Browsing by Subject "Biological system modeling"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Gaussian Process Regression and Monte Carlo Simulation to Determine VOC Biomarker Concentrations Via Chemiresistive Gas Nanosensors
    (IEEE Xplore, 2021-06) Rivera, Paula Angarita; Woollam, Mark; Siegel, Amanda P.; Agarwal, Mangilal; Mechanical and Energy Engineering, School of Engineering and Technology
    Utilizing chemiresistive gas sensors for volatile organic compound (VOC) detection has been a growing area of investigation in the last decade. VOCs have been extensively studied as potential biomarkers for biomedical applications as they are byproducts of metabolic pathways which are dysregulated by disease. Therefore, sensor arrays have been fabricated in previous studies to detect VOC biomarkers. In the process of testing these sensors, it is highly advantageous to quantify the concentration of the VOC biomarkers with high accuracy to diagnose the disease with high sensitivity and specificity. To investigate, analyze, and understand the relation between the concentrations of the VOC to the sensor resistance response, Gaussian Process (GP) models were implemented to predict the behavior of the data with respect to the resistance when the sensor is exposed to a range of concentrations of VOCs. Additionally, the relation between the concentration and resistance of the sensor was studied to predict the concentration of the VOC when a resistance is obtained. Monte Carlo Simulation Sampling from the GP model was utilized to generate data to further understand the trend. The results demonstrated that the relation between the concentration and resistance is linear. The model was tested with sampling data and its accuracy was evaluated.
  • Thumbnail Image
    Item
    Improved Adverse Drug Event Prediction Through Information Component Guided Pharmacological Network Model (IC-PNM)
    (IEEE, 2021) Ji, Xiangmin; Wang, Lei; Hua, Liyan; Wang, Xueying; Zhang, Pengyue; Shendre, Aditi; Feng, Weixing; Li, Jin; Li, Lang; Biostatistics and Health Data Science, Richard M. Fairbanks School of Public Health
    Improving adverse drug event (ADE) prediction is highly critical in pharmacovigilance research. We propose a novel information component guided pharmacological network model (IC-PNM) to predict drug-ADE signals. This new method combines the pharmacological network model and information component, a Bayes statistics method. We use 33,947 drug-ADE pairs from the FDA Adverse Event Reporting System (FAERS) 2010 data as the training data, and the new 21,065 drug-ADE pairs from FAERS 2011-2015 as the validations samples. The IC-PNM data analysis suggests that both large and small sample size drug-ADE pairs are needed in training the predictive model for its prediction performance to reach an area under the receiver operating characteristic curve (\textAUROC)= 0.82(AUROC)=0.82. On the other hand, the IC-PNM prediction performance improved to \textAUROC= 0.91AUROC=0.91 if we removed the small sample size drug-ADE pairs from the prediction model during validation.