Predictive performance and metabolite dynamics of proton MR spectroscopy in neonatal hypoxic-ischemic encephalopathy

Abstract

Background: Prognostic value of proton MR spectroscopy (H-MRS) in hypoxic-ischemic encephalopathy (HIE) is acknowledged; however, effects of gestational age (GA) and postnatal age (PA) on prediction and metabolite levels are unknown.

Methods: One hundred and sixty-nine newborns with moderate-to-severe HIE were studied, having ≥1 H-MRS scan during postnatal days 0-14 and known neurodevelopmental outcome (Bayley-II score/cerebral palsy/death). Initial scans were categorized by PA (day 1-3/4-6/≥7), and metabolite ratios were compared by predictive value. Metabolite dynamics were assessed in a total of 214 scans performed in the study population, using regression modeling, with predictors GA, PA, and outcome.

Results: N-acetyl-aspartate (NAA)/creatine (Cr) and myo-inositol (mI)/NAA height ratios were consistently associated with outcome throughout the first 14 days, with the highest predictive value in the late (≥7 days) period (AUC = 0.963 and 0.816, respectively). Neither GA nor PA had an overall effect on these metabolite ratios, which showed strongest association with outcome (p < 0.001). Assessed separately in patients with good outcome, GA became a significant covariate for metabolite ratios (p = 0.0058 and 0.0002, respectively). However, this association disappeared in the poor outcome group.

Conclusions: In HIE, NAA/Cr and mI/NAA give most accurate outcome prediction throughout postnatal days 0-14. GA only affected metabolite levels in the good outcome group.

Impact: Proton MR spectroscopy metabolite ratios N-acetyl-aspartate/creatine and myo-inositol/N-acetyl-aspartate have persistently high predictive value throughout postnatal days 0-14 in newborns with hypoxic-ischemic encephalopathy, with the highest predictive power between postnatal days 7 and 14. Overall, neither metabolite ratio was affected by gestational age nor by postnatal age, while they showed the strongest association with neurological outcome. However, in newborns facing good outcome, metabolite ratios were associated with gestational age, whereas in cases facing poor outcome, this association disappeared. Proton MR spectroscopy provides valuable prognostic information in neonatal hypoxic-ischemic encephalopathy throughout the first 2 weeks of life, irrespective of the timing of MR scan.

Fig. 1. Algorithm of patient selection for our study, detailing inclusion and exclusion criteria.

^aAge at scan categorization was done based on the initial performed H-MRS scan, where more than one was performed. ^bInitial and control H-MRS spectra were also included, without age at scan categorization. ROC receiver-operating characteristics.

Fig. 2. Representative H-MRS spectra of newborns with moderate-to-severe HIE.

a Gradient echo survey images acquired with echo time (TE) = 5 ms, repetition time (TR) = 75 ms, and 30° flip angle for selection of volume of interest (VOI) from the left thalamus of infants (red frame). b H-MRS of newborn who later had good outcome at TE = 144 ms. c H-MRS of newborn who later had poor outcome at TE = 144 ms. Cho choline, Cr creatine, Cr2 creatine, second peak, Lac lactate, doublet peak, mI myo-inositol, doublet peak, NAA N-acetyl-aspartate. x axis represents chemical shift in parts per million (ppm), y axis represents signal intensity in arbitrary units.

Fig. 3. H-MRS metabolite ratios showing association with outcome across all postnatal age categories (postnatal days 0–14), categorized by outcome and postnatal age category. Bars represent medians, error bars represent interquartile ranges.

mI myo-inositol, NAA N-acetyl aspartate, DOL day of life.