Magnetic resonance images may help identify patients with attention deficit hyperactivity disorder (ADHD) and distinguish among subtypes of the condition, according to a study published in Radiology.
Researchers from China sought to identify cerebral radiomic features related to diagnosis and subtyping of ADHD and to build and evaluate classification models for ADHD diagnosis and subtyping on the basis of the identified features.
A total of 170 children participated in the study: 83 children aged between 7and 14 (71 boys), 40 with ADHD-inattentive (ADHD-I), and 43 with ADHD-combined (ADHD-C, or inattentive and hyperactive) and 87 healthy control subjects. Children ranged in age from 7 to 15. All underwent anatomic and diffusion-tensor MR imaging. Features representing the shape properties of gray matter and diffusion properties of white matter were extracted for each participant.
The initial feature set was input into an all-relevant feature selection procedure within cross-validation loops to identify features with significant discriminative power for diagnosis and subtyping. Random forest classifiers were constructed and evaluated on the basis of identified features.
“The main aim of the current study was to establish classification models that can assist the psychiatrist or clinical psychologist in diagnosing and subtyping of ADHD based on relevant radiomics signatures,” co-author Qiyong Gong, MD, PhD, from the West China Hospital of Sichuan University in Chengdu, said in a release.
The results showed no overall difference between children with ADHD and the control subjects in total brain volume or total gray and white matter volume, but there were alterations in the shape of left temporal lobe, bilateral cuneus, and areas around left central sulcus, which contributed significantly to distinguishing ADHD from typically developing controls.
Overall, the radiomics signatures allowed discrimination of ADHD patients and healthy control children with 74% accuracy and discrimination of ADHD inattentive and ADHD combined subtypes with 80% accuracy.
“This imaging-based classification model could be an objective adjunct to facilitate better clinical decision making,” Gong said in the release. “Additionally, the present study adds to the developing field of psychoradiology, which seems primed to play a major clinical role in guiding diagnostic and treatment planning decisions in patients with psychiatric disorders.”