Wild mushroom consumption susceptibility among Chinese university students: A machine learning study

by Yu Chen, Xinjie Zhao, Ying Yue, Zhenyi Li, Si Chen

To investigate factors associated with susceptibility to wild mushroom consumption using machine learning approaches and identify key predictors for targeted intervention development.

A cross-sectional survey of 216 Chinese university students employed three machine learning algorithms (Logistic Regression, Random Forest, Extremely Randomized Trees [ExtraTrees]) to predict consumption susceptibility based on demographics, media usage, and cognitive factors. Susceptibility was assessed through scenario-based questions following established frameworks from tobacco research. Model performance was evaluated using AUC with 95% confidence intervals calculated via bootstrap resampling (1,000 iterations). Sensitivity analyses were conducted using alternative susceptibility thresholds.

65.3% were classified as susceptible to consumption. Logistic Regression achieved highest performance (AUC = 0.776, 95% CI: 0.679–0.862). Risk perception emerged as the strongest predictor (importance = 0.133 ± 0.044), followed by mushroom picking experience (0.101 ± 0.017) and content impression (0.089 ± 0.018). Among the 63 participants (29.2%) who reported using AI models, 75.93% indicated trust levels of ‘fairly trust’ or above.

In this exploratory study of Chinese university students from a single institution, cognitive factors, particularly risk perception and identification ability, showed the strongest associations with consumption susceptibility. These preliminary findings suggest that targeted interventions enhancing risk awareness may be relevant for this population, though replication across diverse samples is needed before broader conclusions can be drawn.

Trajectories and Co‐Occurrence of Perceived Control in Patients With Heart Failure and Self‐Efficacy in Their Caregivers: A Three‐Month Longitudinal Study of Dual Trajectories

ABSTRACT

Aim

This study aims to explore the trajectories and co-occurrence of perceived control and caregiver self-efficacy among patients with heart failure (HF) and their caregivers within 3 months post-discharge and identify associated risk factors.

Design

A prospective cohort design.

Methods

A prospective cohort study was conducted from March to June 2024 in Tianjin, China. Information on perceived control and caregiver self-efficacy was collected 24 h before discharge, 2 weeks, 1 month, and 3 months after discharge. Group-Based Dual Trajectory Modelling (GBDTM) and logistic regression were used for analysis.

Results

The study included 203 dyads of patients with HF and their caregivers (HF dyads). Perceived control identified three trajectories: low curve (15.3%), middle curve (57.1%) and high curve (27.6%). Caregiver self-efficacy demonstrated three trajectories: low curve (17.2%), middle curve (56.7%) and high stable (26.1%). GBDTM revealed nine co-occurrence patterns, with the highest proportion (36.7%) being ‘middle-curve group for perceived control and middle-curve group for caregiver self-efficacy’, and 16.7% being ‘high-curve group for perceived control and high-stable group for caregiver self-efficacy’. Age, gender, household income, NYHA class, symptom burden and psychological resilience were identified as risk factors for perceived control trajectories; marital status, regular exercise and psychological resilience were identified as risk factors for caregiver self-efficacy trajectories.

Conclusion

We identified distinct trajectories, co-occurrence patterns and risk factors of perceived control and caregiver self-efficacy among HF dyads. These findings help clinical nurses to better design and implement interventions, strengthening the comprehensive management and care outcomes for HF dyads.

Impact

These findings highlighted the interactive relationship between perceived control and caregiver self-efficacy trajectories, suggesting that interventions should boost both to improve personalised treatment plans and outcomes for HF dyads.

Reporting Method

This study adhered to the STROBE checklist.

Patient or Public Contribution

Patients and their caregivers contributed by participating in the study and completing the questionnaire.