Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Lewes, Delaware, by News Rx journalists, research stated, “The pupillary light reflex (PLR) is the constr iction of the pupil in response to light. The PLR in response to a pulse of ligh t follows a complex waveform that can be characterized by several parameters.” The news correspondents obtained a quote from the research, “It is a sensitive m arker of acute neurological deterioration, but is also sensitive to the backgrou nd illumination in the environment in which it is measured. To detect a patholog ical 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. We assessed the sensitivity of seven PLR parameters t o differences in ambient light, using a smartphone-based pupillometer (AI Pupill ometer, Solvemed Inc.). Nine subjects underwent 345 measurements in ambient cond itions ranging from complete darkness (<5 lx) to bright lig hting ( 10,000 lx). Lighting most strongly affected the initial pupil size, cons triction amplitude, and velocity. Nonlinear models were fitted to find the corre ction function that maximally stabilized PLR parameters across different ambient light levels. Next, we demonstrated that the lighting-corrected parameters stil l discriminated reactive from unreactive pupils. Ten patients underwent PLR test ing in an ophthalmology outpatient clinic setting following the administration o f tropicamide eye drops, which rendered the pupils unreactive. The parameters co rrected for lighting were combined as predictors in a machine learning model to produce a scalar value, the Pupil Reactivity (PuRe) score, which quantifies Pupi l Reactivity on a scale 0-5 (0, non-reactive pupil; 0-3, abnormal/’sluggish’ res ponse; 3-5, normal/brisk response). The score discriminated unreactive pupils wi th 100% accuracy and was stable under changes in ambient illuminat ion across four orders of magnitude. This is the first time that a correction me thod has been proposed to effectively mitigate the confounding influence of ambi ent light on PLR measurements, which could improve the reliability of pupillomet ric parameters both in pre-hospital and inpatient care settings. In particular, the PuRe score offers a robust measure of Pupil Reactivity directly applicable t o clinical practice.”
NETL
NSTL