Four-Class Classification of Neuropsychiatric Disorders by Use of Functional Near-Infrared Spectroscopy Derived Biomarkers

Abstract

Diagnosis of most neuropsychiatric disorders relies on subjective measures, which makes the reliability of final clinical decisions questionable. The aim of this study was to propose a machine learning-based classification approach for objective diagnosis of three disorders of neuropsychiatric or neurological origin with functional near-infrared spectroscopy (fNIRS) derived biomarkers. Thirteen healthy adolescents and sixty-seven patients who were clinically diagnosed with migraine, obsessive compulsive disorder, or schizophrenia performed a Stroop task, while prefrontal cortex hemodynamics were monitored with fNIRS. Hemodynamic and cognitive features were extracted for training three supervised learning algorithms (naïve bayes (NB), linear discriminant analysis (LDA), and support vector machines (SVM)). The performance of each algorithm in correctly predicting the class of each participant across the four classes was tested with ten runs of a ten-fold cross-validation procedure. All algorithms achieved four-class classification performances with accuracies above 81% and specificities above 94%. SVM had the highest performance in terms of accuracy (85.1 ± 1.77%), sensitivity (84 ± 1.7%), specificity (95 ± 0.5%), precision (86 ± 1.6%), and F1-score (85 ± 1.7%). fNIRS-derived features have no subjective report bias when used for automated classification purposes. The presented methodology might have significant potential for assisting in the objective diagnosis of neuropsychiatric disorders associated with frontal lobe dysfunction.

Atypical frontotemporal cortical activity in first-episode adolescent-onset schizophrenia during verbal fluency task: A functional near-infrared spectroscopy study

“…The ROC analysis found that the change in oxy-Hb concentration in 7 channels had a good sensitivity and specificity for distinguishing adolescents with SCZ from their healthy counterparts, with a high sensitivity of 0.821 and specificity of 0.909 obtained in channel 4. In addition to previous findings that neurological features based on the frontotemporal cortex are potential biomarkers for SCZ ( 40 ), our study suggested that oxy-Hb changes during the VFT might be a promising imaging biomarker for adolescents with SCZ; however, large-scale studies are needed to verify our findings.…”

IT IS NOT A SMALL WORLD FOR PSYCHIATRIC PATIENTS: Small-world of psychiatric patients

“…The protocol was approved by the Ethics Committee of Pamukkale University in 2008. Our group has previously published portions of this data using analysis methods other than those used in the current study (Akgul, Akin, & Sankur, 2006; Ata Akin et al, 2006; Ciftçi, Sankur, Kahya, & Akin, 2008; Dadgostar, Setarehdan, Shahzadi, & Akin, 2016; Dalmis & Akin, 2015; Einalou, Maghooli, Setarehdan, & Akin, 2015, 2016, 2017; Erdoğan & Yükselen, 2022; Koray Ciftci, Bulent Sankur, Yasemin P Kahya, & Ata Akin, 2008; Sergul Aydore, M. Kivanc Mihcak, Koray Ciftci, & Ata Akin, 2010). All subjects gave written and signed consent to participate in the study before the experiment.…”

It is Not a Small World for Psychiatric Patients

“…All experiments were performed in accordance with relevant guidelines and regulations of the Ethics Committee, which abide with the Helsinki Declaration. Our group has previously published portions of this data using analysis methods other than those used in the current study [20][21][22][23][24][25][26][27][28][29][30] . All subjects gave written and signed consent to participate in the study before the experiment.…”