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.
Pain is a vital function of the human body which serves as an early warning signal to protect tissue damage. The extent to which an individual experiences pain still remains a complex and subjective phenomenon and is considered to depend on a variety of intrinsic and extrinsic factors that include the efficiency of communication between the nociceptors and their subcortical and cortical projections1 besides genetics, past experiences, and cultural influences. Although the current common methodology for pain assessment relies on self-reports in clinical practice, there may be conditions where patients are unable to provide verbal self-reports such as a surgical procedure performed under anesthesia or in situations where the patient is unconscious due to a variety of conditions such as critical cerebral tissue damage. Patients with severe cognitive impairments or patients who preserve their mental abilities but who cannot communicate with their external environment may also be unable to provide objective and accurate self-reports of their pain experience.
Emotion regulation, a fundamental aspect of human functioning, involves the ability to monitor, evaluate, and modify emotional responses. Understanding the neural mechanisms underlying emotion regulation holds significant implications across various disciplines, including psychology, neuroscience, and clinical psychiatry. This study aims to explore the neural correlates of emotion regulation using functional near-infrared spectroscopy (fNIRS) with a specific focus on the prefrontal cortex (PFC). fNIRS, a non-invasive and portable brain imaging technology, offers an excellent opportunity to investigate real-life emotion processing with high temporal resolution. Twenty participants underwent an experimental protocol where they viewed emotional pictures from the International Affective Picture System (IAPS) database, varying in valence (positive and negative) and arousal (high and low). fNIRS data were collected during the picture presentation, and the hemodynamic responses in the PFC were analyzed. The findings demonstrated distinct spatiotemporal patterns of activation associated with different emotional states. Positive valence stimuli elicited higher hemodynamic activation in bilateral dorsolateral prefrontal cortex (DLPFC) and orbitofrontal cortex (OFC) regions when compared to negative valence stimuli. On the other hand, negative valence stimuli induced higher activation in the medial prefrontal cortex (mPFC) when compared to positive valence stimuli. Moreover, high arousal positive valence stimuli evoked higher activation in the left DLPFC region when compared to high arousal negative valence stimuli. These results shed light on the differential neural processing of positive and negative emotions within the PFC, supporting the notion of lateralized emotional processing. The study validates the feasibility of fNIRS for objectively capturing emotion-related neural activity, providing valuable insights for future applications in emotion recognition and affective brain-computer interfaces (BCIs). Understanding the neural basis of emotion regulation has significant implications for designing targeted interventions for individuals experiencing emotion dysregulation disorders. Additionally, the integration of fNIRS technology into affective BCIs may offer new possibilities for real-time emotion detection and communication in populations with communication challenges.
Individuals suffering from Obsessive Compulsive Disorder (OCD) and Schizophrenia (SCZ) frequently exhibit symptoms of cognitive disassociations, which are linked to poor functional integration among brain regions. The loss of integration can be assessed using graph metrics computed from functional connectivity matrices (FCMs) derived from neuroimaging data. A healthy brain with an effective connectivity pattern exhibits small-world features with high clustering coefficients and shorter path lengths in contrast to random networks. We analyzed neuroimaging data from 60 subjects (13healthy controls, 21 OCD and 26 SCZ) using functional near-infrared spectroscopy (fNIRS) during a color word matching Stroop Task and computed FCMs. Small-world features were evaluated using the Global Efficiency ( GE ), Clustering Coefficient ( CC ), Modularity ( Q ), and small-world parameter ( σ ). The proposed pipeline in this study for fNIRS data processing demonstrates that patients with OCD and SCZ exhibit small-world features resembling random networks, as indicated by higher GE and lower CC values compared to healthy controls, implying a higher operational cost for these patients. AUTHOR SUMMARY: Individuals suffering from Obsessive Compulsive Disorder (OCD) and Schizophrenia (SCZ) frequently exhibit symptoms of cognitive disassociations, which are linked to poor functional integration among brain regions. The loss of integration can be assessed using graph metrics computed from functional connectivity matrices (FCMs) derived from neuroimaging data. A healthy brain with an effective connectivity pattern exhibits small-world features with high clustering coefficients and shorter path lengths in contrast to random networks. We analyzed neuroimaging data from 60 subjects (13healthy controls, 21 OCD and 26 SCZ) using functional near-infrared spectroscopy (fNIRS) during a color word matching Stroop Task and computed FCMs. Small-world features were evaluated using the Global Efficiency ( GE ), Clustering Coefficient ( CC ), Modularity ( Q ), and small-world parameter ( σ ). The proposed pipeline in this study for fNIRS data processing demonstrates that patients with OCD and SCZ exhibit small-world features resembling random networks, as indicated by higher GE and lower CC values compared to healthy controls, implying a higher operational cost for these patients.
