Diagnostic performance of synthetic relaxometry for predicting neurodevelopmental outcomes in premature infants: a feasibility study

Abstract

ObjectivesTo investigate the predictability of synthetic relaxometry for neurodevelopmental outcomes in premature infants and to evaluate whether a combination of relaxation times with clinical variables or qualitative MRI abnormalities improves the predictive performance.MethodsThis retrospective study included 33 premature infants scanned with synthetic MRI near or at term equivalent age. Based on neurodevelopmental assessments at 18-24 months of corrected age, infants were classified into two groups (no/mild disability [n = 23] vs. moderate/severe disability [n = 10]). Clinical and MRI characteristics associated with moderate/severe disability were explored, and combined models incorporating independent predictors were established. Ultimately, the predictability of relaxation times, clinical variables, MRI findings, and a combination of the two were evaluated and compared. The models were internally validated using bootstrap resampling.ResultsProlonged T1-frontal/parietal and T2-parietal periventricular white matter (PVWM), moderate-to-severe white matter abnormality, and bronchopulmonary dysplasia were significantly associated with moderate/severe disability. The overall predictive performance of each T1-frontal/-parietal PVWM model was comparable to that of individual MRI finding and clinical models (AUC = 0.71 and 0.76 vs. 0.73 vs. 0.83, respectively; p > 0.27). The combination of clinical variables and T1-parietal PVWM achieved an AUC of 0.94, sensitivity of 90%, and specificity of 91.3%, outperforming the clinical model alone (p = 0.049). The combination of MRI finding and T1-frontal PVWM yielded AUC of 0.86, marginally outperforming the MRI finding model (p = 0.09). Bootstrap resampling showed that the models were valid.ConclusionsIt is feasible to predict adverse outcomes in premature infants by using early synthetic relaxometry. Combining relaxation time with clinical variables or MRI finding improved prediction.