Abstract To promote the mental health of college students and build campus based psychological support system, the study explains that current applications of digital health interventions (DHIs) include independent forms based on a single technology or platform, as well as integrated forms that combine multiple digital technologies with traditional mental health services. These interventions have positive effects on alleviating negative emotions among college students, enhancing psychological resilience, improving quality of life, and ameliorating academic performance. However, differences still exist in the stability of intervention effects. Future development requires continuous improvement in institutional construction, ethical governance and capacity building.

Objective To construct a swallowing dynamic model for simulating dysphagia caused by reduced tongue movement am-plitude.Methods A swallowing dynamic model was established based on medical imaging data from CT and videofluoroscopic swallowing study(VFSS).The finite element method was used to simulate soft tissues,while the smoothed parti-cle hydrodynamics method(SPH)was used to simulate bolus.The model's posture at each time point was com-pared with the imaging data of VFSS from twelve patients with dysphagia,and a normalization method was used for quantitative evaluation of the model's validity.By adjusting the tongue movement amplitude under different viscosity conditions,the role of tongue movement in the swallowing process was investigated,and the swallow-ing safety and efficiency were assessed.Results The tongue posture and bolus trajectory presented by the swallowing dynamic model were consistent with the VFSS imaging.The brightness in the epiglottis area in VFSS images correlated with the equivalent brightness of SPH particles in the simulation results(r=0.97).As the tongue movement amplitude reducing by 20%,the num-ber of aspirated particles,swallowing efficiency and the average velocity of bolus particles in the oropharyngeal cavity all performed well.Pudding-like fluids exhibited favorable swallowing characteristics even when tongue movement amplitude reducing significantly.Conclusion The swallowing dynamic model can simulate the human swallowing process,providing good support for re-habilitation training of patients with dysphagia and the development of specialized medical foods,demonstrating significant potential for clinical applications.

Objective To evaluate the relationship between triglyceride-glucose index(TyG)and intensive care unit(ICU)mor-tality in patients with non-diabetic sepsis.Methods The retrospective cohort study analyzed the data from sepsis patients admitted to the Second Hospital & Clinical Medical School,Lanzhou University between January 2018 and December 2023.The patients were divided into three groups based on the terartiles of the TyG index:group T1,group T2 and group T3,with ICU mortality as the primary endpoint.Multivariate COX regression analysis and restricted cubic spline(RCS)modeling were performed to investigate the potential non-linear relationship between the TyG index and ICU mortality of patients with sepsis,and subgroup analysis were conducted to further explore these relationships.Results This study included 578sepsis patients,with an ICU mortality of 16.96％.The Kaplan-Meier survival curve analysis indicated that the ICU mortality in the group T3 was significantly higher than that in the group T1.The RCS analysis re-vealed a linear relationship between the TyG index and ICU mortality,for every 1-unit increase in the TyG index,the risk of ICU mortal-ity increased by approximately 54％.Subgroup analysis demonstrated consistent effect directions across different subgroups,with no sub-group-specific effects,indicating the robustness of the results.Conclusion TyG index may serve as a potential biomarker for predicting ICU mortality in non-diabetic sepsis patients.

Objective To evaluate the relationship between triglyceride-glucose index(TyG)and intensive care unit(ICU)mor-tality in patients with non-diabetic sepsis.Methods The retrospective cohort study analyzed the data from sepsis patients admitted to the Second Hospital & Clinical Medical School,Lanzhou University between January 2018 and December 2023.The patients were divided into three groups based on the terartiles of the TyG index:group T1,group T2 and group T3,with ICU mortality as the primary endpoint.Multivariate COX regression analysis and restricted cubic spline(RCS)modeling were performed to investigate the potential non-linear relationship between the TyG index and ICU mortality of patients with sepsis,and subgroup analysis were conducted to further explore these relationships.Results This study included 578sepsis patients,with an ICU mortality of 16.96％.The Kaplan-Meier survival curve analysis indicated that the ICU mortality in the group T3 was significantly higher than that in the group T1.The RCS analysis re-vealed a linear relationship between the TyG index and ICU mortality,for every 1-unit increase in the TyG index,the risk of ICU mortal-ity increased by approximately 54％.Subgroup analysis demonstrated consistent effect directions across different subgroups,with no sub-group-specific effects,indicating the robustness of the results.Conclusion TyG index may serve as a potential biomarker for predicting ICU mortality in non-diabetic sepsis patients.

