Performance of Intracranial Pressure Waveform Morphological Features as Biomarkers of Intracranial Hypertension

Intracranial hypertension (IH) is a life-threatening condition requiring timely intervention. Morphology of the intracranial pressure (ICP) waveform, especially the ratio of the second to the first ICP waveform peaks (P2/P1 ratio), may serve as a biomarker for IH.

This study evaluates the potential of the P2/P1 ratio and other morphological features to detect and predict IH and their utility in clinical practice.

Retrospective data from 121 patients with brain injury who underwent both ICP and electrocardiographic monitoring across two neurointensive care units at the University of Pennsylvania were collected between July 1, 2015, and October 31, 2024.

Seven ICP morphological features reflecting peak, amplitude, frequency, and shape domains were calculated every minute. IH events were defined as mean ICP greater than or equal to 20 mm Hg for at least 30 minutes.

Features effectively detected or predicted IH in only a subset of patients, ranging from 20% to 75% for detection and 13% to 53% for prediction. Amplitude-based features outperformed features in other domains, with mean pulse amplitude (AMP) achieving the highest average area under the receiver operating characteristic curve of 0.83 (95% CI, [0.77-0.88]), compared with 0.71 (95% CI [0.67-0.76]) for the P2/P1 ratio. Better amplitude-based feature performance was associated with female sex and traumatic brain injury diagnoses. Optimal classification thresholds varied across individuals. Applying predicted thresholds in real-time monitoring simulations led to reduced performance. AMP achieved the best, albeit suboptimal, performance, with a false-positive rate of 1.77/hr, and IH detection rates of 36%, 54%, and 65% within 30 minutes before onset, 15 minutes after onset, and over the full event duration, respectively.

The ICP morphological features examined demonstrated limited utility in detecting or predicting IH and, in their current form, may not be suitable for routine clinical use.