Babies born prematurely can develop brain injury within days after birth. Early identification of high-risk infants enables appropriate clinical care to mitigate potential lifelong disabilities. Near infra-red spectroscopy is an established technology that can provide continuous measurements of cerebral oxygen saturation (rcSO(2)) over this critical period. We develop a feature set of the rcSO(2) signal for the purpose of detecting brain injury. Our feature set contains amplitude, spectral, and fractal dimension features within 5 frequency bands. Features are combined in a support vector machine (SVM) and performance is assessed within a cross-validation procedure. Using a cohort of 47 infants of <32 weeks of gestation, we find significant (p < 0 : 0 5) features of amplitude in the frequency band 0.9-3.6 mHz and a fractal dimension measure in the frequency band 1.8-3.6 mHz. The SVM has an area-under the receiver operator characteristic (AUC) of 0.75 with sensitivity-specificity values of 67-77%. These moderate results highlight the potential for quantitative analysis of rcSO(2) to detect brain injury and thus enable early identification of high-risk infants.