This article is more than 5 years old. Information may no longer be current.
Computerized adaptive tests may offer alternative to other psychiatric exams
Computerized adaptive tests — electronic tools that developed personalized assessments by varying the questions a patient was asked — could be an effective primary care screening strategy for anxiety and depression, according to findings recently published in Annals of Family Medicine.
Previous research has suggested only about 4% of adults were screened for depression in primary care 10 years after the U.S. Preventive Services Task Force first recommended such screening, suggesting new screening tools for some psychiatric conditions may be warranted.
“The [Computerized Adaptive Test for Mental Health] has yet to be validated among adult primary care populations,” Andrea K. Graham, PhD, of the department of medical social sciences at Northwestern University, and colleagues wrote.
Thus, they asked 271 adults to complete modules from the Computerized Adaptive Diagnostic Tests for Anxiety, Depression and Major Depressive Disorder, Generalized Anxiety Disorder-7, PHQ-9, PHQ-2, and the Structured Clinical Interview for DSM-5 Diagnoses. The assessments were rotated weekly to lower risk for bias.
Graham and colleagues found that 29 adults would be diagnosed with general anxiety disorder and 31 adults would be diagnosed with major depressive disorder based on the interview. The diagnostic accuracy of the Computerized Adaptive Diagnostic Test for Major Depressive Disorder (area under curve = 0.85) was nearly identical to the PHQ-9 (AUC = 0.84) and higher than that of the PHQ-2 (AUC = 0.76) for major depressive disorder screening. In addition, the accuracy of the Computerized Adaptive Test–Anxiety Inventory (AUC = 0.93) was nearly identical to that of the Generalized Anxiety Disorder-7 (AUC = 0.97) for evaluating anxiety severity when using the interview as the reference standard.
Researchers wrote of other “potential advantages” to Computerized Adaptive Tests from the PCP perspective: patient responses are added to electronic health records and other forms in real time; additional conditions can be added to the module; symptom changes can be observed remotely; and there was less risk for response bias.
Graham and colleagues also noted that from the participants’ standpoint, they seemed more receptive to the Computerized Adaptive Test’s electronic format vs. a paper-based questionnaire. – by Janel Miller
Disclosures: Graham reports no relevant financial disclosures. Please see the study for all other authors’ relevant financial disclosures.