Objective Evaluation of Pulse Width Using an Array Pulse Diagram.

BACKGROUND: Pulse width, which can reflect qi, blood excess, and deficiency, has been used for diagnosing diseases and determining the prognosis in traditional Chinese medicine (TCM). This study aimed to devise an objective method to measure the pulse width based on an array pulse diagram for objective diagnosis. METHODS: The channel 6, the region wherein the pulse wave signal is the strongest, is located in the middle of the pulse sensor array and at the guan position of cunkou during data collection. Therefore, the main wave (h1) time of the pulse wave was collected from the channel 6 through calculation. The left h1 time was collected from the remaining 11 channels. The amplitudes at these time points were extracted as the h1 amplitudes for each channel. However, the pulse width could not be calculated accurately at 12 points. Consequently, a bioharmonic spline interpolation algorithm was used to interpolate the h1 amplitude data obtained from the horizontal and vertical points, yielding 651 (31 × 21) h1 amplitude data. The 651 data points were converted into a heat map to intuitively calculate the pulse width. The pulse width was calculated by multiplying the number of grids on the vertical axis with the unit length of the grid. The pulse width was determined by TCM doctors to verify the pulse width measurement accuracy. Meanwhile, a color Doppler ultrasound examination of the volunteers' radial arteries was performed and the intravascular meridian widths of the radial artery compared with the calculated pulse widths to determine the reliability. RESULTS: The pulse width determined using the maximal h1 amplitude method was comparable with the radial artery intravascular meridian widths measured using color Doppler ultrasound. The h1 amplitude was higher in the high blood pressure group and the pulse width was greater. CONCLUSIONS: The pulse width determined using the maximal h1 amplitude was objective and accurate. Comparison between the pulse widths of the normal and high blood pressure groups verified the reliability of the method.

Deep Learning Multi-label Tongue Image Analysis and Its Application in a Population Undergoing Routine Medical Checkup.

Background: Research on intelligent tongue diagnosis is a main direction in the modernization of tongue diagnosis technology. Identification of tongue shape and texture features is a difficult task for tongue diagnosis in traditional Chinese medicine (TCM). This study aimed to explore the application of deep learning techniques in tongue image analyses. Methods: A total of 8676 tongue images were annotated by clinical experts, into seven categories, including the fissured tongue, tooth-marked tongue, stasis tongue, spotted tongue, greasy coating, peeled coating, and rotten coating. Based on the labeled tongue images, the deep learning model faster region-based convolutional neural networks (Faster R-CNN) was utilized to classify tongue images. Four performance indices, i.e., accuracy, recall, precision, and F1-score, were selected to evaluate the model. Also, we applied it to analyze tongue image features of 3601 medical checkup participants in order to explore gender and age factors and the correlations among tongue features in diseases through complex networks. Results: The average accuracy, recall, precision, and F1-score of our model achieved 90.67%, 91.25%, 99.28%, and 95.00%, respectively. Over the tongue images from the medical checkup population, the model Faster R-CNN detected 41.49% fissured tongue images, 37.16% tooth-marked tongue images, 29.66% greasy coating images, 18.66% spotted tongue images, 9.97% stasis tongue images, 3.97% peeled coating images, and 1.22% rotten coating images. There were significant differences in the incidence of the fissured tongue, tooth-marked tongue, spotted tongue, and greasy coating among age and gender. Complex networks revealed that fissured tongue and tooth-marked were closely related to hypertension, dyslipidemia, overweight and nonalcoholic fatty liver disease (NAFLD), and a greasy coating tongue was associated with hypertension and overweight. Conclusion: The model Faster R-CNN shows good performance in the tongue image classification. And we have preliminarily revealed the relationship between tongue features and gender, age, and metabolic diseases in a medical checkup population.

A multi-step approach for tongue image classification in patients with diabetes.

BACKGROUND: In China, diabetes is a common, high-incidence chronic disease. Diabetes has become a severe public health problem. However, the current diagnosis and treatment methods are difficult to control the progress of diabetes. Traditional Chinese Medicine (TCM) has become an option for the treatment of diabetes due to its low cost, good curative effect, and good accessibility. OBJECTIVE: Based on the tongue images data to realize the fine classification of the diabetic population, provide a diagnostic basis for the formulation of individualized treatment plans for diabetes, ensure the accuracy and consistency of the TCM diagnosis, and promote the objective and standardized development of TCM diagnosis. METHODS: We use the TFDA-1 tongue examination instrument to collect the tongue images of the subjects. Tongue Diagnosis Analysis System (TDAS) is used to extract the TDAS features of the tongue images. Vector Quantized Variational Autoencoder (VQ-VAE) extracts VQ-VAE features from tongue images. Based on VQ-VAE features, K-means clustering tongue images. TDAS features are used to describe the differences between clusters. Vision Transformer (ViT) combined with Grad-weighted Class Activation Mapping (Grad-CAM) is used to verify the clustering results and calculate positioning diagnostic information. RESULTS: Based on VQ-VAE features, K-means divides the diabetic population into 4 clusters with clear boundaries. The silhouette, calinski harabasz, and davies bouldin scores are 0.391, 673.256, and 0.809, respectively. Cluster 1 had the highest Tongue Body L (TB-L) and Tongue Coating L (TC-L) and the lowest Tongue Coating Angular second moment (TC-ASM), with a pale red tongue and white coating. Cluster 2 had the highest TC-b with a yellow tongue coating. Cluster 3 had the highest TB-a with a red tongue. Group 4 had the lowest TB-L, TC-L, and TB-b and the highest Per-all with a purple tongue and the largest tongue coating area. ViT verifies the clustering results of K-means, the highest Top-1 Classification Accuracy (CA) is 87.8%, and the average CA is 84.4%. CONCLUSIONS: The study organically combined unsupervised learning, self-supervised learning, and supervised learning and designed a complete diabetic tongue image classification method. This method does not rely on human intervention, makes decisions based entirely on tongue image data, and achieves state-of-the-art results. Our research will help TCM deeply participate in the individualized treatment of diabetes and provide new ideas for promoting the standardization of TCM diagnosis.

