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

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.

Low Frequency Electromagnetic Fields Might Increase the Effect of Enamel Matrix Derivative on Periodontal Tissues

“…Although the pre-clinical in vitro and in vivo testing of this hypothesis may appear straightforward, when it comes to the chosen model, the most challenging factor is possibly the choice of the optimal parameters for EMF stimulation, most noticeably EMF frequency, waveform, and intensity, but also the duration of treatment. The plethora of experimental conditions proposed in the literature has often relied more on technological availability, convenience, or the need to use distinctive instruments and protocols for commercial reasons than purely scientific rationales, but recent attempts to apply machine learning algorithms to pinpoint the most promising experimental parameters [127] may prove a first step in the right direction. The most common stimulation regimes supported by the literature are 75 Hz EMFs with trapezoidal waves, with treatment intensities in the range of 1.5-2.5 mT and 15 Hz PRF PEMF bursts with intensities of 0.3-1.8 mT.…”

Predicting Space Radiation Single Ion Exposure in Rodents: A Machine Learning Approach

“…Recent studies illustrate the use of ML and ensemble methods to automate sleep scoring in rodents using electroencephalogram and electromyogram combination recordings (Gao et al, 2016;Exarchos et al, 2020). More broadly, ML enables the use of human subject-level data in a wide range of medical applications (e.g., bone physiology (Schepelmann et al, 2019), bioelectromagnetics (Halgamuge, 2020), clinical decision making (Chen et al, 2019) -including radiotherapy (Valdes et al, 2017)). Other applications (Cacao et al, 2018) use combinations of stochastic (including Monte-Carlo methods) and physics-based models to predict neuronal dendritic damages caused by exposure to low linear energy transfer radiation (e.g., X-rays, γ-rays and high-energy protons).…”