A transformation of oxygen saturation (the saturation virtual shunt) to improve clinical prediction model calibration...

The relationship between peripheral oxygen saturation (SpO₂) and the inspired oxygen concentration is non-linear. SpO₂ is frequently used as a dichotomized predictor, to manage this non-linearity. We propose the saturation virtual shunt (VS) as a transformation of SpO₂ to a continuous linear variable to improve interpretation of disease severity within clinical prediction models.

We calculate the saturation VS based on an empirically derived approximation formula between physiological VS and SpO₂. We evaluated the utility of the saturation VS in a clinical study predicting the need for facility admission in children in a low resource health-care setting.

The transformation was saturation VS = 68.864 × log₁₀(103.711 - SpO₂) - 52.110. The ability to predict hospital admission based on a dichotomized SpO₂ produced an area under the receiver operating characteristic curve of 0.57, compared to 0.71 based on the untransformed SpO₂ and saturation VS. However, the untransformed SpO₂ demonstrated a lack of fit compared to the saturation VS (goodness-of-fit test p value < 0.0001 vs 0.098). The observed admission rates varied non-linearly with the untransformed SpO₂ but varied linearly with the saturation VS.

The saturation VS estimates a continuous linearly interpretable disease severity based on SpO₂ and improves clinical prediction.