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

Humans ; Neoplasm, Residual/diagnosis* ; Consensus ; East Asian People ; Precursor Cell Lymphoblastic Leukemia-Lymphoma/therapy* ; Bone Marrow ; Flow Cytometry

Humans ; Consensus ; East Asian People ; Hematopoietic Stem Cell Transplantation/adverse effects* ; Hepatitis B/virology* ; Hepatitis B Antibodies ; Hepatitis B Surface Antigens ; Hepatitis B virus/physiology* ; Virus Activation ; Latent Infection/virology*

Humans ; Bronchiolitis Obliterans Syndrome ; Chronic Disease ; Consensus ; East Asian People ; Graft vs Host Disease/etiology* ; Hematopoietic Stem Cell Transplantation ; Eye Diseases/etiology*

Myopia has emerged as a public health issue with the increasing prevalence of myopia in children and adolescents in China. In the clinical diagnosis and treatment of myopia, there are clinical stages and classifications, but they are not suitable for the prevention and control of myopia at the public health level. At the public health level, because there is no staging standard for myopia, there is a lack of staging prevention and control guidance for different refractive errors. Therefore, the Public Health Ophthalmology Branch of the Chinese Preventive Medicine Association organized domestic experts in relevant fields to conduct literature searches and discuss based on the research data on myopia at home and abroad, put forward the stages of public health strategies for myopia prevention and control and corresponding group prevention and control measures for each stage to reached this experts consensus. This consensus first proposes a method for assessing myopia risk, in order to predict the occurrence and development of myopia in children and adolescents; From the perspective of public health, myopia prevention and control is further divided into four stages: myopia prodromal stage, myopia development stage, high myopia stage, and pathological myopia stage. According to this consensus, myopia prevention and control technology is targeted and implemented in different stages to provide guidance for myopia prevention and control from the perspective of public health.
Humans ; Child ; Adolescent ; Public Health ; Consensus ; Myopia/epidemiology* ; Refractive Errors/epidemiology* ; Asian People ; China/epidemiology*

BACKGROUND: The prevalence of hypertension is high among Chinese adults, thus, identifying non-hypertensive individuals at high risk for intervention will help to improve the efficiency of primary prevention strategies. METHODS: The cross-sectional data on 9699 participants aged 20 to 80 years were collected from the China National Health Survey in Gansu and Hebei provinces in 2016 to 2017, and they were nonrandomly split into the training set and validation set based on location. Multivariable logistic regression analysis was performed to develop the diagnostic prediction model, which was presented as a nomogram and a website with risk classification. Predictive performances of the model were evaluated using discrimination and calibration, and were further compared with a previously published model. Decision curve analysis was used to calculate the standardized net benefit for assessing the clinical usefulness of the model. RESULTS: The Lasso regression analysis identified the significant predictors of hypertension in the training set, and a diagnostic model was developed using logistic regression. A nomogram with risk classification was constructed to visualize the model, and a website ( https://chris-yu.shinyapps.io/hypertension_risk_prediction/ ) was developed to calculate the exact probabilities of hypertension. The model showed good discrimination and calibration, with the C-index of 0.789 (95% confidence interval [CI]: 0.768, 0.810) through internal validation and 0.829 (95% CI: 0.816, 0.842) through external validation. Decision curve analysis demonstrated that the model was clinically useful. The model had a higher area under receiver operating characteristic curves in training and validation sets compared with a previously published diagnostic model based on Northern China population. CONCLUSION This study developed and validated a diagnostic model for hypertension prediction in Gansu Province. A nomogram and a website were developed to make the model conveniently used to facilitate the individualized prediction of hypertension in the general population of Han and Yugur.
Adult ; Humans ; Asian People ; China/epidemiology* ; Cross-Sectional Studies ; Health Surveys ; Hypertension/epidemiology* ; Nomograms ; Ethnicity

Humans ; Data Warehousing ; East Asian People ; Intracranial Hemorrhages/diagnostic imaging* ; Asian People ; Cerebral Hemorrhage/diagnostic imaging*

Adult ; Humans ; Depression ; East Asian People ; Life Style ; Asian People ; China

BACKGROUND: Tri-ponderal mass index (TMI) has been reported to be a more accurate estimate of body fat than body mass index (BMI). This study aims to compare the effectiveness of TMI and BMI in identifying hypertension, dyslipidemia, impaired fasting glucose (IFG), abdominal obesity, and clustered cardio-metabolic risk factors (CMRFs) in 3- to 17-year-old children. METHODS: A total of 1587 children aged 3 to 17 years were included. Logistic regression was used to evaluate correlations between BMI and TMI. Area under the curves (AUCs) were used to compare discriminative capability among indicators. BMI was converted to BMI- z scores, and accuracy was compared by false-positive rate, false-negative rate, and total misclassification rate. RESULTS: Among children aged 3 to 17 years, the mean TMI was 13.57 ± 2.50 kg/m 3 for boys and 13.3 ± 2.33 kg/m 3 for girls. Odds ratios (ORs) of TMI for hypertension, dyslipidemia, abdominal obesity, and clustered CMRFs ranged from 1.13 to 3.15, higher than BMI, whose ORs ranged from 1.08 to 2.98. AUCs showed similar ability of TMI (AUC: 0.83) and BMI (AUC: 0.85) in identifying clustered CMRFs. For abdominal obesity and hypertension, the AUC of TMI was 0.92 and 0.64, respectively, which was significantly better than that of BMI, 0.85 and 0.61. AUCs of TMI for dyslipidemia and IFG were 0.58 and 0.49. When 85th and 95th of TMI were set as thresholds, total misclassification rates of TMI for clustered CMRFs ranged from 6.5% to 16.4%, which was not significantly different from that of BMI- z scores standardized according to World Health Organization criteria. CONCLUSIONS TMI was found to have equal or even better effectiveness in comparison with BMI in identifying hypertension, abdominal obesity, and clustered CMRFs TMI was more stable than BMI in 3- to 17-year-old children, while it failed to identify dyslipidemia and IFG. It is worth considering the use of TMI for screening CMRFs in children and adolescents.
Adolescent ; Child ; Child, Preschool ; Female ; Humans ; Male ; Body Mass Index ; Dyslipidemias ; East Asian People ; Hypertension ; Obesity, Abdominal ; Pediatric Obesity/diagnosis* ; Cardiometabolic Risk Factors

Humans ; Nutritional Status ; Prognosis ; East Asian People ; Cardiac Surgical Procedures ; Risk Factors ; Retrospective Studies