This publication was supported by The Fannie E. Rippel Foundation/American Federation Research New Investigator Award on Gender Differences in Aging (PI: Thurston) and the Pittsburgh Mind-Body Center (National Institutes of Heath grants HL076852/076858).
Improving the performance of physiologic hot flash measures with support vector machines
Article first published online: 26 JAN 2009
Copyright © 2009 Society for Psychophysiological Research
Volume 46, Issue 2, pages 285–292, March 2009
How to Cite
Thurston, R. C., Matthews, K. A., Hernandez, J. and De La Torre, F. (2009), Improving the performance of physiologic hot flash measures with support vector machines. Psychophysiology, 46: 285–292. doi: 10.1111/j.1469-8986.2008.00770.x
- Issue published online: 11 FEB 2009
- Article first published online: 26 JAN 2009
- (ReceivedMarch 4, 2008; Accepted June 15, 2008.)
- Behavioral medicine;
Hot flashes are experienced by over 70% of menopausal women. Criteria to classify hot flashes from physiologic signals show variable performance. The primary aim was to compare conventional criteria to Support Vector Machines (SVMs), an advanced machine learning method, to classify hot flashes from sternal skin conductance. Thirty women with ≥4 hot flashes/day underwent laboratory hot flash testing with skin conductance measurement. Hot flashes were quantified with conventional (≥2 μmho, 30 s) and SVM methods. Conventional methods had poor sensitivity (sensitivity=0.41, specificity=1, positive predictive value (PPV)=0.94, negative predictive value (NPV)=0.85) in classifying hot flashes, with poorest performance among women with high body mass index or anxiety. SVM models showed improved performance (sensitivity=0.89, specificity=0.96, PPV=0.85, NPV=0.96). SVM may improve the performance of skin conductance measures of hot flashes.