Leveraging Machine Learning to Identify Predictors of Receiving Psychosocial Treatment for Attention Deficit/Hyperactivity Disorder

(1) Background: Adult attention-deficit/hyperactivity disorder (ADHD) symptoms cause various social difficulties due to attention deficit and impulsivity. In addition, in contrast to ADHD in childhood, ADHD in adulthood is difficult to diagnose due to mixed psychopathologies. This study aimed to determine whether it is possible to predict ADHD symptoms in adults using the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) with machine learning (ML) techniques; (2) Methods: Data collected from 5726 college students were analyzed. The MMPI-2-Restructured Form (MMPI-2-RF) was used, and ADHD symptoms in adults were evaluated using the Attention-Deficit/Hyperactivity Disorder Self-Report Scale (ASRS). For statistical analysis, three ML algorithms were used, i.e., K-nearest neighbors (KNN), linear discriminant analysis (LDA), and random forest, with the ASRS evaluation result as the dependent variable and the 50 MMPI-2-RF scales as predictors; (3) Results: When the KNN, LDA, and random forest techniques were applied, the accuracy was 93.1%, 91.2%, and 93.6%, respectively, and the area under the curve (AUC) was 0.722, 0.806, and 0.790, respectively. The AUC of the LDA method was the largest, with an excellent level of diagnostic accuracy; (4) Conclusions: ML using the MMPI-2 in a large group could provide reliable accuracy in screening for adult ADHD.

Download Full-text

Can neuropsychological testing facilitate differential diagnosis between at-risk mental state (ARMS) for psychosis and adult attention-deficit/hyperactivity disorder (ADHD)?

European Psychiatry ◽

10.1016/j.eurpsy.2018.02.006 ◽

2018 ◽

Vol 52 ◽

pp. 38-44 ◽

Cited By ~ 2

Author(s):

Erich Studerus ◽

Salvatore Corbisiero ◽

Nadine Mazzariello ◽

Sarah Ittig ◽

Letizia Leanza ◽

...

Keyword(s):

Machine Learning ◽

Attention Deficit Hyperactivity Disorder ◽

Differential Diagnosis ◽

Mental State ◽

Attention Deficit ◽

Adult Adhd ◽

Neuropsychological Testing ◽

Verbal Learning ◽

Hyperactivity Disorder ◽

At Risk Mental State

AbstractBackground:Patients with an at-risk mental state (ARMS) for psychosis and patients with attention-deficit/hyperactivity disorder (ADHD) have many overlapping signs and symptoms and hence can be difficult to differentiate clinically. The aim of this study was to investigate whether the differential diagnosis between ARMS and adult ADHD could be improved by neuropsychological testing.Methods:168 ARMS patients, 123 adult ADHD patients and 109 healthy controls (HC) were recruited via specialized clinics of the University of Basel Psychiatric Hospital. Sustained attention and impulsivity were tested with the Continuous Performance Test, verbal learning and memory with the California Verbal Learning Test, and problem solving abilities with the Tower of Hanoi Task. Group differences in neuropsychological performance were analyzed using generalized linear models. Furthermore, to investigate whether adult ADHD and ARMS can be correctly classified based on the pattern of cognitive deficits, machine learning (i.e. random forests) was applied.Results:Compared to HC, both patient groups showed deficits in attention and impulsivity and verbal learning and memory. However, in adult ADHD patients the deficits were comparatively larger. Accordingly, a machine learning model predicted group membership based on the individual neurocognitive performance profile with good accuracy (AUC = 0.82).Conclusions:Our results are in line with current meta-analyses reporting that impairments in the domains of attention and verbal learning are of medium effect size in adult ADHD and of small effect size in ARMS patients and suggest that measures of these domains can be exploited to improve the differential diagnosis between adult ADHD and ARMS patients.

Download Full-text