Dataset Information

Brainstem abnormalities in attention deficit hyperactivity disorder support high accuracy individual diagnostic classification.

ABSTRACT: Despite extensive research, psychiatry remains an essentially clinical and, therefore, subjective clinical discipline, with no objective biomarkers to guide clinical practice and research. Development of psychiatric biomarkers is consequently important. A promising approach involves the use of machine learning with neuroimaging, to make predictions of diagnosis and treatment response for individual patients. Herein, we describe predictions of attention deficit hyperactivity disorder (ADHD) diagnosis using structural T(1) weighted brain scans obtained from 34 young males with ADHD and 34 controls and a support vector machine. We report 93% accuracy of individual subject diagnostic prediction. Importantly, automated selection of brain regions supporting prediction was used. High accuracy prediction was supported by a region of reduced white matter in the brainstem, associated with a pons volumetric reduction in ADHD, adjacent to the noradrenergic locus coeruleus and dopaminergic ventral tegmental area nuclei. Medications used to treat ADHD modify dopaminergic and noradrenergic function. The white matter brainstem finding raises the possibility of "catecholamine disconnection or dysregulation" contributing to the ADHD syndrome, ameliorated by medication.

SUBMITTER: Johnston BA

PROVIDER: S-EPMC6869620 | biostudies-literature | 2014 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Brainstem abnormalities in attention deficit hyperactivity disorder support high accuracy individual diagnostic classification.

Johnston Blair A BA Mwangi Benson B Matthews Keith K Coghill David D Konrad Kerstin K Steele J Douglas JD

Human brain mapping 20140513 10

Despite extensive research, psychiatry remains an essentially clinical and, therefore, subjective clinical discipline, with no objective biomarkers to guide clinical practice and research. Development of psychiatric biomarkers is consequently important. A promising approach involves the use of machine learning with neuroimaging, to make predictions of diagnosis and treatment response for individual patients. Herein, we describe predictions of attention deficit hyperactivity disorder (ADHD) diagn ...[more]

PMID: 24819333

Similar Datasets

Project description:BACKGROUND:Psychiatric disorders, such as schizophrenia, attention deficit hyperactivity disorder (ADHD), and bipolar disorder, may sometimes be difficult to diagnose. There is a great need for a valid and reliable diagnostic tool to aid clinicians in arriving at the diagnoses in a timely and accurate manner. Prior studies have suggested that patients suffering from schizophrenia and ADHD may process certain sound stimuli in the brainstem in an unusual manner. When these patient groups have been examined with the electrophysiological method of brainstem audiometry, some studies have found illness-specific aberrations. Such aberrations may also exist for patients suffering from bipolar disorder. OBJECTIVE:In this study, we will examine whether the method of brainstem audiometry can be used as a diagnostic tool for patients suffering from schizophrenia, ADHD, and bipolar disorder. METHODS:The method includes three steps: (1) auditory stimulation with specific sound stimuli, (2) simultaneous measurement of brainstem activity, and (3) automated interpretation of the resulting brain stem audiograms with data-based signal analysis. We will compare three groups of 12 individuals with confirmed diagnoses of schizophrenia, ADHD, or bipolar disorder with 12 healthy subjects under blinded conditions for a total of 48 participants. The extent to which the method can be used to reach the correct diagnosis will be investigated. RESULTS:The project is now in a recruiting phase. When all patients and controls have been recruited and the measurements have been performed, the data will be analyzed according to a previously arranged algorithm. We expect the recruiting phase and measurements to be completed in early 2015, the analyses to be performed in mid-2015, and the results of the study to be published in early 2016. CONCLUSIONS:If the results support previous findings, this will lend strength to the idea that brainstem audiometry can offer objective diagnostic support for patients suffering from schizophrenia, ADHD, and bipolar disorder. A positive result from the study could imply that brainstem audiometry could become an important supportive tool for clinicians in their efforts to diagnose patients with these disorders in a timely and accurate manner. TRIAL REGISTRATION:ClinicalTrials.gov NCT01629355; https://clinicaltrials.gov/ct2/show/NCT01629355 (Archived by WebCite at http://www.webcitation.org/6VBfTwx5H).

Dataset Information

Brainstem abnormalities in attention deficit hyperactivity disorder support high accuracy individual diagnostic classification.

Publications

Brainstem abnormalities in attention deficit hyperactivity disorder support high accuracy individual diagnostic classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure