Detecting noncredible symptomology in ADHD evaluations using machine learning.

Abstract

Introduction: Diagnostic evaluations for attention-deficit/hyperactivity disorder (ADHD) are becoming increasingly complicated by the number of adults who fabricate or exaggerate symptoms. Novel methods are needed to improve the assessment process required to detect these noncredible symptoms. The present study investigated whether unsupervised machine learning (ML) could serve as one such method, and detect noncredible symptom reporting in adults undergoing ADHD evaluations.

Method: Participants were 623 adults who underwent outpatient ADHD evaluations. Patients' scores from symptom validity tests embedded in two self-report questionnaires were examined in an unsupervised ML model. The model, called "sidClustering," is based on a clustering and random forest algorithm. The model synthesized the raw scores (without cutoffs) from the symptom validity tests into an unspecified number of groups. The groups were then compared to predetermined ratings of credible versus noncredible symptom reporting. The noncredible symptom ratings were defined by either two or three or more symptom validity test elevations.

Results: The model identified two groups that were significantly (p < .001) and meaningfully associated with the predetermined ratings of credible or noncredible symptom reporting, regardless of the number of elevations used to define noncredible reporting. The validity test assessing overreporting of various types of psychiatric symptoms was most influential in determining group membership; but symptom validity tests regarding ADHD-specific symptoms were also contributory.

Conclusion: These findings suggest that unsupervised ML can effectively identify noncredible symptom reporting using scores from multiple symptom validity tests without predetermined cutoffs. The ML-derived groups also support the use of two validity test elevations to identify noncredible symptom reporting. Collectively, these findings serve as a proof of concept that unsupervised ML can improve the process of detecting noncredible symptoms during ADHD evaluations. With additional research, unsupervised ML may become a useful supplementary tool for quickly and accurately detecting noncredible symptoms during these evaluations.