Machine learning-based detection of acute psychosocial stress from body posture and movements.

Investigating acute stress responses is crucial to understanding the underlying mechanisms of stress. Current stress assessment methods include self-reports that can be biased and biomarkers that are often based on complex laboratory procedures. A promising additional modality for stress assessment might be the observation of body movements, which are affected by negative emotions and threatening situations. In this paper, we investigated the relationship between acute psychosocial stress induction and body posture and movements. We collected motion data from N = 59 individuals over two studies (Pilot Study: N = 20, Main Study: N = 39) using inertial measurement unit (IMU)-based motion capture suits. In both studies, individuals underwent the Trier Social Stress Test (TSST) and a stress-free control condition (friendly-TSST; f-TSST) in randomized order. Our results show that acute stress induction leads to a reproducible freezing behavior, characterized by less overall motion as well as more and longer periods of no movement. Based on these data, we trained machine learning pipelines to detect acute stress solely from movement information, achieving an accuracy of 75.0 ± 17.7 % (Pilot Study) and 73.4 ± 7.7 % (Main Study). This, for the first time, suggests that body posture and movements can be used to detect whether individuals are exposed to acute psychosocial stress. While more studies are needed to further validate our approach, we are convinced that motion information can be a valuable extension to the existing biomarkers and can help to obtain a more holistic picture of the human stress response. Our work is the first to systematically explore the use of full-body body posture and movement to gain novel insights into the human stress response and its effects on the body and mind.

CARWatch - A smartphone application for improving the accuracy of cortisol awakening response sampling.

BACKGROUND: Many studies investigating the cortisol awakening response (CAR) suffer from low adherence to the study protocol as well as from the lack of precise and objective methods for assessing the awakening and saliva sampling times which leads to measurement bias on CAR quantification. METHODS: To address this issue, we have developed "CARWatch", a smartphone application that aims to enable low-cost and objective assessment of saliva sampling times as well as to concurrently increase protocol adherence. As proof-of-concept study, we assessed the CAR of N = 117 healthy participants (24.2 ± 8.7 years, 79.5% female) on two consecutive days. During the study, we recorded awakening times (AW) using self-reports, the CARWatch application, and a wrist-worn sensor, and saliva sampling times (ST) using self-reports and the CARWatch application. Using combinations of different AW and ST modalities, we derived different reporting strategies and compared the reported time information to a Naive sampling strategy assuming an ideal sampling schedule. Additionally, we compared the AUCI, computed using information from different reporting strategies, against each other to demonstrate the effect of inaccurate sampling on the CAR. RESULTS: The use of CARWatch led to a more consistent sampling behavior and reduced sampling delay compared to self-reported saliva sampling times. Additionally, we observed that inaccurate saliva sampling times, as resulting from self-reports, were associated with an underestimation of CAR measures. Our findings also revealed potential error sources for inaccuracies in self-reported sampling times and showed that CARWatch can help in better identifying, and possibly excluding, sampling outliers that would remain undiscovered by self-reported sampling. CONCLUSION: The results from our proof-of-concept study demonstrated that CARWatch can be used to objectively record saliva sampling times. Further, it suggests its potential of increasing protocol adherence and sampling accuracy in CAR studies and might help to reduce inconsistencies in CAR literature resulting from inaccurate saliva sampling. For that reason, we published CARWatch and all necessary tools under an open-source license, making it freely accessible to every researcher.