Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
, 61 (4), 471-493

Predicting Post-Experiment Fatigue Among Healthy Young Adults: Random Forest Regression Analysis

Affiliations

Predicting Post-Experiment Fatigue Among Healthy Young Adults: Random Forest Regression Analysis

Eun-Young Mun et al. Psychol Test Assess Model.

Abstract

The current study utilized a random forest regression analysis to predict post-experiment fatigue in a sample of 212 healthy participants (mean age = 20.5, SD = 2.21; 52% women) between the ages of 18 and 30 following a mildly stressful experiment. We used a total of 30 features of demographic variables, lifestyle variables, alcohol and other drug use behaviors and problems, state anxiety and depressive symptoms, and physiological indicators that were lab assessed or self-reported. A random forest regression analysis with 10-fold cross-validation resulted in accurate prediction of post-experiment fatigue (R2 equivalent = 0.93) with the average "out-of-bag" (OOB) R2 = 0.52. Not surprisingly, self-reported pre-experiment fatigue was the most important variable (54%) in the prediction of post-experiment fatigue. Feeling anxious (state anxiety) pre- and post-experiment (3%, 7%), feeling less vigorous post experiment (3%), systolic and diastolic blood pressure (3%, 2%) and LF HRV (2%) assessed at baseline, and self-reported alcohol-related problems (3%) and sleep (2%) additionally contributed to the prediction of post-experiment fatigue. Other remaining input variables had relatively minimal importance. Substantively, this study suggests that complex interactions across multiple systems domains that support regulation may be linked to fatigue. A random forest regression analysis can relatively easily be implemented with a built-in cross-validation function and reveal a web of connections undergirding health behavior and risks.

Keywords: fatigue; machine learning; random forests; regulation; stress.

Figures

Figure 1:
Figure 1:
Bivariate correlations of all pairs of variables (features). The target variable, self-reported post-experiment fatigue was most strongly correlated with the following variables in the order of magnitude: Pre-experiment POMS fatigue (0.73), post-experiment STAI state anxiety (.45), pre-experiment STAI state anxiety (0.40), CESD depressive symptoms (0.33), post-experiment POMS vigor (−.30), systolic blood pressure at baseline (−.21), diastolic blood pressure at baseline (−.20), LF/HF ratio (.16) at baseline, mean heart rate during the last task session (.13), HF HRV at baseline (−.13), mean heart rate at baseline (0.12), and light to moderate physical activity (0.12)
Figure 2:
Figure 2:
Before (top) and after (bottom) preprocessing and scaling data for analysis
Figure 3:
Figure 3:
OOB error rate drops as the number of trees (estimators) increases
Figure 4:
Figure 4:
Measures of variable (feature) importance in predicting post-experiment fatigue
Figure 5:
Figure 5:
Measures of baseline variable (feature) importance in predicting pre-experiment fatigue

Similar articles

See all similar articles

LinkOut - more resources

Feedback