Novel Noninvasive and Inexpensive Biomarker for Diagnosing Major Depressive Disorder

Overview

Major depressive disorder (MDD) is a common mental disorder that affects adolescents and adults, causing staggering economic burdens, disabilities in the workforce, and suicidal thoughts, if not treated in time. Invasive and expensive neuroimaging methods, such as functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), and others, have routinely been used to identify several brain regions that are functionally, neurochemically, and structurally abnormal in MDD. The purpose of this study was to identify a noninvasive and inexpensive biomarker that is widely available to supplement the patient health questionnaire (PHQ-9) to accurately diagnose MDD using a machine learning model in silico and corroborate the results with a Drosophila melanogaster model in vivo. In this novel study, statistical analysis was performed for (i) two trials for all measures of Region of Interest (ROI) in the brain using a publicly available T1-weighted fMRI dataset from nineteen never-depressed and nineteen MDD participants (ii) two trials on the Retinal Nerve Fiber Layer (RNFL) and Ganglion Cell Layer-Inner Plexiform Layer (GCL-IPL) on average and individual thickness of each quadrant in both eyes using internal Spectral Domain Optical Coherence Tomography (SD-OCT) scans from 22 never-depressed and 22 MDD participants. Eye thickness was measured in vivo for multiple sets (Control, Withdrawal, Induced Depression, Genetically Modified) of Drosophila melanogaster. In both trials, MDD showed a statistically significant effect for all combined occipital region measures and RNFL and GCL-IPL thickness on the average, and also in each quadrant in both eyes. In three trials for each set of Drosophila, MDD showed a statistically significant effect on the eye thickness. A machine learning bagging ensemble model, created with Decision Tree, KNN, and RFC algorithms, provided an accuracy of 0.9730 for fMRI data and 0.9444 for OCT data. Results from this novel study have suggested that by examining the optic nerve and the innermost layers of the RNFL and GCL-IPL, we can accurately diagnose MDD using a noninvasive and inexpensive routine OCT procedure, and that early diagnosis and treatment of MDD could improve the overall health and quality of life for people living with this disorder.

Competition history

• AJAS 2020 Category not listed

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

• All Biomedical and Health Sciences projects
• AJAS Biomedical and Health Sciences projects
• Every AJAS 2020 project