RF Safe

Supervised Machine Learning Algorithms for Bioelectromagnetics: Prediction Models and Feature Selection Techniques Using Data from Weak Radiofrequency Radiation Effect on Human and Animals Cells.

International journal of environmental research and public health · 2020 · Unclear · Insufficient evidence

← Research stream
UnclearInsufficient evidencePaper 5636

Using extracted data from 300 publications (1127 experimental case studies), Random Forest showed the best prediction performance across groups, with reported AUC = 0.903 (k-fold = 60). The authors report a robust correlation of SAR with frequency and of cumu…

Study snapshot

PublicationInternational journal of environmental research and public health · 2020
Study typeother
Reported directionUnclear
Evidence ratingInsufficient

Abstract

The emergence of new technologies to incorporate and analyze data with high-performance computing has expanded our capability to accurately predict any incident. Supervised Machine learning (ML) can be utilized for a fast and consistent prediction, and to obtain the underlying pattern of the data better. We develop a prediction strategy, for the first time, using supervised ML to observe the possible impact of weak radiofrequency electromagnetic field (RF-EMF) on human and animal cells without performing in-vitro laboratory experiments. We extracted laboratory experimental data from 300 peer-reviewed scientific publications (1990-2015) describing 1127 experimental case studies of human and animal cells response to RF-EMF. We used domain knowledge, Principal Component Analysis (PCA), and the Chi-squared feature selection techniques to select six optimal features for computation and cost-efficiency. We then develop grouping or clustering strategies to allocate these selected features into five different laboratory experiment scenarios. The dataset has been tested with ten different classifiers, and the outputs are estimated using the k-fold cross-validation method. The assessment of a classifier's prediction performance is critical for assessing its suitability. Hence, a detailed comparison of the percentage of the model accuracy (PCC), Root Mean Squared Error (RMSE), precision, sensitivity (recall), 1 - specificity, Area under the ROC Curve (AUC), and precision-recall (PRC Area) for each classification method were observed. Our findings suggest that the Random Forest algorithm exceeds in all groups in terms of all performance measures and shows AUC = 0.903 where k-fold = 60. A robust correlation was observed in the specific absorption rate (SAR) with frequency and cumulative effect or exposure time with SAR×time (impact of accumulated SAR within the exposure time) of RF-EMF. In contrast, the relationship between frequency and exposure time was not significant. In future, with more experimental data, the sample size can be increased, leading to more accurate work.

Machine Enhanced Logic

AI evidence extraction

Structured fields below were generated from the paper’s abstract and metadata to make the evidence easier to inspect. Automated extraction may be incomplete or incorrect; verify important details against the original paper.

Study typeother
Effect directionunclear
PopulationHuman and animal cells (in-vitro experimental case studies extracted from published literature)
Sample size1127
ExposureRF
Evidence strengthInsufficientConfidence: 74% · Peer reviewed: yes

Main findings

Using extracted data from 300 publications (1127 experimental case studies), Random Forest showed the best prediction performance across groups, with reported AUC = 0.903 (k-fold = 60). The authors report a robust correlation of SAR with frequency and of cumulative exposure time with SAR×time, while the relationship between frequency and exposure time was not significant.

Outcomes measured

  • Machine-learning classifier performance for predicting cellular response to RF-EMF (e.g., AUC, accuracy, RMSE, precision, sensitivity/recall, specificity, PRC area)
  • Associations/correlations among exposure parameters (e.g., SAR with frequency; cumulative exposure time with SAR×time)

Limitations

  • This is a supervised machine-learning modeling study using previously published experimental data rather than new biological experiments
  • Exposure details (e.g., specific frequencies, SAR levels, exposure durations) are not specified in the abstract
  • The abstract does not report the direction or magnitude of RF-EMF biological effects on cells, focusing instead on prediction performance and feature relationships
View raw extracted JSON
{
  "study_type": "other",
  "exposure": {
    "band": "RF",
    "source": null,
    "frequency_mhz": null,
    "sar_wkg": null,
    "duration": null
  },
  "population": "Human and animal cells (in-vitro experimental case studies extracted from published literature)",
  "sample_size": 1127,
  "outcomes": [
    "Machine-learning classifier performance for predicting cellular response to RF-EMF (e.g., AUC, accuracy, RMSE, precision, sensitivity/recall, specificity, PRC area)",
    "Associations/correlations among exposure parameters (e.g., SAR with frequency; cumulative exposure time with SAR×time)"
  ],
  "main_findings": "Using extracted data from 300 publications (1127 experimental case studies), Random Forest showed the best prediction performance across groups, with reported AUC = 0.903 (k-fold = 60). The authors report a robust correlation of SAR with frequency and of cumulative exposure time with SAR×time, while the relationship between frequency and exposure time was not significant.",
  "effect_direction": "unclear",
  "limitations": [
    "This is a supervised machine-learning modeling study using previously published experimental data rather than new biological experiments",
    "Exposure details (e.g., specific frequencies, SAR levels, exposure durations) are not specified in the abstract",
    "The abstract does not report the direction or magnitude of RF-EMF biological effects on cells, focusing instead on prediction performance and feature relationships"
  ],
  "evidence_strength": "insufficient",
  "confidence": 0.74,
  "peer_reviewed_likely": "yes",
  "keywords": [
    "radiofrequency electromagnetic field",
    "RF-EMF",
    "weak radiofrequency radiation",
    "machine learning",
    "supervised learning",
    "Random Forest",
    "feature selection",
    "PCA",
    "chi-squared",
    "specific absorption rate",
    "SAR",
    "in-vitro",
    "human cells",
    "animal cells",
    "cross-validation",
    "AUC"
  ],
  "suggested_hubs": []
}
AI can be wrong. Always verify against the paper.

AI-extracted fields are generated from the abstract and metadata and may be incomplete or incorrect. This material is for informational purposes and is not medical advice.

Identifiers and source

DOI: 10.3390/ijerph17124595
PubMed: 32604814

Read the original paper →

Related papers

← Back to the Research Library