Clinical data mining on network of symptom and index and correlation of tongue-pulse data in fatigue population

Shi, Yulin; Hu, Xiaojuan; Cui, Ji; Cui, Longtao; Ma, Xuxiang; Jiang, Tao; Yao, Xinghua; Xu, Jiatuo; Lan, Fang; Li, Jun; Bi, Zijuan; Li, Jiacai; Wang, Yu; Fu, Haoran; Wang, Jue; Lin, Yow−Jon; Bai, Jingxuan; Guo, Xiaojing; Tu, Liping

doi:10.21203/rs.3.rs-59498/v2

Cited by 4 publications

(4 citation statements)

References 27 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A complex network by the improved node contraction method [38][39][40] is a weighted network that contains the degree and weight of edges based on the obtained node importance.…”

Section: Application Of Tongue Image Detection Modelmentioning

confidence: 99%

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

Jiang

et al. 2022

Evidence-Based Complementary and Alternative Medicine

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…A complex network by the improved node contraction method [38][39][40] is a weighted network that contains the degree and weight of edges based on the obtained node importance.…”

Section: Application Of Tongue Image Detection Modelmentioning

confidence: 99%

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

Jiang

et al. 2022

Evidence-Based Complementary and Alternative Medicine

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our study, 76.77% (2,459 cases) of patients were diagnosed with SF. SF is one of the most common types of subhealth, with fatigue as its most prominent manifestation [29]. However, we have not found relevant clinical research evidence on treating SF with FEJ.…”

Section: Discussionmentioning

confidence: 72%

Efficacy of Fufang E’jiao Jiang in the Treatment of Patients with Qi and Blood Deficiency Syndrome: A Real-World Prospective Multicenter Study with a Patient Registry

Zhao

Xiao

Ying

et al. 2023

Evidence-Based Complementary and Alternative Medicine

View full text Add to dashboard Cite

Objective. This nationwide, multicenter prospective observational study with a patient registry was designed to evaluate the efficacy of Fufang E’jiao Jiang (FEJ) in Chinese patients with Qi and blood deficiency syndrome (QBDS). Methods. QBDS patients were consecutively recruited from 81 investigational sites in China from July, 2019, to December, 2020. Patients who met the eligibility criteria were enrolled in a prospective registry database. Baseline characteristics and changes in scores on the traditional Chinese medicine (TCM) symptom evaluation scale for Qi and blood deficiency, the clinical global impression (CGI) scale, the fatigue scale-14 (FS-14), and the Pittsburgh sleep quality index (PSQI) were analyzed to determine the clinical efficacy of FEJ. Results. A total of 3,203 patients were recruited. The average remission rate (i.e., the sum of the cure rate and improvement rate) of the 20 symptoms of QBDS was 92.49% after 4 weeks of FEJ treatment, which was higher than at baseline; the rate increased to 94.69% at 8 weeks. The CGI scale revealed that the number of total remissions at 4 and 8 weeks was 3,120 (97.41%) and 415 (100%), respectively. The total FS-14 scores decreased by 1.67 ± 4.11 ( p < 0.001 ) at 4 weeks and 1.72 ± 3.09 ( p < 0.001 ) at 8 weeks of treatment. The PSQI scores were 6.6 ± 4.7 and 6.52 ± 3.07 at 4 and 8 weeks, respectively, which were significantly lower than the baseline scores ( p < 0.001 ; p = 0.0033 ). Both the subhealth fatigue (SF) and iron deficiency anemia (IDA) groups showed significantly improved clinical symptoms of QBDS ( p < 0.01 ). Between-group comparisons revealed significantly greater improvements in FS-14 and PSQI scores in the SF group than in the IDA group ( p < 0.05 ). A multivariate logistic regression analysis showed that disease course, FS-14 score at baseline, and four-week FEJ doses were independent risk factors for the degree of symptom relief in QBDS patients ( p < 0.05 ). Conclusion. In real-world settings, FEJ has a promising effect in treating QBDS and can significantly improve the severity of its symptoms.

show abstract

“…Tongue indices can be divided into two categories: tongue body (TB) index and tongue coating (TC) index which mainly come from the three color spaces of Lab, HIS, and YCrCb [29][30][31][32]. Each parameter of tongue diagnosis and pulse diagnosis has its corresponding medical significance [32][33][34]. In tongue indices, they are R (Red), G (Green), B (Blue), H (Hue), S(Saturation), I (Intensity) and L (Light), a (red-green axis), b (yellow-blue axis), Y (brightness), Cr (difference between red signal and brightness), Cb (difference between blue signal and brightness), texture indices include CON (Contrast), ASM (Angular Second Moment), ENT (Entropy), MEAN (Mean), and tongue coating indices include perAll and perPart.…”

Section: Diagnosticmentioning

confidence: 99%

A New Method for Syndrome Classification of Non-Small-Cell Lung Cancer Based on Data of Tongue and Pulse with Machine Learning

Shi

Liu

et al. 2021

BioMed Research International

Self Cite

View full text Add to dashboard Cite

Objective. To explore the data characteristics of tongue and pulse of non-small-cell lung cancer with Qi deficiency syndrome and Yin deficiency syndrome, establish syndrome classification model based on data of tongue and pulse by using machine learning methods, and evaluate the feasibility of syndrome classification based on data of tongue and pulse. Methods. We collected tongue and pulse of non-small-cell lung cancer patients with Qi deficiency syndrome ( n = 163 ), patients with Yin deficiency syndrome ( n = 174 ), and healthy controls ( n = 185 ) using intelligent tongue diagnosis analysis instrument and pulse diagnosis analysis instrument, respectively. We described the characteristics and examined the correlation of data of tongue and pulse. Four machine learning methods, namely, random forest, logistic regression, support vector machine, and neural network, were used to establish the classification models based on symptom, tongue and pulse, and symptom and tongue and pulse, respectively. Results. Significant difference indices of tongue diagnosis between Qi deficiency syndrome and Yin deficiency syndrome were TB-a, TB-S, TB-Cr, TC-a, TC-S, TC-Cr, perAll, and the tongue coating texture indices including TC-CON, TC-ASM, TC-MEAN, and TC-ENT. Significant difference indices of pulse diagnosis were t4 and t5. The classification performance of each model based on different datasets was as follows: tongue and pulse < symptom < symptom and tongue and pulse. The neural network model had a better classification performance for symptom and tongue and pulse datasets, with an area under the ROC curves and accuracy rate which were 0.9401 and 0.8806. Conclusions. It was feasible to use tongue data and pulse data as one of the objective diagnostic basis in Qi deficiency syndrome and Yin deficiency syndrome of non-small-cell lung cancer.

show abstract

Clinical data mining on network of symptom and index and correlation of tongue-pulse data in fatigue population

Cited by 4 publications

References 27 publications

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

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

Efficacy of Fufang E’jiao Jiang in the Treatment of Patients with Qi and Blood Deficiency Syndrome: A Real-World Prospective Multicenter Study with a Patient Registry

A New Method for Syndrome Classification of Non-Small-Cell Lung Cancer Based on Data of Tongue and Pulse with Machine Learning

Contact Info

Product

Resources

About