Key result
Personalized neural process models outperformed standard machine learning models in classifying acute stress, achieving an average precision of 0.957 compared to 0.881 for the best general model.
Why the study?
Relationships between affective states and physiological processes measured by wearable sensors can be person-specific, motivating neural processes to address individual differences.
Do personalized neural process models improve acute stress classification from physiological signals compared to standard machine learning models?
Do personalized neural process models improve acute stress classification from physiological signals compared to standard machine learning models?
Neural processes can effectively adapt to person-specific physiological sensor data to improve acute stress classification compared to general machine learning models.
Answers are grounded in this paper and cite their sources.
May enhance research on wearable stress detection; leaves open clinical validation or cardiovascular outcome impact.
Objective: A person's affective state has known relationships to physiological processes which can be measured by wearable sensors. However, while there are general trends those relationships can be person-specific. This work proposes using neural processes as a way to address individual differences. Methods: Stress classifiers built from classic machine learning models and from neural processes are compared on two datasets using leave-one-participant-out cross-validation. The neural processes models are contextualized on data from a brief period of a particular person's recording. Results: The neural processes models outperformed the standard machine learning models, and had the best performance when using periods of stress and baseline as context. Contextual points chosen from other participants led to lower performance. Conclusion: Neural processes can learn to adapt to person-specific physiological sensor data. There are a wide range of affective and medical applications for which this model could prove useful.
No takes yet. Share an insight, caveat, or question.
Stewart et al. (2020) studied Acute stress (n=28). Personalized neural processes (machine learning model) vs. General machine learning models (Lasso, SVM, k-NN) was evaluated on Stress classification performance measured by average precision. Personalized neural process models outperformed standard machine learning models in classifying acute stress, achieving an average precision of 0.957 compared to 0.881 for the best general model.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: