Computerized Adaptive Diagnosis and Testing of Mental Health Disorders

Abstract

In this review we explore recent developments in computerized adaptive diagnostic screening and computerized adaptive testing for the presence and severity of mental health disorders such as depression, anxiety, and mania. The statistical methodology is unique in that it is based on multidimensional item response theory (severity) and random forests (diagnosis) instead of traditional mental health measurement based on classical test theory (a simple total score) or unidimensional item response theory. We show that the information contained in large item banks consisting of hundreds of symptom items can be efficiently calibrated using multidimensional item response theory, and the information contained in these large item banks can be precisely extracted using adaptive administration of a small set of items for each individual. In terms of diagnosis, computerized adaptive diagnostic screening can accurately track an hour-long face-to-face clinician diagnostic interview for major depressive disorder (as an example) in less than a minute using an average of four questions with unprecedented high sensitivity and specificity. Directions for future research and applications are discussed.

Time to Rethink Our Approach to Patient-Reported Outcome Measures for ESRD

“…Studies clearly show that this inclusion is appreciated by both patients and clinicians and can result in improved outcomes for patients (7,(10)(11)(12).…”

“…It is particularly interesting to note that electronic testing is now attracting increased attention and useful in facilitating reporting to clinicians, permitting more frequent testing, avoiding the drawbacks of repetitive testing, providing useful feedback to clinicians, and improving outcomes (11). A robust literature has developed on the use of computerized adaptive testing (CAT) to establish diagnoses for patients with psychiatric disorders (11).…”

“…A robust literature has developed on the use of computerized adaptive testing (CAT) to establish diagnoses for patients with psychiatric disorders (11). Advantages noted of CAT include a high level of diagnostic precision, the use of a limited number of questions that are most relevant for an individual, and the ability to administer repetitive testing without response set bias, because the questions adapt to the patient responses.…”

“…CAT offers a way to individualize administration of PROMS, minimizing the burden to patients, avoiding the problem of repetitive testing, and facilitating the monitoring of the overall quality of life of patients using a much-reduced number of questions with a high degree of reliability (7,11,12).…”

Dynamic Question Ordering in Online Surveys

“…More recently, IRT-based adaptive testing has been used for diagnoses of mental health disorders through patient questionnaires, for measuring both unidimensional (e.g., (Gardner et al 2004;Fliege et al 2005)) and multidimensional (e.g., (Gibbons et al 2008(Gibbons et al 2012Achtyes et al 2015)) constructs (see overview in (Gibbons et al 2016)). For example, Gibbons et al (2008) use a bifactor IRT model to assess patients' severity of mood and anxiety disorders.…”