8,700 Studies Reviewed. 87.0% Found Biological Effects. The Evidence is Clear.
Shield Your Body
Cardiovascular304 citations

Sharma A , Shrivastava S, Shukla S

Bioeffects Seen

Authors not listed · 2020

Share:

AI can predict heart disease with 91.8% accuracy, but similar tools don't exist for EMF health effects.

Plain English Summary

Summary written for general audiences

Researchers developed an artificial intelligence system using machine learning to predict heart disease with 91.8% accuracy. The study used advanced computer algorithms to analyze patient data and identify patterns that indicate heart disease risk. This represents a significant improvement over previous automated diagnostic tools for cardiovascular conditions.

Why This Matters

While this study focuses on artificial intelligence for heart disease prediction rather than EMF effects, it highlights an important gap in our current medical diagnostic capabilities. The reality is that we have sophisticated AI systems that can predict heart disease with over 90% accuracy, yet we lack similar automated tools to identify EMF-related health effects or track exposure patterns that might contribute to cardiovascular problems. The science demonstrates that EMF exposure can affect heart rhythm and cardiovascular function, but our medical system isn't systematically monitoring these connections. What this means for you is that while doctors are getting better at predicting heart disease through data analysis, they're not yet equipped to factor in your daily EMF exposure from cell phones, WiFi, and other wireless devices as a potential contributing factor to cardiovascular health issues.

Exposure Information

Specific exposure levels were not quantified in this study.

Cite This Study
Unknown (2020). Sharma A , Shrivastava S, Shukla S.
Show BibTeX
@article{sharma_a_shrivastava_s_shukla_s_ce3026,
  author = {Unknown},
  title = {Sharma A , Shrivastava S, Shukla S},
  year = {2020},
  doi = {10.1016/j.jksuci.2020.10.013},
  
}
DOI: 10.1016/j.jksuci.2020.10.013

Quick Questions About This Study

The XGBoost algorithm achieved 91.8% accuracy in predicting heart disease, which is higher than many traditional diagnostic methods. However, it's designed to assist doctors, not replace them, by analyzing complex data patterns humans might miss.
Bayesian optimization is a mathematical technique used to fine-tune the machine learning algorithm's settings for maximum accuracy. In this study, it helped optimize the XGBoost classifier to achieve the highest possible prediction performance.
One-Hot encoding converts categorical data (like gender or chest pain type) into numerical format that machine learning algorithms can process more effectively. This preprocessing technique helped improve the model's overall prediction accuracy.
The researchers used five metrics: accuracy (91.8%), sensitivity, specificity, F1-score, and AUC-ROC curves. These measurements collectively demonstrate the system's ability to correctly identify both healthy patients and those at risk for heart disease.
The Cleveland dataset is a standard benchmark in medical AI research, but like most historical medical datasets, it may not fully represent all demographic groups. This could affect how well the model performs across different populations.