Figures index : Transradial Access - A Predictive Model to Assess Radial Artery Diameter : Science and Education Publishing

Figures index

American Journal of Medicine Studies. 2022, 10(1), 1-7 doi:10.12691/ajms-10-1-1

Figure 1a. Example of upper extremity CT slice used for right radial artery measurement

Figure 1b. Example of upper extremity CT slice with coinciding right radial artery measurement label used for analysis

Figure 2a. Example of lower extremity/pelvic CT slice used for right femoral artery measurement

Figure 2b. Example of lower extremity/pelvic CT slice with coinciding right femoral artery measurement label used for analysis

Figure 3. Comparison of femoral artery to radial artery diameter per decedent

Figure 4. Results of final 100 iterations of random forest classifier training steps

Figure 5. Visualization of random forest classifier model with the model’s features and weights. The cell color spectrum, from orange to blue, represents the confidence that a decedent’s radial artery is greater than 2.5mm (more orange) or less than 2.5mm (more blue). The Gini index can be seen decreasing further along the forest, thus indicating less variance and improved classification. Conclusively, the plot yields a decision tree for evaluating if the decedent’s radial artery is greater than or less than 2.5mm. These data also contained the associated biographic and demographic features (height(cm), carcinogen exposure, smoking history, biological sex, weight(kg), age(years), alcohol use history, and recreation drug use/substance use exposure). When the node’s statement is true, one moves to the left to the next node, and false to the right

Figure 6. Results of linear regression model when predicting radial artery diameter from femoral artery diameter and other biographical variables. The linear algorithm reveals the following listed features from most to least significant: femoral artery diameter(mm), height(cm), carcinogen exposure(1 if yes, 0 if no), smoking history(1 if yes, 0 if no), biological sex(1if male, 0 if female), weight(kg), age(years), alcohol exposure(1 if any lifetime alcohol exposure, 0 if none), and recreation drug exposure(1 if any lifetime recreational drug exposure, 0 if none)