Evaluation of machine learning algorithms for noninvasive intracranial pressure estimation using near infrared spectroscopy as a covariate.

Abstract

Intracranial pressure (ICP) is a vital parameter that is continuously monitored in patients with severe brain injury and imminent intracranial hypertension. To estimate intracranial pressure without intracranial probes based on transcutaneous near infrared spectroscopy (NIRS). We developed machine learning based approaches for noninvasive intracranial pressure (ICP) estimation using signals from transcutaneous near infrared spectroscopy (NIRS) as well as other cardiovascular and artificial ventilation parameters. In a patient cohort of 25 patients, with 22 used for model development and 3 for model testing, the best performing models were Fourier transform based Transformer ICP waveform estimation which produced a mean absolute error of 4.68 mm Hg (SD = 5.4) in estimation. We did not find a significant improvement in ICP estimation accuracy by including signals measured by transcutaneous NIRS. We expect that with higher quality and greater volume of data, noninvasive estimation of ICP will improve.