Fetal pHocus: A Novel Approach to Non-Invasive Fetal Arterial Blood pH Assessment via Near-Infrared Spectroscopy

Modern intrapartum fetal health assessments are currently limited to monitoring heart rate and spatial parameters, neglecting critical biomarkers that remain unmeasurable with today's clinical devices without performing surgery. Without precise evaluations of oxygen levels and blood acidity, clinicians are forced to rely on postnatal assessments to gauge fetal well-being, a delay that may obscure timely intervention. Fetal blood pH is a vital indicator of acid-base balance and cellular health, as any deviation could indicate potential health risks such as hypoxia and acidemia. In this study, we leverage the indirect relationship between pH and oxygen saturation to estimate fetal blood pH non-invasively using near-infrared (NIR) spectroscopy with wavelengths optimized for light transmission depth and oxygen saturation measurements. A convolutional neural network (CNN) extracts features from the acquired data, enabling accurate prediction of fetal blood pH using our machine learning (ML) model. Evaluation using hypoxic sheep models demonstrated an average prediction error of just 0.023 pH units, with all rounds maintaining errors below 0.05 pH units.