A5053804373- Traditional Chinese Medicine Studies
- Cancer-related molecular mechanisms research
- Non-Invasive Vital Sign Monitoring
- Salivary Gland Disorders and Functions
- Cardiovascular Health and Disease Prevention
- Acupuncture Treatment Research Studies
- Metabolomics and Mass Spectrometry Studies
- Head and Neck Cancer Studies
- Lung Cancer Diagnosis and Treatment
- Heart Rate Variability and Autonomic Control
- Traditional Chinese Medicine Analysis
- Ovarian function and disorders
- Fibromyalgia and Chronic Fatigue Syndrome Research
- Healthcare and Venom Research
- Radiomics and Machine Learning in Medical Imaging
- Bioinformatics and Genomic Networks
- Cardiovascular Health and Risk Factors
- Medical Research and Treatments
- Phonocardiography and Auscultation Techniques
- Image Retrieval and Classification Techniques
- Clinical Laboratory Practices and Quality Control
- Liver Disease Diagnosis and Treatment
- Voice and Speech Disorders
- Advanced Chemical Sensor Technologies
- Complementary and Alternative Medicine Studies
Shanghai University of Traditional Chinese Medicine
2011-2025
Yuhuangding Hospital
2025
Qingdao University
2025
Shuguang Hospital
2022
Xiamen University
2020
Shanghai University
2012
Tsinghua University
2007
Anemia is a global public health issue causing symptoms such as fatigue, weakness, and cognitive decline. Furthermore, anemia associated with various diseases increases the risk of postoperative complications mortality. Frequent invasive blood tests for diagnosis also pose additional discomfort risks to patients. This study aims assess facial spectral characteristics patients develop predictive model using machine learning approaches. Between August 2022 September 2023, we collected image...
Abstract Background Tongue diagnosis is an important research field of TCM diagnostic technology modernization. The quality tongue images the basis for constructing a standard dataset in diagnosis. To establish image database industry, we need to evaluate massive number and add qualified database. Therefore, automatic, efficient accurate control model significance development intelligent TCM. Methods Machine learning methods, including Support Vector (SVM), Random Forest (RF), Gradient...
Nonalcoholic fatty liver disease (NAFLD), a leading cause of chronic hepatic disease, can progress to fibrosis, cirrhosis, and hepatocellular carcinoma. Therefore, it is extremely important explore early diagnosis screening methods. In this study, we developed models based on computer tongue image analysis technology observe the characteristics 1778 participants (831 cases NAFLD 947 non-NAFLD). Combining quantitative features, basic information, serological indexes, including steatosis index...
Metabolic associated fatty liver disease (MAFLD) is a widespread that can lead to fibrosis and cirrhosis. Therefore, it essential develop early diagnosic screening methods.
Fatigue is a common and subjective symptom, which associated with many diseases suboptimal health status. A reliable evidence-based approach lacking to distinguish disease fatigue non-disease fatigue. This study aimed establish method for early differential diagnosis of fatigue, can be used from investigate the feasibility characterizing states in view tongue pulse data analysis.Tongue Face Diagnosis Analysis-1 (TFDA-1) instrument Pulse (PDA-1) were collect data. Four machine learning models...
Background and objective Polycystic ovary syndrome is one of the most common types endocrine metabolic diseases in women reproductive age that needs to be screened early assessed non-invasively. The current study was develop prediction models for polycystic based on data tongue pulse using machine learning techniques. Methods A dataset 285 patients 201 healthy were investigated identify significant parameters predicting syndrome. In this study, feature selection performed least absolute...
Objective Lung cancer—with its global prevalence and critical need for early diagnosis treatment—is the focus of our study. This study aimed to develop a nomogram based on acoustic–clinical features—a tool that could significantly enhance clinical prediction lung cancer. Methods We reviewed voice data information 350 individuals: 189 pathologically confirmed cancer patients 161 non-lung patients, which included 77 with benign pulmonary lesions 84 healthy volunteers. First, acoustic features...
<sec> <title>INTERNATIONAL REGISTERED REPORT</title> RR2-10.2196/64204 </sec>
<title>Abstract</title> Background This study aimed to analyze the tongue image features and oral microbial markers in different TCM syndromes related metabolic dysfunction-associated steatotic liver disease (MASLD). Methods involved 34 healthy volunteers 66 MASLD patients [36 with Dampness-Heat (DH) 30 Qi-Deficiency (QD) syndrome]. Oral microbiome analysis was conducted through 16S rRNA sequencing. Tongue feature extraction used Uncertainty Augmented Context Attention Network (UACANet),...
