Transfer Learning in Non-stationary Environments

  • Minku L
Citations of this article
Mendeley users who have this article in their library.
Get full text


Objectives: To examine the association between low positive affect, somatic anxiety and general distress with affective disorders, anxious misery, and visceral fear among coronary heart disease patients. Participants: Patients awaiting a coronary revascularization procedure (N = 158; 20.9% female; median age = 65, interquartile range 58-73) underwent structured interview with the Mini-International Neuropsychiatric Interview. Patients completed a brief version of the Mood and Anxiety Symptom Questionnaire (i.e., Anxiety Depression Distress Inventory-27) and a measure of Type D personality. Results: Somatic anxiety scores yielded an area under the curve (AUC) = .784 and 75.0% sensitivity and 68.5% specificity in relation to panic disorder. Low positive affect yielded AUC = .811 and 70.4% sensitivity and 77.1% specificity for major depression. General distress yielded AUC = .795 and 75.0% sensitivity and 72.5% specificity for generalized anxiety disorder. No affective dimension was optimally associated with the anxious misery or visceral fear cluster. Trait negative affect was not a suitable screener for any disorder. Conclusions: The Anxiety Depression Distress Inventory-27 dimensions of low positive affect and somatic anxiety provided optimal detection of depression and panic disorder, respectively, as hypothesized, supporting discriminant validity. © 2012 Wiley Periodicals, Inc.




Minku, L. L. (2019). Transfer Learning in Non-stationary Environments (pp. 13–37).

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free