Deep Learning to Optimize Magnetic Resonance Imaging Prediction of Motor Outcomes After Hypoxic-Ischemic Encephalopathy

Zachary A. Vesoulis*, Shamik B. Trivedi, Hallie F. Morris, Robert C. McKinstry, Yi Li, Amit M. Mathur, Yvonne W. Wu

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Background: Magnetic resonance imaging (MRI) is the gold standard for outcome prediction after hypoxic-ischemic encephalopathy (HIE). Published scoring systems contain duplicative or conflicting elements. Methods: Infants ≥36 weeks gestational age (GA) with moderate to severe HIE, therapeutic hypothermia treatment, and T1/T2/diffusion-weighted imaging were identified. Adverse motor outcome was defined as Bayley-III motor score <85 or Alberta Infant Motor Scale <10th centile at 12 to 24 months. MRIs were scored using a published scoring system. Logistic regression (LR) and gradient-boosted deep learning (DL) models quantified the importance of clinical and imaging features. The cohort underwent 80/20 train/test split with fivefold cross validation. Feature selection eliminated low-value features. Results: A total of 117 infants were identified with mean GA = 38.6 weeks, median cord pH = 7.01, and median 10-minute Apgar = 5. Adverse motor outcome was noted in 23 of 117 (20%). Putamen/globus pallidus injury on T1, GA, and cord pH were the most informative features. Feature selection improved model accuracy from 79% (48-feature MRI model) to 85% (three-feature model). The three-feature DL model had superior performance to the best LR model (area under the receiver-operator curve 0.69 versus 0.75). Conclusions: The parsimonious DL model predicted adverse HIE motor outcomes with 85% accuracy using only three features (putamen/globus pallidus injury on T1, GA, and cord pH) and outperformed LR.

Original languageEnglish (US)
Pages (from-to)26-31
Number of pages6
JournalPediatric neurology
Volume149
DOIs
StatePublished - Dec 2023

Funding

Statement of financial support: 1. NIH Career Development Awards: K23 NS111086 (Vesoulis). 2. NIH Project Grant U01 NS092764 (Wu). 3. Thrasher Research Fund (Wu). Statement of financial support: 1. NIH Career Development Awards: K23 NS111086 (Vesoulis). 2. NIH Project Grant U01 NS092764 (Wu). 3. Thrasher Research Fund (Wu).

Keywords

  • HIE
  • MRI
  • Machine learning
  • Neonatal
  • Outcome

ASJC Scopus subject areas

  • Pediatrics, Perinatology, and Child Health
  • Neurology
  • Developmental Neuroscience
  • Clinical Neurology

Fingerprint

Dive into the research topics of 'Deep Learning to Optimize Magnetic Resonance Imaging Prediction of Motor Outcomes After Hypoxic-Ischemic Encephalopathy'. Together they form a unique fingerprint.

Cite this