Ventriculomegaly thresholds for prediction of symptomatic post-hemorrhagic ventricular dilatation in preterm infants.

Abstract

Benefits from early surgical intervention in preterm infants with intraventricular hemorrhage (IVH) prior to symptomatic ventriculomegaly must be weighed against risks of surgery. We calculated thresholds of common ventriculomegaly indices at a late-intervention institution to predict subsequent symptomatic ventriculomegaly requiring neurosurgery. We retrospectively reviewed neuroimaging and neurosurgical outcomes in preterm infants with grade III/IV IVH between 2007 and 2020. Frontal-occipital horn ratio (FOHR), frontal-temporal horn ratio (FTHR), anterior horn width (AHW), and ventricular index (VI) were measured. Area under the receiver operating curve (AUC) for predicting intervention (initiated after progressive symptomatic ventriculomegaly) was calculated for diagnostic scan, scans during weeks 1-4, and maximum measurement prior to intervention. Threshold values that optimized sensitivity and specificity were derived. A total of 1254 scans in 132 patients were measured. In all, 37 patients had a neurosurgical intervention. All indices differed between those with and without intervention from the first diagnostic scan (p < 0.001). AUC of maximum measurement was 97.1% (95% CI 94.6-99.7) for FOHR, 97.7% (95% CI 95.6-99.8) for FTHR, 96.6% (95% CI 93.9-99.4) for AHW, and 96.8% (95% CI 94.0-99.5) for VI. Calculated thresholds were FOHR 0.66, FTHR 0.62, AHW 15.5 mm, and VI 8.4 mm > p97 (sensitivities >86.8%, specificities >90.1%). Ventriculomegaly indices were greater for patients who developed progressive persistent ventriculomegaly from the first diagnostic scan and predicted neurosurgical intervention. We derived thresholds of common ventriculomegaly indices (ventricular index, anterior frontal horn width, fronto-occipital horn and fronto-temporal horn index) to best predict the development of progressive symptomatic post-hemorrhage hydrocephalus in preterm infants with intraventricular hemorrhage. While current thresholds were established by a priori expert consensus, we report the first data-driven derivation of ventriculomegaly thresholds across all indices for the prediction of symptomatic hydrocephalus. Data-derived thresholds will more precisely weigh the risks and benefits of early intervention.