2024 | Robert Richer, Veronika Koch, Luca Abel, Felicitas Hauck, Miriam Kurz, Veronika Ringgold, Victoria Müller, Arne Küderle, Lena Schindler-Gmelch, Bjoern M. Eskofier, Nicolas Rohleder
This paper investigates the relationship between acute psychosocial stress induction and body posture and movements, aiming to explore the potential of using motion data for stress detection. The study involved 59 participants across two studies (Pilot Study: N = 20, Main Study: N = 39) who underwent the Trier Social Stress Test (TSST) and a stress-free control condition (friendly-TSST; f-TSST) in randomized order. Motion data were collected using inertial measurement unit (IMU)-based motion capture suits. Results showed that acute stress induction led to a reproducible freezing behavior characterized by less overall motion and longer periods of no movement. Machine learning models trained on these data achieved an accuracy of 75.0 ± 17.7% (Pilot Study) and 73.4 ± 7.7% (Main Study) in detecting acute stress from movement information. This suggests that body posture and movements can be used to detect acute psychosocial stress, providing a valuable extension to existing biomarkers for a more holistic understanding of the human stress response. The study is the first to systematically explore the use of full-body posture and movement to gain insights into the human stress response and its effects on the body and mind.This paper investigates the relationship between acute psychosocial stress induction and body posture and movements, aiming to explore the potential of using motion data for stress detection. The study involved 59 participants across two studies (Pilot Study: N = 20, Main Study: N = 39) who underwent the Trier Social Stress Test (TSST) and a stress-free control condition (friendly-TSST; f-TSST) in randomized order. Motion data were collected using inertial measurement unit (IMU)-based motion capture suits. Results showed that acute stress induction led to a reproducible freezing behavior characterized by less overall motion and longer periods of no movement. Machine learning models trained on these data achieved an accuracy of 75.0 ± 17.7% (Pilot Study) and 73.4 ± 7.7% (Main Study) in detecting acute stress from movement information. This suggests that body posture and movements can be used to detect acute psychosocial stress, providing a valuable extension to existing biomarkers for a more holistic understanding of the human stress response. The study is the first to systematically explore the use of full-body posture and movement to gain insights into the human stress response and its effects on the body and mind.