Problem Statement: Pain has a crucial function in the human body acting as an early warning signal to protect against tissue damage. However, both assessment of pain experience and its clinical diagnosis rely on highly subjective methods. Objective evaluation of the presence of pain under analgesic drug administrations becomes even more complicated. Objectives: The aim of this study was to propose a transfer learning (TL) based deep learning (DL) methodology for accurate detection and objective classification of the neural processing of painful and non-painful stimuli that were presented under different levels of analgesia. Method: A publicly available fNIRS dataset of 14 participants was obtained during an experimental protocol that involved painful and non-painful events. Separate fNIRS scans were taken under the same nociceptive protocol before analgesic drug (Morphine and Placebo) administration and at three different times (30,60 and 90 min) post-administration. By utilizing data from pre-drug fNIRS scans, a DL architecture for classifying painful and non-painful stimuli was constructed as a base model. Knowledge generated in pre-drug base model was transferred to 6 distinct post-drug conditions by adapting a TL approach. The DeepSHAP method was utilized to unveil the contribution weights of nine R OIs for each of the pre-drug and post-drug models. Results: Mean performance of pre-drug base model was above 95% for accuracy, sensitivity, specificity and AUC metrics. Each of the post-drug models had mean accuracy, sensitivity, specificity and AUC performance above 90%. No statistically significant difference across post-drug models were found for classification performance of any of the performance metrics. Post-placebo models had higher decoding accuracy than post-morphine models. Conclusion: Knowledge obtained from a pre-drug base model could be successfully utilized to build pain decoding models for six distinct brain states that were altered with either analgesic or placebo intervention. Contribution of different cortical regions to classification performance varied across the post-drug models. Importance: The proposed methodology may remove the necessity to build new DL models for data collected at clinical or daily life conditions for which obtaining training data is not practical or building a new decoding model will have a computational cost. Unveiling the explanation power of different cortical regions may aid the design of more computationally efficient fNIRS based BCI system designs that target other application areas.
Background: Migraine diagnosis and severity staging rest on clinical interviews according to the ICHD-3 criteria, with no validated objective biomarker. Functional near-infrared spectroscopy (fNIRS) is a portable and non-invasive method, but existing fNIRS migraine classification studies remain relatively small and rely on cognitive tasks. We assessed whether prefrontal hemodynamic responses with a head-down-to-knees maneuver separate migraine patients from controls, and high- from low-severity migraine. Methods: Prefrontal fNIRS, including short separation channels, was recorded during the maneuver in 50 interictal migraine patients and 52 controls screened for the absence of migraine, serious chronic conditions and hypertension. Nine hemodynamic parameters per chromophore (HbO, Hb and HbT) across thirty channels entered a hypothesis-neutral pipeline of 270 candidate pipelines (3 chromophores × 3 feature selection strategies × 30 classifiers) with no predefined region of interest. Results: Deoxyhemoglobin features selected by embedded L1 regularization with shrinkage-regularized linear discriminant analysis separated the groups with 92% balanced accuracy on the internal hold-out (92% sensitivity, 92% specificity, ROC-AUC 0.99; permutation p = 3 × 10−4), against 87% in development-set cross-validation and 88% under nested selection cross-validation, with a selection bias of +0.03. High- vs. low-severity classification (19 high, 31 low) did not exceed chance under nested validation (45%; permutation p = 0.45). Conclusions: A wide-scale pipeline achieved a robust, validated separation of migraine from screened controls, carried by a distributed venous-weighted deoxyhemoglobin signature; specificity against other headache disorders remains to be established. Attack frequency severity was not separable above chance, indicating that scalar hemodynamic descriptors are sufficient for a categorical but not a graded contrast.