Machine learning-enabled detection of attention-deficit/hyperactivity disorder with multimodal physiological data: a case-control study

BACKGROUND

Attention-Deficit/Hyperactivity Disorder (ADHD) is a multifaceted neurodevelopmental psychiatric condition that typically emerges during childhood but often persists into adulthood, significantly impacting individuals' functioning, relationships, productivity, and overall quality of life. However, the current diagnostic process exhibits limitations that can significantly affect its overall effectiveness. Notably, its face-to-face and time-consuming nature, coupled with the reliance on subjective recall of historical information and clinician subjectivity, stand out as key challenges. To address these limitations, objective measures such as neuropsychological evaluations, imaging techniques and physiological monitoring of the Autonomic Nervous System functioning, have been explored.

METHODS

The main aim of this study was to investigate whether physiological data (i.e., Electrodermal Activity, Heart Rate Variability, and Skin Temperature) can serve as meaningful indicators of ADHD, evaluating its utility in distinguishing adult ADHD patients. This observational, case-control study included a total of 76 adult participants (32 ADHD patients and 44 healthy controls) who underwent a series of Stroop tests, while their physiological data was passively collected using a multi-sensor wearable device. Univariate feature analysis was employed to identify the tests that triggered significant signal responses, while the Informative k-Nearest Neighbors (KNN) algorithm was used to filter out less informative data points. Finally, a machine-learning decision pipeline incorporating various classification algorithms, including Logistic Regression, KNN, Random Forests, and Support Vector Machines (SVM), was utilized for ADHD patient detection.

RESULTS

Results indicate that the SVM-based model yielded the optimal performance, achieving 81.6% accuracy, maintaining a balance between the experimental and control groups, with sensitivity and specificity of 81.4% and 81.9%, respectively. Additionally, integration of data from all physiological signals yielded the best results, suggesting that each modality captures unique aspects of ADHD.

CONCLUSIONS

This study underscores the potential of physiological signals as valuable diagnostic indicators of adult ADHD. For the first time, to the best of our knowledge, our findings demonstrate that multimodal physiological data collected via wearable devices can complement traditional diagnostic approaches. Further research is warranted to explore the clinical applications and long-term implications of utilizing physiological markers in ADHD diagnosis and management.

Sex- and Subtype-Related Differences in the Comorbidity of Adult ADHDs

OBJECTIVE

Comorbidity in adult ADHD (aADHD) has been investigated in a large number of studies using varying research approaches with divergent results. In contrast, there is limited information about sex- or subtype-related differences from studies with small sample size.

METHOD

A large sample of 910 individuals (458 males, 452 females) affected with aADHD was recruited at a tertiary referral center. All probands underwent a four-step procedure for diagnosing aADHD, including the Structured Clinical Interview of Diagnostic and Statistical Manual of Mental Disorders (4th ed.; DSM-IV) Axis I disorders to assess comorbidity. This study will provide additional information regarding the co-morbidity of Axis I disorders in the currently largest clinical referral sample. However, the main objective of this study is to gain information about sex- or subtype-related differences.

RESULTS

Affected females show higher rates of mood (61% vs. 49%), anxiety (32% vs. 22%), and eating disorders (16% vs. 1%) than affected males, while substance use disorders were more frequent in affected males (45% vs. 29%), which mirrors sex differences in prevalence in the general population. There were hardly any relevant differences in comorbidities between subtypes, with the exception of the inattentive subtype having an especially low prevalence of panic disorder. Comorbidity in general and substance use disorders in particular, but not sex or subtype, were highly predictive of lower psychosocial status.

CONCLUSION

Sex-related differences in the comorbidity of aADHD are more pronounced than subtype-related differences.

Comorbidity in adults with attention-deficit hyperactivity disorder

OBJECTIVE

To examine the prevalence of comorbid Axis I (current and lifetime) and II disorders in adult men and women with attention-deficit hyperactivity disorder (ADHD).

METHOD

Adult patients (n = 447; 266 men, 181 women) received comprehensive assessments for ADHD and Axis I and II disorders. Adults were aged between 17 and 74 years. Among the patients diagnosed with ADHD (n = 335), there were those with ADHD inattentive subtype (ADHD-I) (n = 199), hyperactive-impulsive subtype (ADHD-H) (n = 24), or combined ADHD subtype (ADHD-C) (n = 112). Chi-square and logistic regression analyses were performed to examine associations between adults with and without ADHD on Axis I and II disorders.

RESULTS

Adults with ADHD, compared with those without ADHD, had higher rates of Axis I (46.9% and 27.31%) and Axis II (50.7% and 38.2%) disorders. Adults with ADHD-C were more likely to have mood disorder, anxiety, conduct disorder, and substance use disorder as well as obsessive-compulsive personality disorder, passive-aggressive personality disorder, depressive personality disorder, narcissistic personality disorder, and borderline personality disorder (BPD). Men with ADHD were more likely to have antisocial personality disorder and had higher rates of current drug abuse than women with ADHD. Women with ADHD had higher rates of past and current panic disorder, and past anorexia and bulimia. Women with ADHD were more likely to have BPD than men with ADHD.

CONCLUSIONS

Adults with ADHD have very high rates of comorbid Axis I and II disorders, with differences found between men and women on certain comorbid disorders.