Novel Analysis of Human Stress Using Adult Blood Pressure and Heart Rate Data Using Random Forest Algorithm

Aim: This study uses the Novel Random Forest (RF) algorithm to identify mental stress in adult patients. Heart rate and blood pressure (systolic and diastolic) measurements are utilized to identify mental stress. Materials and Methods: A total of 108402 samples are taken from the Stress Detection of Medical Practitioners dataset, which is hosted on Kaggle. Clincalc, which has two distinct groups, alpha (0.05), power (80<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>), and enrollment ratio, is used to compute the G power for samples. The training dataset (n = 75882) comprises 70% of these samples, whereas the test dataset (n = 32520) comprises 30% of them. To measure how well the RF algorithm performs, accuracy is computed. Results: When it came to the stress detection of medical practitioners and human stress detection datasets, the novel RF method achieved an accuracy of 90.4 % and 88.2%, respectively, whereas logistic regression earned an accuracy of 87.4% and 85.3% (P<0.05). The G power is calculated as 0.8. Conclusion: The results of this investigation show that the RF algorithm outperforms the LR method by a large margin.