0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Detection Methods Food & Water Gut & Microbiome Human Health Effects Policy & Risk Sign in to save

What Drives Microplastic Exposure in Human Blood and Feces? Machine Learning Reveals Potential Key Influencing Factors

Environmental Science & Technology 2025 Score: 48 ? 0–100 AI score estimating relevance to the microplastics field. Papers below 30 are filtered from public browse.
Pengcheng Tu, Junhao Xie, Junhao Xie, Xueqing Li, Xue Ma, Mingluan Xing, Mingluan Xing, Huixia Niu, Lizhi Wu, Zhe Mo, Xin Gong, Xiaoming Lou, Z P Chen, Bei Gao, Jun-Li Xu, Jun-Li Xu

Summary

Researchers analyzed 229 blood and 227 fecal samples for microplastics using pyrolysis-GC-MS and applied machine learning to identify the strongest predictors of microplastic body burden. The model identified diet, packaging use, and indoor environment as key drivers of microplastic levels in human blood and feces, highlighting lifestyle factors as modifiable exposure determinants.

Models
Study Type Environmental

Microplastics are pervasive environmental pollutants, making human exposure unavoidable. Although previous studies have detected microplastics in human blood and feces, these investigations were limited by small sample sizes and key contributors to microplastic biomonitoring remain underexplored. In this study, we analyzed 229 blood and 227 fecal samples using pyrolysis-gas chromatography-mass spectrometry to quantify microplastic exposure and identify key influencing factors through machine learning modeling. Seven polymer types were detected in both biological matrices, including polyethylene, poly(vinyl chloride) (PVC), polypropylene, polystyrene, polyamide 66, poly(ethylene terephthalate), and poly(methyl methacrylate), with polyethylene, PVC, and polystyrene being the most prevalent. A significant negative correlation was observed between blood and fecal PVC levels, while other polymers showed no significant intermatrix association. Demographic, lifestyle, socioeconomic, and dietary information were collected via questionnaires. Age, sex, geographic, and indoor environmental variations in microplastic levels were observed. Machine learning models were developed to predict microplastic levels from anthropometric measurements and questionnaire data. Explainable AI tools revealed that the drinking water source was the strongest predictor of blood PVC levels. Socioeconomic factors, including income and education, were also significant predictors, with lower-income individuals showing higher microplastic burdens. This approach provides a framework for understanding and mitigating microplastic exposure.

Sign in to start a discussion.

More Papers Like This

Article Tier 2

Assessment of microplastics in human stool: A pilot study investigating the potential impact of diet-associated scenarios on oral microplastics exposure

In this pilot study, 15 volunteers followed different plastic-use and food consumption scenarios, and microplastics were detected in every stool sample collected, with polyethylene being the most common type. Using plastic packaging for food and eating highly processed foods were statistically linked to higher microplastic levels in stool, providing early evidence that dietary choices influence how many microplastics people ingest.

Meta Analysis Tier 1

Quantitative evaluation of microplastic interference with gut microbiota: Identifying sensitive indicators and key factors

This meta-analysis combined with machine learning found that the Firmicutes-to-Bacteroidetes ratio is the most sensitive biomarker of microplastic-induced gut microbiome disruption, with exposure concentration, particle size, and duration as the key drivers. The resulting predictive model (R=0.91) offers a quantitative tool for assessing gastrointestinal harm from microplastic exposure.

Article Tier 2

Microplastics in human feces and their correlation with dietary behavior: A pilot study

This pilot study analyzed microplastics in human fecal samples and examined correlations with dietary habits, finding that seafood and packaged food consumption were associated with higher fecal microplastic counts. The results provide early evidence linking diet to human microplastic exposure levels.

Article Tier 2

Predicting aqueous sorption of organic pollutants on microplastics with machine learning

Researchers developed machine learning models to predict how organic pollutants bind to microplastics in water, using data from 475 published experiments. The models outperformed traditional approaches by accounting for properties of both the microplastics and the pollutants simultaneously. The study provides a more universal tool for understanding how microplastics can transport and concentrate harmful chemicals in freshwater systems.

Article Tier 2

Appraisal of microplastic pollution and its related risks for urban indoor environment in Bangladesh using machine learning and diverse risk evolution indices

This first-of-its-kind study in Bangladesh found an average of about 26 microplastic particles per gram of household dust in urban homes, with polystyrene being the most common type. Children were estimated to ingest roughly twice as many microplastic particles per day as adults through household dust exposure. The pollution levels were rated moderate to high, suggesting that indoor environments are a significant source of microplastic exposure for people.

Share this paper