Screening for Adulthood ADHD and Comorbidities in a Tertiary Mental Health Center Using EarlyDetect: A Machine Learning-Based Pilot Study

Abstract

Screening for adult Attention-Deficit/Hyperactivity Disorder (ADHD) and differentiating ADHD from comorbid mental health disorders remains to be clinically challenging. A screening tool for ADHD and comorbid mental health disorders is essential, as most adult ADHD is comorbid with several mental health disorders. The current pilot study enrolled 955 consecutive patients attending a tertiary mental health center in Canada and who completed EarlyDetect assessment, with 45.2% of patients diagnosed with ADHD. The best ADHD classification model using composite scoring achieved a balanced accuracy of 0.788, showing a 2.1% increase compared to standalone ADHD screening, detecting four more patients with ADHD per 100 patients. The classification model including ADHD with comorbidity was also successful (balanced accuracy = 0.712). The results suggest the novel screening method can improve ADHD detection accuracy and inform the risk of ADHD with comorbidity, and may further inform specific comorbidity including MDD and BD.

A systematic review on the application of machine learning models in psychometric questionnaires for the diagnosis of attention deficit hyperactivity disorder

“…Secondly, by focusing on adults with ADHD, ML can also be beneficial in improving diagnosis in this population, as it improves objectivity (Liu et al, 2023). This is because ML models reduce the possibility of cognitive or individual bias in the self-assessment process.…”

“…A perfect prediction has an area under the curve of 1.0, whereas a random prediction has an area under the curve of 0.5 (Poldrack et al, 2020). Nine articles out of 17 specified the AUC of the techniques used (Chen et al, 2023;Christiansen et al, 2020;Duda et al, 2016Duda et al, , 2017Haque et al, 2023;Kim et al, 2021Kim et al, , 2023Liu et al, 2023;Tachmazidis et al, 2020).…”

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

“…The use of machine learning in aiding the diagnosis of ADHD has been covered extensively in existing reviews [ 32 , 34 , 35 ] and will, therefore, not be discussed in detail in this review. Briefly, some evidence suggests that machine learning algorithms have the potential to benefit the diagnosis of ADHD by either simplifying the diagnostic process in complex cases (e.g., achieving similar accuracy with less items, increasing accuracy in patients with comorbidities) [ 43 – 49 ] or increasing accuracy with additional neurobehavioral measures or activity records [ 50 – 55 ]. The contribution of the classification models can be limited by factors such as the sample sizes used, which often contribute toward inflated accuracies.…”

Practical pathway for the management of depression in the workplace: a Canadian perspective

“…Useful screening tools to identify comorbid conditions associated with work-related MDD include the Mood Disorder Questionnaire (MDQ) for bipolar spectrum disorders ( 45 ), the ADHD Self-Report Scale (ASRS) ( 46 ), and Alcohol Use Disorders Identification Test (AUDIT) ( 47 ). Recently, validated, digital and machine-learning-based screening instruments such as EarlyDetect, promise some modern approaches in screening for MDD and other comorbid disorders such as ADHD and bipolar disorder ( 48 – 50 ). However, more research and clinical experience are required before such programs can replace traditional screening instruments.…”