Supporting information: Analysis Code. by Jessica Donzowa (21681010)

Subjects:

Predicted probability of the perceived threat of COVID-19 to the family (in green) and to oneself (in orange) by advertisement image (on the y-axis) and country. by Jessica Donzowa (21681010)

Subjects:

Adoption rates of preventive measures by advertisement image and country. by Jessica Donzowa (21681010)

Subjects:

Number of participants by advertisement image and country over the survey period. by Jessica Donzowa (21681010)

Subjects:

Images used in the Facebook advertisements to recruit respondents for the “COVID-19 Health Behavior Survey” conducted between March and August 2020 in eight countries in Europe and... by Jessica Donzowa (21681010)

Subjects:

Feature importance heatmap across all models. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Basic Characteristics of Respondents. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Feature sensitivity analysis. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Hosmer-lemeshow test statistics and p-values. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Learning curves for six machine learning models. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Features importance comparison across models. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

DeLong test results (AUC Comparison). by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Variable definitions and assignments. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

The flow chart of the study. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Key metrics for machine learning. by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

SHAP feature importance (Mean). by Bo Dong (218172)

“…</p><p>Results</p><p>The health status of China’s migrant population is generally positive, though it is influenced by multiple factors, with varying degrees of significance. Among six distinct machine learning models, the Random Forest model demonstrated the best predictive performance. …”

Genome length influences HIV-1 core uncoating and elasticity. by Akshay Deshpande (19648554)

The Vancouver Scar Scale. by Na Wang (193263)

“…</p><p>Results</p><p>We found that numerical rating scale(NRS) score and incidence of breast fistula in group A were significantly lower than other, the continuous decrease of postoperative drainage in group A was higher than other, there were significant differences among groups (p<0.001). …”

S1 Dataset - by Na Wang (193263)

“…</p><p>Results</p><p>We found that numerical rating scale(NRS) score and incidence of breast fistula in group A were significantly lower than other, the continuous decrease of postoperative drainage in group A was higher than other, there were significant differences among groups (p<0.001). …”

Numerical Rating Scale (NRS). by Na Wang (193263)

“…</p><p>Results</p><p>We found that numerical rating scale(NRS) score and incidence of breast fistula in group A were significantly lower than other, the continuous decrease of postoperative drainage in group A was higher than other, there were significant differences among groups (p<0.001). …”