EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Acute Psychological Stress Detection Using Explainable Artificial Intelligence for Automated Insulin Delivery

Mahmoud M. Abdel-Latif, Mudassir M. Rashid, Mohammad Reza Askari, Andrew Shahidehpour, Mohammad Ahmadasas, Minsun Park, Lisa Sharp, Lauretta Quinn, Ali Cinar

Signals · 30.07.2024 · 5 (3) · 494-507

DOI: 10.3390/signals5030026 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Signals, online erschienen am 30.07.2024. Verfasst von Mahmoud M. Abdel-Latif und 8 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIH, JDRF.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Acute psychological stress (APS) is a complex and multifactorial phenomenon that affects metabolism, necessitating real-time detection and interventions to mitigate its effects on glycemia in people with type 1 diabetes. This study investigates the detection of APS using physiological variables measured by the Empatica E4 wristband and employs explainable machine learning to evaluate the importance of the physiological signals. The extreme gradient boosting model is developed for classification of APS and non-stress (NS) with weighted training, achieving an overall accuracy of 99.93%. The Shapley additive explanations (SHAP) technique is employed to interpret the global importance of the physiological signals, determining the order of importance for the variables from most to least as galvanic skin response (GSR), heart rate (HR), skin temperature (ST), and motion sensors (accelerometer readings). The increase in GSR and HR are positively correlated with the occurrence of APS as indicated by high positive SHAP values. The SHAP technique is also used to explain the local signal importance for particular instances of misclassified samples. The detection of APS can inform multivariable automated insulin delivery systems to intervene to counteract the APS-induced glycemic excursions in people with type 1 diabetes.

Förderung

  • NIH
  • JDRF

Zitieren

APA

Abdel-Latif, M. M., Rashid, M. M., Askari, M. R., Shahidehpour, A., Ahmadasas, M., Park, M., Sharp, L., Quinn, L., & Cinar, A. (2024). Acute Psychological Stress Detection Using Explainable Artificial Intelligence for Automated Insulin Delivery. Signals, 5(3), 494-507. https://doi.org/10.3390/signals5030026

Vancouver

Abdel-Latif MM, Rashid MM, Askari MR, Shahidehpour A, Ahmadasas M, Park M, et al. Acute Psychological Stress Detection Using Explainable Artificial Intelligence for Automated Insulin Delivery. Signals. 2024;5(3):494-507. doi:10.3390/signals5030026

BibTeX
@article{AbdelLatif2024,
  author = {Abdel-Latif, Mahmoud M. and Rashid, Mudassir M. and Askari, Mohammad Reza and Shahidehpour, Andrew and Ahmadasas, Mohammad and Park, Minsun and Sharp, Lisa and Quinn, Lauretta and Cinar, Ali},
  title = {Acute Psychological Stress Detection Using Explainable Artificial Intelligence for Automated Insulin Delivery},
  journal = {Signals},
  year = {2024},
  volume = {5},
  number = {3},
  pages = {494--507},
  doi = {10.3390/signals5030026}
}
Kostenlos starten →