to solve the problems such as excessive or similar categories. With the development of natural language processing techniques, text generation technique has become increasingly mature. In this study, we aimed to establish the CM diagnosis generation model by transforming the CM diagnosis issues into text generation issues. The semantic context characteristic learning capacity was enhanced referring to Bidirectional Long Short-Term Memory (BILSTM) with Transformer as the backbone network. Meanwhile, the CM diagnosis generation model Knowledge Graph Enhanced Transformer (KGET) was established by introducing the knowledge in medical field to enhance the inferential capability. The KGET model was established based on 566 CM case texts, and was compared with the classic text generation models including Long Short-Term Memory sequence-to-sequence (LSTM-seq2seq), Bidirectional and Auto-Regression Transformer (BART), and Chinese Pre-trained Unbalanced Transformer (CPT), so as to analyze the model manifestations. Finally, the ablation experiments were performed to explore the influence of the optimized part on the KGET model. The results of Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation 1 (ROUGE1), ROUGE2 and Edit distance of KGET model were 45.85, 73.93, 54.59 and 7.12, respectively in this study. Compared with LSTM-seq2seq, BART and CPT models, the KGET model was higher in BLEU, ROUGE1 and ROUGE2 by 6.00-17.09, 1.65-9.39 and 0.51-17.62, respectively, and lower in Edit distance by 0.47-3.21. The ablation experiment results revealed that introduction of BILSTM model and prior knowledge could significantly increase the model performance. Additionally, the manual assessment indicated that the CM diagnosis results of the KGET model used in this study were highly consistent with the practical diagnosis results. In conclusion, text generation technology can be effectively applied to CM diagnostic modeling. It can effectively avoid the problem of poor diagnostic performance caused by excessive and similar categories in traditional CM diagnostic classification models. CM diagnostic text generation technology has broad application prospects in the future.
Humans ; Medicine, Chinese Traditional ; Pattern Recognition, Automated ; Asian People ; Language ; Learning

Bibliometric and scientific knowledge graph methods were used to analyze the research status and hot spots of acupuncture-moxibustion in treatment of myofascial pain syndrome (MPS) and explore its development trend. The articles of both Chinese and English versions relevant to MPS treated by acupuncture-moxibustion were searched in CNKI, VIP, Wanfang, SinoMed and WOS from the database inception to March 20, 2023. Using Excel2016, CiteSpace6.2.R2 and VOSviewer1.6.18, the visual analysis was conducted by means of the cooperative network, keyword co-occurrence, keyword timeline, keyword emergence, etc. From Chinese databases and WOS database, 910 Chinese articles and 300 English articles were included, respectively. The annual publication volume showed an overall rising trend. Literature output of English articles was concentrated in Spain, China, and the United States, of which, there was less cross-regional cooperation. In the keyword analysis, regarding acupuncture-moxibustion therapy, Chinese articles focused on "acupuncture", "electroacupuncture" and "acupotomy"; while, "dry needling" and "injection" were dominated for English one. Clinical study was the current hot spot in Chinese databases, in comparison, the randomized controlled double-blind clinical trial was predominant in WOS. Both Chinese and English articles were limited in the report of mechanism research. The cooperation among research teams should be strengthened to conduct comparative research, dose-effect research and effect mechanism research with different methods of acupuncture-moxibustion involved so that the evidences can be provided for deeper exploration.
Humans ; Moxibustion ; Pattern Recognition, Automated ; Acupuncture Therapy ; Myofascial Pain Syndromes/therapy* ; Electroacupuncture

BACKGROUND: Distinguishing between primary clear cell carcinoma of the liver (PCCCL) and common hepatocellular carcinoma (CHCC) through traditional inspection methods before the operation is difficult. This study aimed to establish a Faster region-based convolutional neural network (RCNN) model for the accurate differential diagnosis of PCCCL and CHCC. METHODS: In this study, we collected the data of 62 patients with PCCCL and 1079 patients with CHCC in Beijing YouAn Hospital from June 2012 to May 2020. A total of 109 patients with CHCC and 42 patients with PCCCL were randomly divided into the training validation set and the test set in a ratio of 4:1.The Faster RCNN was used for deep learning of patients' data in the training validation set, and established a convolutional neural network model to distinguish PCCCL and CHCC. The accuracy, average precision, and the recall of the model for diagnosing PCCCL and CHCC were used to evaluate the detection performance of the Faster RCNN algorithm. RESULTS: A total of 4392 images of 121 patients (1032 images of 33 patients with PCCCL and 3360 images of 88 patients with CHCC) were uesd in test set for deep learning and establishing the model, and 1072 images of 30 patients (320 images of nine patients with PCCCL and 752 images of 21 patients with CHCC) were used to test the model. The accuracy of the model for accurately diagnosing PCCCL and CHCC was 0.962 (95% confidence interval [CI]: 0.931-0.992). The average precision of the model for diagnosing PCCCL was 0.908 (95% CI: 0.823-0.993) and that for diagnosing CHCC was 0.907 (95% CI: 0.823-0.993). The recall of the model for diagnosing PCCCL was 0.951 (95% CI: 0.916-0.985) and that for diagnosing CHCC was 0.960 (95% CI: 0.854-0.962). The time to make a diagnosis using the model took an average of 4 s for each patient. CONCLUSION The Faster RCNN model can accurately distinguish PCCCL and CHCC. This model could be important for clinicians to make appropriate treatment plans for patients with PCCCL or CHCC.
Humans ; Liver Neoplasms/pathology* ; Retrospective Studies ; Carcinoma, Hepatocellular/pathology* ; Neural Networks, Computer

