Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Based on the traditional Chinese medicine theory that "all pain， itching， and sores are related to the heart"， this paper proposes treating recurrent aphthous ulcers from the perspective of the heart. It suggests that excessive heart fire and tissue erosion due to flaming fire in the heart meridian constitute the core pathogenesis of this condition. Hyperactive heart fire is identified as the key pathogenic factor， while heart yin deficiency， obstruction of the heart collaterals， and malnourishment of the heart spirit are considered significant contributing factors. Clinically， the treatment follows the principle of clearing heart fire as the main strategy， supplemented by nourishing yin， activating collaterals， and calming the spirit. The self-formulated Qingxin Yuchuang Formulation （清心愈疮方） serves as the base prescription， with flexible modifications incorporating the Yuyin Formulation （育阴方）， Huoxue Formulation （活血方）， and Yu'an Formulation （郁安方） to address specific syndromes involving heart yin deficiency， collateral blockage， and emotional disturbance.

Acute burns and chronic wounds frequently fail to heal owing to various reasons. Most drugs currently used for wound therapy in clinical practice have notable drawbacks, making their application a substantial concern. For instance, anti-inflammatory drugs can exert multisystem toxicity, and cellular therapies are costly and difficult to retain. In recent years, natural functional proteins derived from animals and plants have gained increasing attention owing to their unique biological activities, low cost, and broad application prospects in wound therapy. Herein, we isolated a new protein (JH015Y) from amphibians and demonstrated its excellent wound repair and regeneration properties compared with those of epidermal growth factor, both in vitro and in vivo. JH015 protein increased the proliferative ability of human keratinocytes and skin fibroblasts by 47.73 and 41.40%, respectively. In vivo, the medium-dose (0.5 mg/dose) groups of JH015Y protein demonstrated accelerated wound healing from day 4, with wound healing rates 1.26, 1.27, and 1.14 times that of the blank group in acute wounds, burn wounds, and diabetic ulcer, respectively. Histological analysis of Masson-stained sections indicated that the JH015Y protein contributed to collagen deposition on the wound surface, markedly reduced inflammatory cell infiltration, and exhibited low biological toxicity. Accordingly, the JH015Y protein is a promising biotherapeutic agent for accelerated wound repair and regeneration.

Acute burns and chronic wounds frequently fail to heal owing to various reasons. Most drugs currently used for wound therapy in clinical practice have notable drawbacks, making their application a substantial concern. For instance, anti-inflammatory drugs can exert multisystem toxicity, and cellular therapies are costly and difficult to retain. In recent years, natural functional proteins derived from animals and plants have gained increasing attention owing to their unique biological activities, low cost, and broad application prospects in wound therapy. Herein, we isolated a new protein (JH015Y) from amphibians and demonstrated its excellent wound repair and regeneration properties compared with those of epidermal growth factor, both in vitro and in vivo. JH015 protein increased the proliferative ability of human keratinocytes and skin fibroblasts by 47.73 and 41.40%, respectively. In vivo, the medium-dose (0.5 mg/dose) groups of JH015Y protein demonstrated accelerated wound healing from day 4, with wound healing rates 1.26, 1.27, and 1.14 times that of the blank group in acute wounds, burn wounds, and diabetic ulcer, respectively. Histological analysis of Masson-stained sections indicated that the JH015Y protein contributed to collagen deposition on the wound surface, markedly reduced inflammatory cell infiltration, and exhibited low biological toxicity. Accordingly, the JH015Y protein is a promising biotherapeutic agent for accelerated wound repair and regeneration.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.