Machine learning approach for ambient-light-corrected parameters and the Pupil Reactivity score in smartphone-based pupillometry

Abstract

Introduction: The pupillary light reflex (PLR) is the constriction of the pupil in response to light. The PLR in response to a pulse of light follows a complex waveform that can be characterized by several parameters. It is a sensitive marker of acute neurological deterioration, but is also sensitive to the background illumination in the environment in which it is measured. To detect a pathological change in the PLR, it is therefore necessary to separate the contributions of neuro-ophthalmic factors from ambient illumination. Illumination varies over several orders of magnitude and is difficult to control due to diurnal, seasonal, and location variations.

Methods and results: We assessed the sensitivity of seven PLR parameters to differences in ambient light, using a smartphone-based pupillometer (AI Pupillometer, Solvemed Inc.). Nine subjects underwent 345 measurements in ambient conditions ranging from complete darkness (<5 lx) to bright lighting (≲10,000 lx). Lighting most strongly affected the initial pupil size, constriction amplitude, and velocity. Nonlinear models were fitted to find the correction function that maximally stabilized PLR parameters across different ambient light levels. Next, we demonstrated that the lighting-corrected parameters still discriminated reactive from unreactive pupils. Ten patients underwent PLR testing in an ophthalmology outpatient clinic setting following the administration of tropicamide eye drops, which rendered the pupils unreactive. The parameters corrected for lighting were combined as predictors in a machine learning model to produce a scalar value, the Pupil Reactivity (PuRe) score, which quantifies Pupil Reactivity on a scale 0-5 (0, non-reactive pupil; 0-3, abnormal/"sluggish" response; 3-5, normal/brisk response). The score discriminated unreactive pupils with 100% accuracy and was stable under changes in ambient illumination across four orders of magnitude.

Discussion: This is the first time that a correction method has been proposed to effectively mitigate the confounding influence of ambient light on PLR measurements, which could improve the reliability of pupillometric parameters both in pre-hospital and inpatient care settings. In particular, the PuRe score offers a robust measure of Pupil Reactivity directly applicable to clinical practice. Importantly, the formulae behind the score are openly available for the benefit of the clinical research community.

Keywords: Artificial Intelligence (AI); Pupil Reactivity; Pupil Reactivity (PuRe) score; critical care; intensive care unit; neurocritical care; pupillary light reflex (PLR); pupillometry.