Key result
LSTM and RNN models predict stress levels minutes ahead with ~96% accuracy using sensor data.
Why the study?
The study aimed to explore predicting stress in older adults using recurrent neural networks trained on behavioral time series sensor data combined with cortisol biomarkers.
Can RNN and LSTM models accurately predict stress levels using time series sensor data in older adults?
Can RNN and LSTM models accurately predict stress levels using time series sensor data in older adults?
RNN and LSTM models can accurately predict stress levels in older adults using physiological sensor data, potentially enabling proactive interventions.
Answers are grounded in this paper and cite their sources.
May support proactive stress interventions in older adults via wearables; leaves open prospective validation before clinical adoption.
We explore the problem of stress prediction with a combination of behavioral time series sensor data, including Electrodermal Activity (EDA), Blood Volume Pulse (BVP), and Skin Temperature (ST) employing Recurrent Neural Networks (RNNs). The dataset is labeled with cortisol biomarker and TSST protocol for binary stress levels. Leveraging the capabilities of RNNs, specifically Long Short-Term Memory (LSTM) net-works, this research examines the relationship between various behavioral patterns captured by sensors and cortisol levels. The experiment includes data from a targeted age group of 40 older adults. The RNN models are trained to forecast stress levels up to 4.5 minutes ahead, enabling proactive intervention strategies. We report an accuracy of 94% and 96% for RNN and LSTM respectively. Our early investigation showcases the potential of integrating multiple data modalities for accurate stress prediction, underscoring the importance of time series machine learning techniques in stress monitoring applications.
No takes yet. Share an insight, caveat, or question.
Onim et al. (2024) studied Stress (n=40). Recurrent Neural Networks (RNN) and Long Short-Term Memory (LSTM) models was evaluated on Stress prediction accuracy. LSTM and RNN models using time series sensor data predicted stress levels up to 4.5 minutes ahead with 96% and 94% accuracy, respectively.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: