Presentation Information
[SY-54-05]Precision Psychiatry in Practice: Leveraging fNIRS and Machine Learning for Scalable Diagnostic Biomarkers
*Cyrus Su Hui Ho (National University of Singapore(Singapore))
Keywords:
Precision Psychiatry,Functional near-infrared spectroscopy,Machine learning,Biomarkers
Psychiatry continues to face a critical gap in the availability of definitive, objective biomarkers for diagnosis, prognosis, and treatment stratification. Functional near-infrared spectroscopy (fNIRS), a portable and non-invasive neuroimaging modality, holds promise in addressing this need, particularly when combined with machine learning techniques. In this presentation, I will share findings from our research leveraging fNIRS to differentiate between major psychiatric conditions, including depression, bipolar disorder, and borderline personality disorder. I will demonstrate how machine learning models can enhance diagnostic accuracy and offer potential for predicting treatment responses. Furthermore, I will explore the integration of fNIRS data with other omics-based biomarkers to further refine diagnostic precision. Crucially, this approach may be particularly valuable in low-resource settings, where access to psychiatric expertise is limited, enabling earlier detection and timely intervention. This work marks a meaningful step toward scalable, data-driven solutions that advance the vision of precision psychiatry.