Precision Nutrition

See What's
Really In Your Food

Advanced computer vision and scientific datasets estimate microplastic contamination in your meals. Empowering consumers through molecular transparency.

verified_userDOI-Verified SourcessciencePeer Reviewed

Analysis Result

Organic Power Bowl

~127particles
verifiedHigh ConfidenceTier A
12% of daily avg.Low Risk

See It In Action

Upload a meal or select a sample case study.

cloud_upload

Click or drag to upload

JPG, PNG, up to 10MB

Packaging:
Preparation:
Or try a pre-analyzed example
Meal Total
~0particles
range: 32–198 particles
0%
of daily average
check_circleLow Risk

≈ 2 glasses of tap water

Chicken Nuggets

verifiedHigh ConfidenceTier A · ≥45μm
Highly ProcessedSource: Milne et al. 2024
~0
PARTICLES
MIN (8)MAX (120)
tips_and_updates
  • Swapping to grilled breast meat reduces detected particles by ~80%
  • Air frying home-cut potatoes further minimizes microplastic exposure
310 cal·15g protein·18g carbs·20g fat

French Fries

verifiedMedium ConfidenceTier A · ≥45μm
Minimally ProcessedSource: Milne et al. 2024 (extrapolated)
infoEstimated from processed potato products data
~0
PARTICLES
MIN (14)MAX (104)
tips_and_updates
  • Cut and fry potatoes at home to avoid factory processing contamination
  • Use glass or ceramic containers instead of paper-lined cardboard
365 cal·4g protein·48g carbs·17g fat
Recommended Actions
  • ecoSwap plastic containers for glass or ceramic
  • ecoAvoid reheating food in plastic containers
  • ecoIncrease share of whole fruits over packaged snacks

These estimates are based on peer-reviewed research and statistical modeling. Actual microplastic content may vary based on brand, origin, preparation method, and local environmental conditions. This is not medical advice.

Scientific Pipeline

photo_camera

1. Optical Recognition

System identifies specific food matrix and packaging materials from pixels.

database

2. Dataset Matching

Cross-referencing global research on microplastic concentrations in identified matrices.

insights

3. Statistical Modeling

Monte Carlo simulations account for variance in processing and environmental factors.

What makes PlastiScan different?

High-Resolution Accuracy — combining visual detection with peer-reviewed inference to quantify what others can only estimate.

verifiedReal-time DOI updates
verifiedAcademic oversight
verifiedTransparency first
verifiedGlobal food mapping
MOLECULAR SCAN

Transparent Methodology

Quantifying the invisible with rigorous cross-study synthesis.

TierDetection LimitDetection MethodConfidence
ATier A: Empirical> 45 μmVisual + Raman/FTIR SpectroscopyverifiedHigh Confidence
BTier B: Extended~10–100 μmμ-FTIRverifiedMedium Confidence
CTier C: Micro-scale1–5 μmSEM-EDXverifiedMedium Confidence
DTier D: Nano-scale< 1 μmSRS / SEM MicroscopyverifiedLow Confidence
MTier M: Mass-basedN/A (mass)Pyrolysis-GC/MSverifiedMedium Confidence
report

Why Scaling Matters

Research shows particle counts scale exponentially as detection limits decrease. A study detecting at 1.5µm finds orders of magnitude more than one at 45µm — even in the same sample. PlastiScan accounts for these variations to provide balanced “Composite Estimates.”

bookKey References

Milne et al. (2024) — Environmental Science & Technologyarrow_forward
Oliveri Conti et al. (2020) — Environmental Researcharrow_forward
Dessì et al. (2021) — Food Additives & Contaminantsarrow_forward
Qian et al. (2024) — Science Advancesarrow_forward
Hernandez et al. (2019) — Environmental Science & Technologyarrow_forward
Cox et al. (2019) — Environmental Science & Technologyarrow_forward
Hussain et al. (2023) — Environmental Toxicology and Pharmacologyarrow_forward
Kim et al. (2018) — Environmental Science & Technologyarrow_forward
Luo et al. (2022) / Yadav et al. (2023) — ES&T / Sci Total Environarrow_forward