Back

Objective dystonia prediction with MRI after neonatal hypoxic-ischemic encephalopathy

Chintalapati, K.; Miao, H.; Mathur, A.; Neil, J.; Aravamuthan, B. R.

2020-05-29 neurology
10.1101/2020.05.29.20116947 medRxiv
Show abstract

AimTo determine an objective and clinically-feasible method to predict dystonia in cerebral palsy (CP) using magnetic resonance imaging (MRI) following neonatal hypoxic-ischemic encephalopathy (HIE). MethodsIn this retrospective case-control study, we examined brain MRIs in neonates at age 4-5 days who underwent therapeutic hypothermia for HIE at a single tertiary care center. The lower average apparent diffusion coefficient (ADC) values between the left and right striatum and thalamus were determined using clinically-integrated software (IBM iConnect Access). Neonatal neurology, movement disorder, and cerebral palsy specialist notes were screened through age 5 years for motor abnormality documentation. ResultsIn 50 subjects, ADC values significantly predicted dystonia in CP with receiver operator characteristic areas under the curve of 0.862 (p = 0.0004) in the striatum and 0.838 (p = 0.001) in the thalamus. Striatal ADC values less than 1.014x10-3 mm2/s provided 100% specificity and 70% sensitivity for dystonia. Thalamic ADC values less than 0.973x10-3 mm2/s provided 100% specificity and 80% sensitivity for dystonia. InterpretationIn this small retrospective study, analysis of clinically-acquired MRIs predicted dystonia with high specificity following neonatal HIE. This could be a useful prognostication adjunct guiding when to establish appropriate vigilance for dystonia in CP.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.