Objective: To explore the feasibility of remotely obtaining complex information on traditional Chinese medicine (TCM) pulse conditions through voice signals. Methods: We used multi-label pulse conditions as the entry point and modeled and analyzed TCM pulse diagnosis by combining voice analysis and machine learning. Audio features were extracted from voice recordings in the TCM pulse condition dataset. The obtained features were combined with information from tongue and facial diagnoses. A multi-label pulse condition voice classification DNN model was built using 10-fold cross-validation, and the modeling methods were validated using publicly available datasets. Results: The analysis showed that the proposed method achieved an accuracy of 92.59% on the public dataset. The accuracies of the three single-label pulse manifestation models in the test set were 94.27%, 96.35%, and 95.39%. The absolute accuracy of the multi-label model was 92.74%. Conclusion Voice data analysis may serve as a remote adjunct to the TCM diagnostic method for pulse condition assessment.

OBJECTIVETo explore the relationship between total plasma homocysteine (tHcy) levels, dietary habits and susceptibility of gastric cancer (CGC) in Yangzhong and Yixing cities, the two high GC risk areas in Jiangsu province.

METHODSA population-based case-control study was conducted including 391 histologically-confirmed adenocarcinoma GC cases and 608 age and sex frequency-matched cancer-free controls. The plasma tHcy concentration was measured by enzymatic biochemical assay of homocysteine on microtiter plates, using crude lysate containing recombinant methionine 7-lyase. The relationship between different tHcy levels and risk of GC was analyzed and factors as vegetables and fruits intake, smoking and drinking status were also evaluated together with tHey levels on the risk of GC.

RESULTSThe average tHcy levels in GC cases were significantly higher than that in controls (P = 0.002). In addition, according to the quartile levels (7.9, 10.1, 13.7 micromol/L) in the controls, the risks of GC had an increase of 67% (adjusted OR = 1.67, 95% CI: 1.12-2.48), 98% (adjusted OR = 1.98, 95% CI: 1.33-2.94) and 112% (adjusted OR = 2.12, 95% CI: 1.44-3.15) compared to the lowest quartile of tHcy (< or = 7.9 micromol/L), respectively while the increasing trend was significantly noticed (chi2 = 15.78, P < 0.001). The increase of vegetables and fruits intake could decrease the risk of GC. Results from crossover analyses indicated that subjects with less vegetables and fruits intake or both smoking drinking together with plasma tHcy >15.0 micromol/L could increase the GC risk, when compared to the effect on GC risk of each factor.

CONCLUSIONThese findings supported the hypothesis that the high level of plasma tHcy and the badness dietary habits were associated to the increased risk of GC. Further larger scale and genetics involved studies on the environment and genetic factors were needed to confirm our findings.

Aged ; Alcohol Drinking ; adverse effects ; Case-Control Studies ; Feeding Behavior ; Female ; Fruit ; Homocysteine ; blood ; Humans ; Male ; Middle Aged ; Smoking ; adverse effects ; Stomach Neoplasms ; blood ; Vegetables

Objective:To investigate the effects of anxiety and depressive symptoms in mediation of pain catastrophizing on disability in patients with low back pain.Methods:A cross-sectional survey was conducted among 97 patients with low back pain in the Changjiang Subdistrict community health center from July to October 2021. Oswestry Disability Index, pain catastrophic subscale in Coping Strategies Questionnaire-24, Generalized Anxiety Disorder Scale-short version, Patient Health Depression Questionnaire-short version were used to evaluate the activity dysfunction, pain catastrophic cognition and anxiety and depression levels of patients,respectively. Path analysis was implemented to test the mediation model, and the indirect effects were assessed using the bootstrap procedure with bias-corrected 95 %CI. Results:Results suggested significant positive correlations among pain catastrophizing, anxiety, depressive symptoms and disability of patients. In addition, both anxiety and depressive symptoms significantly mediated the impact of pain catastrophizing on disability (standardized indirect effects were 0.183 and 0.197, P<0.05). Patients with higher levels of pain catastrophic cognition showed higher levels of anxiety and depressive symptoms (β=0.757, 0.720; P<0.01), and reported more severe motor dysfunction (β=0.241, 0.274; P<0.05). Conclusions:Our findings suggest that anxiety and depression may be the psychological pathways through which pain catastrophizing predicts disability in patients with low back pain. Effective psychological interventions, such as emotion regulation and stress reduction strategies should be considered in treatment and supportive care for patients with low back pain.

Objective To establish a dynamic prediction model of fatal massive hemorrhage in trauma based on the vital signs time series data and machine learning algorithms.Methods Retrospectively analyze the vital signs time series data of 7522 patients with trauma in the Medical Information Mart for Intensive Care-Ⅳ(MIMIC-Ⅳ)database from 2008 to 2019.According to the occurrence of posttraumatic fatal massive hemorrhage,the patients were divided into two groups:fatal massive hemorrhage group(n=283)and non-fatal massive hemorrhage group(n=7239).Six machine learning algorithms,including logistic regression(LR),support vector machine(SVM),random forests(RF),adaptive boosting(AdaBoost),gated recurrent unit(GRU),and GRU-D were used to develop a dynamic prediction models of fatal massive hemorrhage in trauma.The probability of fatal massive hemorrhage in the following 1,2,and 3 h was dynamically predicted.The performance of the models was evaluated by accuracy,sensitivity,specificity,positive predictive value,negative predictive value,Youden index,and area under receiver operating characteristic curve(AUC).The models were externally validated based on the trauma database of the Chinese PLA General Hospital.Results In the MIMIC-Ⅳ database,the set of dynamic prediction models based on the GRU-D algorithm was the best.The AUC for predicting fatal major bleeding in the next 1,2,and 3 h were 0.946±0.029,0.940±0.032,and 0.943±0.034,respectively,and there was no significant difference(P=0.905).In the trauma dataset,GRU-D model achieved the best external validation effect.The AUC for predicting fatal major bleeding in the next 1,2,and 3 h were 0.779±0.013,0.780±0.008,and 0.778±0.009,respectively,and there was no significant difference(P=0.181).This set of models was deployed in a public web calculator and hospital emergency department information system,which is convenient for the public and medical staff to use and validate the model.Conclusion A set of dynamic prediction models has been successfully developed and validated,which is greatly significant for the early diagnosis and dynamic prediction of fatal massive hemorrhage in trauma.