The present study aims to establish comprehensive evaluation models of physical fitness of the elderly based on machine learning, and provide an important basis to monitor the elderly's physique. Through stratified sampling, the elderly aged 60 years and above were selected from 10 communities in Nanchang City. The physical fitness of the elderly was measured by the comprehensive physical assessment scale based on our previous study. Fuzzy neural network (FNN), support vector machine (SVM) and random forest (RF) models for comprehensive physical evaluation of the elderly people in communities were constructed respectively. The accuracy, sensitivity and specificity of the comprehensive physical fitness evaluation models constructed by FNN, SVM and RF were above 0.85, 0.75 and 0.89, respectively, with the FNN model possessing the best prediction performance. FNN, RF and SVM models are valuable in the comprehensive evaluation and prediction of physical fitness, which can be used as tools to carry out physical evaluation of the elderly.
Aged ; Humans ; Physical Fitness ; Neural Networks, Computer ; Exercise ; Machine Learning

OBJECTIVE: This study aimed to develop an artificial neural network (ANN) model combined with dietary retinol intake from different sources to predict the risk of non-alcoholic fatty liver disease (NAFLD) in American adults. METHODS: Data from the 2007 to 2014 National Health and Nutrition Examination Survey (NHANES) 2007-2014 were analyzed. Eligible subjects ( n = 6,613) were randomly divided into a training set ( n ₁ = 4,609) and a validation set ( n ₂ = 2,004) at a ratio of 7:3. The training set was used to identify predictors of NAFLD risk using logistic regression analysis. An ANN was established to predict the NAFLD risk using a training set. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the accuracy of the model using the training and validation sets. RESULTS: Our study found that the odds ratios ( ORs) and 95% confidence intervals ( CIs) of NAFLD for the highest quartile of plant-derived dietary retinol intake (i.e., provitamin A carotenoids, such as β-carotene) ( OR = 0.75, 95% CI: 0.57 to 0.99) were inversely associated with NAFLD risk, compared to the lowest quartile of intake, after adjusting for potential confounders. The areas under the ROC curves were 0.874 and 0.883 for the training and validation sets, respectively. NAFLD occurs when its incidence probability is greater than 0.388. CONCLUSION The ANN model combined with plant-derived dietary retinol intake showed a significant effect on NAFLD. This could be applied to predict NAFLD risk in the American adult population when government departments formulate future health plans.
Adult ; Humans ; Vitamin A ; Non-alcoholic Fatty Liver Disease/epidemiology* ; Nutrition Surveys ; Diet ; Neural Networks, Computer

To realize the non-destructive and rapid origin discrimination of Poria cocos in batches, this study established the P. cocos origin recognition model based on hyperspectral imaging combined with machine learning. P. cocos samples from Anhui, Fujian, Guangxi, Hubei, Hunan, Henan and Yunnan were used as the research objects. Hyperspectral data were collected in the visible and near infrared band(V-band, 410-990 nm) and shortwave infrared band(S-band, 950-2 500 nm). The original spectral data were divided into S-band, V-band and full-band. With the original data(RD) of different bands, multiplicative scatter correction(MSC), standard normal variation(SNV), S-G smoothing(SGS), first derivative(FD), second derivative(SD) and other pretreatments were carried out. Then the data were classified according to three different types of producing areas: province, county and batch. The origin identification model was established by partial least squares discriminant analysis(PLS-DA) and linear support vector machine(LinearSVC). Finally, confusion matrix was employed to evaluate the optimal model, with F1 score as the evaluation standard. The results revealed that the origin identification model established by FD combined with LinearSVC had the highest prediction accuracy in full-band range classified by province, V-band range by county and full-band range by batch, which were 99.28%, 98.55% and 97.45%, respectively, and the overall F1 scores of these three models were 99.16%, 98.59% and 97.58%, respectively, indicating excellent performance of these models. Therefore, hyperspectral imaging combined with LinearSVC can realize the non-destructive, accurate and rapid identification of P. cocos from different producing areas in batches, which is conducive to the directional research and production of P. cocos.
Hyperspectral Imaging ; Wolfiporia ; China ; Least-Squares Analysis ; Support Vector Machine