Assessment Parameters for Arrayed Pulse Wave Analysis and Application in Hypertensive Disorders.

Study on the objectivity of pulse diagnosis is inseparable from the instruments to obtain the pulse waves. The single-pulse diagnostic instrument is relatively mature in acquiring and analysing pulse waves, but the pulse information captured by single-pulse diagnostic instrument is limited. The sensor arrays can simulate rich sense of the doctor's fingers and catch multipoint and multiparameter array signals. How to analyse the acquired array signals is still a major problem in the objective research of pulse diagnosis. The goal of this study was to establish methods for analysing arrayed pulse waves and preliminarily apply them in hypertensive disorders. While a sensor array can be used for the real-time monitoring of twelve pulse wave channels, for each subject in this study, only the pulse wave signals of the left hand at the "guan" location were obtained. We calculated the average pulse wave (APW) per channel over a thirty-second interval. The most representative pulse wave (MRPW) and the APW were matched by their correlation coefficient (CC). The features of the MRPW and the features that corresponded to the array pulse volume (APV) parameters were identified manually. Finally, a clinical trial was conducted to detect these feature performance indicators in patients with hypertensive disorders. The independent-samples t-tests and the Mann-Whitney U-tests were performed to assess the differences in these pulse parameters between the healthy and hypertensive groups. We found that the radial passage (RP) APV h1, APV h3, APV h4, APV h3/h1 (P < 0.01), and APV h4/h1 (P < 0.05) were significantly higher in the hypertensive group than in the healthy group; the intermediate passage (IP) APV h4, APV h3/h1 (P < 0.05), and APV h4/h1 (P < 0.01) and the mean APV h3, APV h3/h1 (P < 0.05), and APV h4/h1 (P < 0.01) were significantly higher in the hypertensive group than in the healthy group, and the ulnar passage (UP) APV h4/h1 (P < 0.05) was clearly elevated in the hypertensive group. These results provide a preliminary validation of this novel approach for determining the APV by arrayed pulse wave analysis. In conclusion, we identified effective indicators of hypertensive vascular function. Traditional Chinese medicine (TCM) pulses comprise multidimensional information, and a sensor array could provide a better indication of TCM pulse characteristics. In this study, the validation of the arrayed pulse wave analysis demonstrates that the APV can reliably mirror TCM pulse characteristics.

A tongue features fusion approach to predicting prediabetes and diabetes with machine learning.

BACKGROUND: Diabetics has become a serious public health burden in China. Multiple complications appear with the progression of diabetics pose a serious threat to the quality of human life and health. We can prevent the progression of prediabetics to diabetics and delay the progression to diabetics by early identification of diabetics and prediabetics and timely intervention, which have positive significance for improving public health. OBJECTIVE: Using machine learning techniques, we establish the noninvasive diabetics risk prediction model based on tongue features fusion and predict the risk of prediabetics and diabetics. METHODS: Applying the type TFDA-1 Tongue Diagnosis Instrument, we collect tongue images, extract tongue features including color and texture features using TDAS, and extract the advanced tongue features with ResNet-50, achieve the fusion of the two features with GA_XGBT, finally establish the noninvasive diabetics risk prediction model and evaluate the performance of testing effectiveness. RESULTS: Cross-validation suggests the best performance of GA_XGBT model with fusion features, whose average CA is 0.821, the average AUROC is 0.924, the average AUPRC is 0.856, the average Precision is 0.834, the average Recall is 0.822, the average F1-score is 0.813. Test set suggests the best testing performance of GA_XGBT model, whose average CA is 0.81, the average AUROC is 0.918, the average AUPRC is 0.839, the average Precision is 0.821, the average Recall is 0.81, the average F1-score is 0.796. When we test prediabetics with GA_XGBT model, we find that the AUROC is 0.914, the Precision is 0.69, the Recall is 0.952, the F1-score is 0.8. When we test diabetics with GA_XGBT model, we find that the AUROC is 0.984, the Precision is 0.929, the Recall is 0.951, the F1-score is 0.94. CONCLUSIONS: Based on tongue features, the study uses classical machine learning algorithm and deep learning algorithm to maximum the respective advantages. We combine the prior knowledge and potential features together, establish the noninvasive diabetics risk prediction model with features fusion algorithm, and detect prediabetics and diabetics noninvasively. Our study presents a feasible method for establishing the association between diabetics and the tongue image information and prove that tongue image information is a potential marker which facilitates effective early diagnosis of prediabetics and diabetics.