Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity: Insights from a Multimodal Deep Learning Approach

Wei-Chun Lin; Brian K Jordan; Brian Scottoline; Susan R Ostmo; Aaron S Coyner; Praveer Singh; Jayashree Kalpathy-Cramer; Deniz Erdogmus; R V Paul Chan; Michael F Chiang; J Peter Campbell

doi:10.1016/j.xops.2023.100417

Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity: Insights from a Multimodal Deep Learning Approach

Ophthalmol Sci. 2023 Oct 21;4(2):100417. doi: 10.1016/j.xops.2023.100417. eCollection 2024 Mar-Apr.

Authors

Affiliations

¹ Department of Ophthalmology, Oregon Health & Science University, Portland, Oregon.
² Department of Neonatology, Oregon Health and Science University, Portland, Oregon.
³ Department of Ophthalmology, University of Colorado (CU) School of Medicine, Denver, Colorado.
⁴ Department of Electrical and Computer Engineering, Northeastern University, Boston, Massachusetts.
⁵ Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, Illinois.
⁶ National Eye Institute, National Institutes of Health, Bethesda, Maryland.
⁷ National Library of Medicine, National Institutes of Health, Bethesda, Maryland.

Abstract

Purpose: Retinopathy of prematurity (ROP) is one of the leading causes of blindness in children. Although the role of oxygen in the pathophysiology of ROP is well established, a precise understanding of the dynamic relationship between oxygen exposure ROP incidence and severity is lacking. The purpose of this study was to evaluate the correlation between time-dependent oxygen variables and the onset of ROP.

Design: Retrospective cohort study.

Participants: Two hundred thirty infants who were born at a single academic center and met the inclusion criteria were included. Infants are mainly born between January 2011 and October 2022.

Methods: Patient data were extracted from electronic health records (EHRs), with sufficient time-dependent oxygen data. Clinical outcomes for ROP were recorded as none/mild or moderate/severe (defined as type II or worse). Mixed-effects linear models were used to compare the 2 groups in terms of dynamic oxygen variables, such as daily average and the coefficient of variation (COV) fraction of inspired oxygen (FiO₂). Support vector machine (SVM) and long-short-term memory (LSTM)-based multimodal models were trained with fivefold cross-validation to predict which infants would develop moderate/severe ROP. Gestational age (GA), birth weight, and time-dependent oxygen variables were used to develop predictive models.

Main outcome measures: Model cross-validation performance was evaluated by computing the mean area under the receiver operating characteristic (AUROC) curve, precision, recall, and F1 score.

Results: We found that both daily average and COV of FiO₂ were associated with more severe ROP (adjusted P < 0.001). With fivefold cross-validation, the multimodal LSTM models had higher performance than the best static models (SVM using GA and 3 average FiO₂ features) and SVM models trained on GA alone (mean AUROC = 0.89 ± 0.04 vs. 0.86 ± 0.05 vs. 0.83 ± 0.04).

Conclusions: The development of severe ROP might not only be influenced by oxygen exposure but also by its fluctuation, which provides direction for future study of pathophysiological factors associated with severe ROP development. Additionally, we demonstrated that multimodal neural networks can be a method to extract useful information from time-series data, which may be a valuable methodology for the investigation of other diseases using EHR data.

Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Keywords: Deep learning; Machine learning; Multimodal model; Retinopathy of prematurity; Time series data.

Abstract

Grants and funding