Puerariae Lobatae Radix, the dried root of Pueraria lobata, is a traditional Chinese medicine with a long history. Puerariae Lobatae Caulis as an adulterant is always mixed into Puerariae Lobatae Radix for sales in the market. This study employed hyperspectral imaging(HSI) to distinguish between the two products. VNIR lens(spectral scope of 410-990 nm) and SWIR lens(spectral scope of 950-2 500 nm) were used for image acquiring. Multi-layer perceptron(MLP), partial least squares discriminant analysis(PLS-DA), and support vector machine(SVM) were employed to establish the full-waveband models and select the effective wavelengths for the distinguishing between Puerariae Lobatae Caulis and Puerariae Lobatae Radix, which provided technical and data support for the development of quick inspection equipment based on HSI. The results showed that MLP model outperformed PLS-DA and SVM models in the accuracy of discrimination with full wavebands in VNIR, SWIR, and VNIR+SWIR lens, which were 95.26%, 99.11%, and 99.05%, respectively. The discriminative band selection(DBS) algorithm was employed to select the effective wavelengths, and the discrimination accuracy was 93.05%, 98.05%, and 98.74% in the three different spectral scopes, respectively. On this basis, the MLP model combined with the effective wavelengths within the range of 2 100-2 400 nm can achieve the accuracy of 97.74%, which was close to that obtained with the full waveband. This waveband can be used to develop quick inspection devices based on HSI for the rapid and non-destructive distinguishing between Puerariae Lobatae Radix and Puerariae Lobatae Caulis.
Pueraria ; Hyperspectral Imaging ; Medicine, Chinese Traditional ; Algorithms ; Neural Networks, Computer

With inherent sparse spike-based coding and asynchronous event-driven computation, spiking neural network (SNN) is naturally suitable for processing event stream data of event cameras. In order to improve the feature extraction and classification performance of bio-inspired hierarchical SNNs, in this paper an event camera object recognition system based on biological synaptic plasticity is proposed. In our system input event streams were firstly segmented adaptively using spiking neuron potential to improve computational efficiency of the system. Multi-layer feature learning and classification are implemented by our bio-inspired hierarchical SNN with synaptic plasticity. After Gabor filter-based event-driven convolution layer which extracted primary visual features of event streams, we used a feature learning layer with unsupervised spiking timing dependent plasticity (STDP) rule to help the network extract frequent salient features, and a feature learning layer with reward-modulated STDP rule to help the network learn diagnostic features. The classification accuracies of the network proposed in this paper on the four benchmark event stream datasets were better than the existing bio-inspired hierarchical SNNs. Moreover, our method showed good classification ability for short event stream input data, and was robust to input event stream noise. The results show that our method can improve the feature extraction and classification performance of this kind of SNNs for event camera object recognition.
Visual Perception ; Learning ; Action Potentials ; Neural Networks, Computer ; Neuronal Plasticity

In order to fully explore the neural oscillatory coupling characteristics of patients with mild cognitive impairment (MCI), this paper analyzed and compared the strength of the coupling characteristics for 28 MCI patients and 21 normal subjects under six different-frequency combinations. The results showed that the difference in the global phase synchronization index of cross-frequency coupling under δ-θ rhythm combination was statistically significant in the MCI group compared with the normal control group ( P = 0.025, d = 0.398). To further validate this coupling feature, this paper proposed an optimized convolutional neural network model that incorporated a time-frequency data enhancement module and batch normalization layers to prevent overfitting while enhancing the robustness of the model. Based on this optimized model, with the phase locking value matrix of δ-θ rhythm combination as the single input feature, the diagnostic accuracy of MCI patients was (95.49 ± 4.15)%, sensitivity and specificity were (93.71 ± 7.21)% and (97.50 ± 5.34)%, respectively. The results showed that the characteristics of the phase locking value matrix under the combination of δ-θ rhythms can adequately reflect the cognitive status of MCI patients, which is helpful to assist the diagnosis of MCI.
Humans ; Electroencephalography/methods* ; Cognitive Dysfunction/diagnosis* ; Neural Networks, Computer ; Sensitivity and Specificity

Alzheimer's disease (AD) is an irreversible neurodegenerative disorder that damages patients' memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods* ; Neuroimaging/methods* ; Diagnosis, Computer-Assisted ; Brain ; Cognitive Dysfunction