Using Functional Magnetic Resonance Imaging and Personal Characteristics Features for Detection of Neurological Conditions.

Neuroimaging-based diagnosis could help clinicians in making accurate diagnosis, accessing accurate prognosis, and deciding faster, more effective, and personalized treatment on an individual person basis. In this research work, we aim to develop a neuro-imaging, i.e. functional magnetic resonance imaging (fMRI), based method to detect attention deficit hyper-activity disorder (ADHD), which is a psychiatric disorder categorized by the impulsive nature, lack of attention, and hyper activeness. We utilized fMRI scans as well as personal characteristic features (PCF) data provided as part of ADHD-200 challenge. We aim to train a machine learning classifier by using fMRI and PCF data to classify each participant into one of the following three classes: healthy control (HC), combined-type ADHD (ADHD-C), or inattentive-type ADHD (ADHD-I). We used participants’ PCF and fMRI data separately, and then evaluated the combined use of both the datasets in detecting different classes. Support vector machine classifier with linear kernel was used for the training. The experiments were conducted under two different configurations: (i) 2-way configuration where classification was conducted between HC and ADHD (ADHD-C+ADHD-I) patients, and between ADHD-C and ADHD-I, and (ii) 3-way configuration where data of all the categories (HC, ADHD-C and ADHD-I) was combined together for classification. The 2-way classification approach achieved the diagnostic accuracy of 86.52% and 82.43% in distinguishing HC from ADHD patients, and ADHD-C and ADHD-I, respectively. The 3-way classification revealed classification success rate of 78.59% when both fMRI and PCF data were used together. These results demonstrate the importance of utilizing fMRI data and PCF for the detection of psychiatric disorders.