OBJECTIVES: To construct vocal recognition classification models using 6 machine learning algorithms and vocal emotional characteristics of individuals with subthreshold depression to facilitate early identification of subthreshold depression. METHODS: We collected voice data from both normal individuals and participants with subthreshold depression by asking them to read specifically chosen words and texts. From each voice sample, 384-dimensional vocal emotional feature variables were extracted, including energy feature, Meir frequency cepstrum coefficient, zero cross rate feature, sound probability feature, fundamental frequency feature, difference feature. The Recursive Feature Elimination (RFE) method was employed to select voice feature variables. Classification models were then built using the machine learning algorithms Adaptive Boosting (AdaBoost), Random Forest (RF), Linear Discriminant Analysis (LDA), Logistic Regression (LR), Lasso Regression (LRLasso), and Support Vector Machine (SVM), and the performance of these models was evaluated. To assess generalization capability of the models, we used real-world speech data to evaluate the best speech recognition classification model. RESULTS: The AdaBoost, RF, and LDA models achieved high prediction accuracies of 100%, 100%, and 93.3% on word-reading speech test set, respectively. In the text-reading speech test set, the accuracies of the AdaBoost, RF, and LDA models were 90%, 80%, and 90%, respectively, while the accuracies of the other 3 models were all below 80%. On real-world word-reading and text-reading speech data, the classification models using AdaBoost and Random Forest still achieved high predictive accuracies (91.7% and 80.6% for AdaBoost and 86.1% and 77.8% for Random, respectively). CONCLUSIONS Analyzing vocal emotional characteristics allows effective identification of individuals with subthreshold depression. The AdaBoost and RF models show excellent performance for classifying subthreshold depression individuals, and may thus potentially offer valuable assistance in the clinical and research settings.
Humans ; Machine Learning ; Emotions ; Depression/diagnosis* ; Algorithms ; Voice ; Support Vector Machine ; Male ; Female

Based on the"You Gu Wu Yun"theory in traditional Chinese medicine(TCM),this paper believes that"Gu"in"You Gu Wu Yun"is extended to"state"from the perspective of"TCM state".In order to avoid the adverse reactions of TCM,the macro,meso,and micro three views should be used together,and macro,meso,and micro parameters should be integrated.We should also carefully identify the physiological characteristics,pathological characteristics,constitution,syndrome,and disease of human body by combining qualitative and quantitative method,highlighting the relationship between the prescription and the"state".The correspondence between prescription and the"state"will reduce the risk of adverse reactions of TCM.In this paper,we hope to focus on the guiding role of the"You Gu Wu Yun"theory in TCM research,to give full play to the characteristics and advantages of TCM,and to dialectically treat the role of TCM.

The correspondence between prescription and syndrome is the advantage and characteristic of traditional Chinese medicine(TCM)treatment.However,the pathogenesis of clinical diseases is complex and the condition is changeable,and the clinical application is difficult to achieve the maximum effect under the existing cognition of the correspondence between prescription and syndrome.In this paper,the five categories of physiological characteristics,pathological characteristics,constitution,syndrome,and disease of the longitudinal classification of"TCM state"are introduced into the correspondence of prescription and syndrome.Under the vertical perspective of"TCM state",the theoretical connotation of the correspondence between prescription and syndrome is interpreted as"correspondence between prescription and state",namely correspondence of"prescription-physiological characteristics",correspondence of"prescription-pathological characteristics",correspondence of"prescription-constitution",correspondence of"prescription-syndrome",and correspondence of"prescription-disease".It is hoped to accurately grasp the corresponding connotation of the correspondence between prescription and syndrome,in order to deepen the clinical thinking mode of TCM.