Optic Nerve Sheath Diameter and Transcranial Doppler Pulsatility Index for Non-Invasive ICP Assessment in Acute...

Background: Intracranial hypertension is a critical complication of acute intracerebral hemorrhage (ICH), contributing to high early mortality and poor functional outcomes. Invasive intracranial pressure (ICP) monitoring remains the gold standard but carries procedural risks and is resource-intensive. This study evaluated the diagnostic and prognostic utility of optic nerve sheath diameter (ONSD) ultrasonography and transcranial Doppler (TCD)-derived pulsatility index (PI) as non-invasive ICP surrogates in patients with severe ICH. Methods: A prospective observational study was conducted in 42 patients with acute ICH who underwent concurrent invasive ICP monitoring and serial ONSD/PI measurements at 10 time points (T0-T9) between October 2021 and August 2024. Diagnostic performance was assessed using measurement-level receiver operating characteristic (ROC) curve analysis. Exploratory early mortality prediction was evaluated using random forest machine learning models incorporating ONSD, PI, age, and sex. Results: A total of 274 paired ONSD-PI-ICP measurements were obtained. Both ONSD and PI showed moderate positive correlations with invasive ICP (rho = 0.49 and 0.43, respectively; p < 0.001). ONSD demonstrated superior diagnostic accuracy for detecting ICP ≥ 20 mmHg (AUC = 0.83; optimal threshold: 5.88 mm; sensitivity: 81%; specificity: 82%) compared to PI (AUC = 0.75). In exploratory random forest analyses, the combined ONSD-PI model showed high apparent discrimination for elevated ICP detection (AUC = 0.98), while the model incorporating ONSD, PI, age, and sex showed promising but potentially optimistic discrimination for early mortality prediction (AUC = 0.95). These machine learning results should be interpreted cautiously because of the small sample size, repeated-measurement structure, measurement-level data partitioning, and limited number of early deaths. Conclusions: ONSD ultrasonography and TCD-derived PI showed promising performance as non-invasive ICP markers in severe acute ICH. However, because of the small sample size, repeated-measurement design, measurement-level analyses, and exploratory nature of the machine learning models, these findings require validation in larger external cohorts before routine clinical implementation.