ArticlePloS one2025
Identifying key determinants of health among China's migrant population using machine learning methods: Evidence from the china migrants dynamic survey.
Article in PloS one, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. It carries an expression of concern. Cited by 2 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
2 citing papers in PubMed.
- Article
- Integrating migration into cancer geography: spatial clustering of five digestive cancer burden in China.Frontiers in public health · 2026Article
Corrections and comments
- Expression of concern
Authors and funding
5 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundContinuously improving health security for the migrant population is a key component of China's healthcare system reform. Existing research indicates that migrant health is influenced by multiple factors, yet the relative importance of these factors remains inadequately measured. This study aims to analyze the current health status of China's migrant population and rank the primary factors influencing their health based on importance.
methodsData were sourced from the 2018 China Migrants Dynamic Survey, including 108,669 cases after data cleaning. The health status of the migrant population was initially analyzed using frequency and percentage distributions. Logistic regression was then applied to examine the relationship between various factors and migrant health. Subsequently, six machine learning methods (Neural Network, Random Forest, Support Vector Machine, Gradient Boosting Machine, Extra Trees, and Decision Tree) were applied to rank the importance of these factors. A multidimensional performance metric system (accuracy, precision, recall, F1 score, and AUC value) was employed to comprehensively evaluate the classification performance of the models. SHAP (Shapley Additive Prediction) values were used to illustrate the contribution of different factors to the health status of the migrant population.
resultsThe 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. Its results indicate that the key factors affecting migrant health are age, employment, income, and education level. SHAP value analysis reveals that stable employment, higher education levels, and higher income are positively correlated with better health outcomes, while age was predominantly negatively correlated, indicating a detrimental effect on health status.
conclusionThe overall health status of China's migrant population is relatively optimistic. However, their disadvantaged positions in areas such as education and income expose them to higher health risks. To address these key determinants, further improvements in health safeguards should focus on: developing stratified intervention strategies based on age structure differences; optimizing work environments and employment security; enhancing health literacy; and strengthening public health emergency management and social support systems.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.