2025-09-17 マサチューセッツ大学アマースト校
<関連情報>
- https://www.umass.edu/news/article/hot-flashes-can-be-reliably-predicted-ai-driven-algorithm-developed-umass-amherst-and
- https://onlinelibrary.wiley.com/doi/10.1111/psyp.70056
ジャストインタイム介入のためのほてり予測 Hot Flash Prediction for the Delivery of Just-In-Time Interventions
Nader Naghavi, Thomas Cook, Ryan Turner, Sofiya Shreyer, Katherine Colfer, Sonja Billes, Matthew Smith, Michael Busa
Psychophysiology Published: 18 July 2025
DOI:https://doi.org/10.1111/psyp.70056
ABSTRACT
During menopause, the majority of women experience hot flashes (HF) that have a significant negative impact on sleep and quality of life. Current HF therapies are either ineffective or associated with unacceptable side effects. Digital health technologies offer a novel opportunity to fill this treatment gap with just-in-time thermal interventions through wearable devices. Thermal interventions have shown promise in reducing the negative impact of HFs. We hypothesized that HF event onsets can be accurately and reliably predicted from physiological signals prior to a person’s perception of the events. This study investigated the feasibility of using skin conductance (SC) to predict the onset of HF events before they are subjectively perceived. 62 women who were experiencing HFs and self-reported being in peri- or postmenopause were recruited. Data collection consisted of three remotely conducted 48-h sessions. During each session, SC from the lateral torso was measured continuously and participants logged the precise timing of each perceived HF event onset. We developed new features to identify characteristics of SC signals before HFs were perceived. The best performing model trained with these features identified 82% of HF events on average 17 s before the onset with less than 2% false-positive rate. Among the identified events, the model predicted 69% of HF events before onset. This study demonstrates the feasibility of predicting HF event onsets before subjective perception. Future studies should investigate both multimodal prediction as well as user acceptance and effectiveness of just-in-time thermal interventions.
