Medical undergraduates are burdened with academic and career pressures, and their mental health deserves close attention. This study aims to analyze the current status of mental health among these students and examine how academic-career experience, interpersonal relationships and family finance influence their mental health, as well as the underlying pathways of action.

A multicenter cross-sectional survey was performed from April to September 2025. A total of 1853 undergraduates were recruited from one medical university each in Southwest, Northwest and East China by convenience sampling. Chinese College Students Mental Health Scale (CCSMHS) was used to assess mental health status. Demographic data were collected, including gender, grade, major category, only-child status, and family residence. Academic-career experiences encompassed major satisfaction, course difficulty, academic pressure, attitude toward employment prospects, and career planning clarity. Interpersonal relationships involved relationships with classmates, typical responses to interpersonal conflicts, and psychological feelings brought by romantic relationships. Family financial factors included family atmosphere, family members’ usual practices when disagreement arise, monthly family income, monthly living expenses, and the impact of family economic status on study and life. The scores of each dimension of the scale for medical undergraduate were compared with the norms for ordinary college students. Intergroup difference tests were performed to analyze disparities in psychological scores among students with different demographic characteristics. Spearman correlation analysis was employed to explore correlations between mental health status and its influencing factors. SPSS Amos 28 was applied to construct a structural equation model for mediating effect analysis, and the Bootstrap method with 5000 resamples was adopted to test the significance of mediating effect.

A total of 13.00% of the participants were at high risk for mental health problems. Compared with the norms for ordinary college students, medical students had significantly higher scores in the inferiority and paranoia dimensions (P<0.001), lower scores in 9 dimensions including anxiety, depression, sexual dysfunction, obsession, dependence, impulsivity, psychotic tendency, social withdrawal, and social aggression (P<0.05), but somatization showed no significant intergroup difference (P=0.824). Female students, freshmen and non-clinically majors presented significantly higher overall scores of psychological symptoms (P<0.05). There were no statistically significant differences in scores between only-child and non-only-child students or between urban and rural students. Spearman correlation analysis revealed that academic-career experiences, interpersonal relationships, and family financial factors were all significantly correlated with inferiority and paranoia (P<0.001). The structural equation model showed good fit (χ²/df=2.880, CFI=0.980, TLI=0.972, RMSEA=0.032). Academic-career experiences positively predicted mental health (β=1.501, 95%CI: 0.828 to 2.178, P<0.001), and also positively predicted interpersonal relationships (β=0.211, 95%CI: 0.161 to 0.263, P<0.001). Interpersonal relationships positively predicted mental health (β=6.027, 95%CI: 3.875 to 8.499, P<0.001). The indirect effect of academic-career experiences on mental health through interpersonal relationships was significant (β=1.274, 95%CI: 0.829 to 1.855, P<0.001), accounting for 34.68% of the total effect.

Most medical undergraduates maintain good mental health, with stratified differences by gender, grade and major. Academic-career experiences, interpersonal relationships and family finances are all influencing factors for their mental health; interpersonal relationships exert a mediating role between academic-career experiences and mental well-being. Positive academic-career experiences can directly improve their mental health, and can also indirectly reduce psychological distress through good interpersonal relationships. Accordingly, medical universities should improve interpersonal support systems and implement targeted tiered psychological interventions.

To construct a prognosis prediction model of primary liver cancer after surgical treatment based on synthetic minority over-sampling technique (SMOTE) algorithm and machine learning model.

A retrospective cohort study was conducted on 4 297 patients with primary liver cancer from the surveillance, epidemiology, and end results (SEER) database. One-Hot Encoding and Multiple Imputation were used to preprocess the collect data, and SMOTE algorithm was employed to solve the imbalance of data categories. The obtained clinical variables were included in the machine learning model. Based on decision tree (DT), random forest(RF), gradient boosting decision tree (GBDT) and eXtreme Gradient Boosting(XGBoost), a prognostic prediction model(SMOTE+DT/RF/GBDT/XGBoost) was build, and then the best prediction model was determined by comparing the performance of various models. Finally, a prognostic analysis system for primary liver cancer was developed based on the optimal model, which was then visualized.

The combination model SMOTE+RF showed the best predictive performance, with higher area under the curve(0.895), accuracy(0.811) and precision(0.806) than those of other models in receiver operating characteristic curve(ROC) analysis.

The SMOTE+RF prognostic prediction model can effectively predict the survival outcome of patients with primary liver cancer.