With the increasing aging population in China and rising incidence rates of diseases such as cancer and cardiovascular conditions, the demand for palliative care services continues to grow. In recent years, the integration of artificial intelligence and medical disciplines has advanced significantly, with machine learning research and applications in the palliative care field progressing steadily. This paper reviews the overview of machine learning, its applications in palliative care, and effectiveness evaluations. It also discusses existing limitations in current research and provides recommendations for future studies. The aim is to assist healthcare professionals in improving palliative care services and offer valuable insights for the development of palliative care in China.

Objective: To analyze the current status and influencing factors of psychological crisis among college students, so as to provide a scientific basis for the formulation of psychological crisis intervention plans in colleges and universities. Methods: From September to December 2024, 645 college students from a medical undergraduate university in Heilongjiang Province were selected with a convenience sampling method. A convergent mixed analysis design was used. Quantitative analysis was conducted using College Students Psychological Crisis Screening Scale, Emotion Regulation Questionnaire, Short-Egna Minnen av Barndoms Uppfostran and Perceived School Climate Scale. Binary Logistic regression analysis was used to explore the related factors of psychological crisis among college students. Qualitative research was conducted on 15 college students with psychological crisis identified in the quantitative analysis by a purposive sampling method. The interview data were organized and analyzed using the thematic framework analysis method. Results: Among the surveyed college students, 92 (14.3%) had psychological crisis. Binary Logistic regression analysis results showed that positive parenting style ( OR=0.97,95%CI =0.95-0.99), negative parenting style ( OR=1.01,95%CI =1.00-1.02), cognitive reappraisal ( OR=0.88, 95%CI =0.83-0.92), expressive suppression ( OR=1.08, 95%CI =1.02-1.15), and perceived campus atmosphere ( OR=0.97, 95%CI =0.95-0.98) were all related factors of psychological crisis among college students ( P <0.05). The qualitative analysis results showed that there were three themes for the influencing factors of college students psychological crisis, including differential impact of emotion regulation strategies on psychological state, shaping of psychological state of college students by family and bidirectional effect of perceived campus atmosphere on psychological state. Mixed analysis results showed that the influencing factors of college students psychological crisis were consistent in terms of emotion regulation strategies, and were expansive in terms of parenting style and perceived campus atmosphere. Conclusion Schools and mental health service departments can reduce the risk of psychological crisis by optimizing cognitive reappraisal and reducing expressive suppression, improve the level of psychological crisis by strengthening positive family interaction and blocking negative parenting style, and maintain the mental health level of college students by building a supportive campus environment and alleviating high pressure.

Objective To construct a swallowing dynamic model for simulating dysphagia caused by reduced tongue movement am-plitude.Methods A swallowing dynamic model was established based on medical imaging data from CT and videofluoroscopic swallowing study(VFSS).The finite element method was used to simulate soft tissues,while the smoothed parti-cle hydrodynamics method(SPH)was used to simulate bolus.The model's posture at each time point was com-pared with the imaging data of VFSS from twelve patients with dysphagia,and a normalization method was used for quantitative evaluation of the model's validity.By adjusting the tongue movement amplitude under different viscosity conditions,the role of tongue movement in the swallowing process was investigated,and the swallow-ing safety and efficiency were assessed.Results The tongue posture and bolus trajectory presented by the swallowing dynamic model were consistent with the VFSS imaging.The brightness in the epiglottis area in VFSS images correlated with the equivalent brightness of SPH particles in the simulation results(r=0.97).As the tongue movement amplitude reducing by 20%,the num-ber of aspirated particles,swallowing efficiency and the average velocity of bolus particles in the oropharyngeal cavity all performed well.Pudding-like fluids exhibited favorable swallowing characteristics even when tongue movement amplitude reducing significantly.Conclusion The swallowing dynamic model can simulate the human swallowing process,providing good support for re-habilitation training of patients with dysphagia and the development of specialized medical foods,demonstrating significant potential for clinical applications.

With the increasing aging population in China and rising incidence rates of diseases such as cancer and cardiovascular conditions, the demand for palliative care services continues to grow. In recent years, the integration of artificial intelligence and medical disciplines has advanced significantly, with machine learning research and applications in the palliative care field progressing steadily. This paper reviews the overview of machine learning, its applications in palliative care, and effectiveness evaluations. It also discusses existing limitations in current research and provides recommendations for future studies. The aim is to assist healthcare professionals in improving palliative care services and offer valuable insights for the development of palliative care in China.

Objective This study aims to extract medical events from the ancient Chinese medical book"Treatise on Febrile Diseases"and explore their internal connections.By constructing an event evolution graph,this study visualizes the progression of diseases related to the three Yang and three Yin,provides new ideas for the digitization of ancient Chinese medical literature,and offers more intuitive learning and reference material for modern clinical practice and education in Traditional Chinese Medicine(TCM).Methods Taking the classic TCM literature"Treatise on Febrile Diseases"as the research subject,we initially used a combination of the BERT model and LSTM-CRF model to identify medical events and their argument constituents in the ancient text.Then,an improved SpERT model was employed to identify multi-event relationships.Finally,we constructed an event evolution graph of"Treatise on Febrile Diseases"with medical events as nodes and event relationships as edges,which represents the internal connections among medical events.Results The models mentioned above achieved a precision rate of 0.768,a recall rate of 0.761,and an F1 score of 0.772 for identifying medical events and their argument constituents.Additionally,achieving a precision rate of 0.736,a recall rate of 0.682,and an F1 score of 0.687 for recognizing complex event relationships.Through the above model,the text of Treatises of Febrile Diseases was extracted,and finally the theory graph was constructed by Neo4j,which contained 3518 medical events and 5294 event relationships.Conclusion The event evolution graph organizes medical events in a cohesive manner,facilitating understanding of the relationships among diseases,patterns,treatments,prescriptions,and outcomes.Therefore,it provides a multidimensional approach for learning and guiding clinical practice in TCM.

Objective This study aims to extract medical events from the ancient Chinese medical book"Treatise on Febrile Diseases"and explore their internal connections.By constructing an event evolution graph,this study visualizes the progression of diseases related to the three Yang and three Yin,provides new ideas for the digitization of ancient Chinese medical literature,and offers more intuitive learning and reference material for modern clinical practice and education in Traditional Chinese Medicine(TCM).Methods Taking the classic TCM literature"Treatise on Febrile Diseases"as the research subject,we initially used a combination of the BERT model and LSTM-CRF model to identify medical events and their argument constituents in the ancient text.Then,an improved SpERT model was employed to identify multi-event relationships.Finally,we constructed an event evolution graph of"Treatise on Febrile Diseases"with medical events as nodes and event relationships as edges,which represents the internal connections among medical events.Results The models mentioned above achieved a precision rate of 0.768,a recall rate of 0.761,and an F1 score of 0.772 for identifying medical events and their argument constituents.Additionally,achieving a precision rate of 0.736,a recall rate of 0.682,and an F1 score of 0.687 for recognizing complex event relationships.Through the above model,the text of Treatises of Febrile Diseases was extracted,and finally the theory graph was constructed by Neo4j,which contained 3518 medical events and 5294 event relationships.Conclusion The event evolution graph organizes medical events in a cohesive manner,facilitating understanding of the relationships among diseases,patterns,treatments,prescriptions,and outcomes.Therefore,it provides a multidimensional approach for learning and guiding clinical practice in TCM.