Concerning computer aided analysis of the Traditional Chinese Medicine Pulse Diagnosis, recognition effect wrist pulse signals is undesirable because its morphology complexity and features ambiguity. To solve problem, we propose a new methodology based on classifier using Shannon Energy Envelope, Hilbert Transform (SEEHT) Deep Convolutional Neural Networks (DCNN). In this paper, demonstrate wave extractor: SEEHT, which better than traditional one in case wider, small or sudden changes...
Type 2 diabetes mellitus (T2DM) with distal symmetric polyneuropathy (DSPN) is a disease involving the nervous system caused by metabolic disorder, while spectrum and key metabolites remain poorly defined.Plasma samples of 30 healthy controls, T2DM patients, 60 DSPN patients were subjected to nontargeted metabolomics. Potential biomarkers screened based on univariate multivariate statistical analyses, ROC curve analysis, logistic regression. Finally, another 22 who developed after follow-up...
Objective: To investigate the tongue image features of patients with lung cancer and benign pulmonary nodules to construct a risk warning model using machine learning methods. Methods: From July 2020 March 2022, we collected 862 participants including 263 cancer, 292 nodules, 307 healthy subjects. The TFDA-1 digital diagnosis instrument was used capture images, feature extraction technology obtain index images. statistical characteristics correlations were analyzed, six algorithms build...
Background. Research on intelligent tongue diagnosis is a main direction in the modernization of technology. Identification shape and texture features difficult task for traditional Chinese medicine (TCM). This study aimed to explore application deep learning techniques image analyses. Methods. A total 8676 images were annotated by clinical experts, into seven categories, including fissured tongue, tooth-marked stasis spotted greasy coating, peeled rotten coating. Based labeled images, model...
Background Chronic fatigue syndrome (CFS) is a debilitating multisystem disorder that can lead to various pathophysiological abnormalities and symptoms, including insomnia, gastrointestinal disorders, anxiety. Due the side effects of currently available drugs, there growing need for safe effective nondrug therapies. The Prolong Life With Nine Turn (PLWNT) Qigong method system mind-body exercise with restorative benefits alleviate clinical symptoms CFS impart significant inhibitory effect....
Background and Objective. The same range of blood pressure values may reflect different vascular functions, especially in the elderly. Therefore, a single value not comprehensively reveal cardiovascular function. This study focused on identifying pulse wave features elderly that can be used to show functional differences when are range. Methods. First, data were preprocessed cycles segmented. Second, time domain, higher‐order statistics, energy wavelet packet decomposition coefficients...
Equus asinus L [Equidae; Asini Corii Colla] (donkey-hide gelatin, Ejiao), a well-known traditional Chinese medicine, has been widely used to nourish the blood, especially for women. The aim of this study was assess efficacy and safety Ejiao in blood-deficient patients. A total 210 participants were recruited randomly allocated into placebo control group Ejiao-treated (6 g/day). primary outcomes on included medicine symptom scores, blood indicators, SF-36. secondary changes fireness...
Abstract Subhealth is a transitional state between health and disease, it can be detected through routine physical check-ups. However, the complexity diversity of examination items difficulty quantifying subhealth manifestations are main problems that hinder its treatment. The aim this study was to systematically investigate performance subhealthy population further explore deeper relationships indicators. Indicators were obtained for 878 subjects, including basic information, Western...
To analyze the tongue feature of NSCLC at different stages, as well correlation between and tumor marker, investigate feasibility establishing prediction models for stages based on marker.Tongue images were collected from non-advanced patients (n = 109) advanced 110), analyzed to obtain feature, marker in NSCLC. On this basis, six classifiers, decision tree, logistic regression, SVM, random forest, naive bayes, neural network, used establish marker.There statistically significant differences...
Study on the objectivity of pulse diagnosis is inseparable from instruments to obtain waves. The single-pulse diagnostic instrument relatively mature in acquiring and analysing waves, but information captured by limited. sensor arrays can simulate rich sense doctor's fingers catch multipoint multiparameter array signals. How analyse acquired signals still a major problem objective research diagnosis. goal this study was establish methods for arrayed waves preliminarily apply them...