Related Experiment Video
Updated: Jan 23, 2026
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
Published on: November 11, 2022
Deep Learning-Based Prediction of Cardiopulmonary Disease in Retinal Images of Premature Infants
Praveer Singh1, Sourav Kumar1, Riya Tyagi2
1Ophthalmology, University of Colorado School of Medicine, Aurora.
Insights
Retinal images from retinopathy of prematurity screening can predict bronchopulmonary dysplasia and pulmonary hypertension in premature infants. This imaging approach may enable earlier diagnosis and reduce invasive testing.
Area of Science:
- Neonatal Medicine
- Ophthalmology
- Medical Imaging
Background:
- Bronchopulmonary dysplasia (BPD) and pulmonary hypertension (PH) are significant causes of mortality and morbidity in premature infants.
- Early detection of BPD and PH is crucial for timely intervention and improved outcomes.
Purpose of the Study:
- To investigate the potential of using retinal images from retinopathy of prematurity (ROP) screening to identify infants with BPD and PH.
- To evaluate a multimodal deep learning model integrating imaging features and demographic data for predicting BPD and PH, comparing its performance against demographic data alone.
Main Methods:
- A deep learning model (ResNet18) was trained on retinal images from the i-ROP study (2012-2020) including infants at risk for ROP.
- Support vector machine models predicted BPD and PH using image features, demographics, or a combination, with secondary models trained on ROP-free images.
- Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) on a held-out test set.
Main Results:
- The multimodal model achieved higher accuracy for BPD prediction (AUC, 0.82) compared to demographics-only (0.72) or imaging-only (0.72) models.
- For PH prediction, the multimodal model showed superior performance (AUC, 0.91) versus the demographics-only model (0.68).
- The predictive value of retinal images persisted even when excluding images with clinical signs of ROP.
Conclusions:
- Retinal images acquired during ROP screening contain features predictive of BPD and PH in preterm infants.
- A multimodal model incorporating imaging and demographic data demonstrates enhanced predictive capability for these conditions.
- This non-invasive approach holds promise for earlier diagnosis of BPD and PH, potentially reducing the need for invasive procedures.
Importance:
Bronchopulmonary dysplasia (BPD) and pulmonary hypertension (PH) are leading causes of morbidity and mortality in premature infants.
Objective:
To determine whether images obtained as part of retinopathy of prematurity (ROP) screening might contain features associated with BPD and PH in infants and whether a multimodal model integrating imaging features with demographic risk factors might outperform a model based on demographic risk alone.
Design, Setting, And Participants:
A deep learning model was used to study retinal images collected from patients enrolled in the multi-institutional Imaging and Informatics in Retinopathy of Prematurity (i-ROP) study. The analysis included infants at risk for ROP undergoing routine ROP screening examinations from 2012 to 2020. Infants were recruited from 7 neonatal intensive care units. Images were limited to 34 weeks' or less postmenstrual age (PMA) so as to precede the clinical diagnosis of BPD or PH. The dataset included the period from June 2015 to April 2020. Data were analyzed from April to June 2025.
Exposures:
BPD was diagnosed by the presence of an oxygen requirement at 36 weeks' PMA, and PH was diagnosed by echocardiogram at 34 weeks. A support vector machine model was trained to predict BPD or PH diagnosis using (1) image features alone (extracted using ResNet18), (2) demographics alone, or (3) image features concatenated with demographics. To reduce the possibility of confounding with ROP, secondary models were trained using only images without clinical signs of ROP.
Main Outcomes And Measures:
For both BPD and PH, performance was reported on a held-out test set and assessed by the area under receiver operating characteristic curve (AUROC).
Results:
A total of 493 infants (mean [SD] gestational age, BPD, 25.7 [1.8] weeks; normal, 27.3 [1.8] weeks; 267 male [54.2%]) were included in this analysis. Performance was reported on a held-out test set (99 patients from the BPD cohort and 37 patients from the PH cohort). For BPD, the multimodal model showed higher accuracy (AUC, 0.82; 95% CI, 0.72-0.90) than demographics-only (0.72; ∆AUC, 0.1; 95% CI, -0.008 to 0.21; P = .07) or imaging-only (0.72; ∆AUC, 0.1; 95% CI, 0.04-0.16; P = .002) models. For PH, multimodal AUC was 0.91 vs the demographics-only 0.68 (∆AUC, 0.14; 95% CI, 0.006-0.27; P = .04) and imaging-only 0.91 (∆AUC, -0.09; 95% CI, -0.3 to 0.12; P = .40) models. Results persisted when trained on images lacking clinical ROP signs.
Conclusions And Relevance:
Results suggest that retinal images obtained during ROP screening may be used to predict the diagnosis of BPD and PH in preterm infants, which may lead to earlier diagnosis and avoid the need for invasive diagnostic testing in the future.
Related Concept Videos
01:21Cardiopulmonary Resuscitation I: Adult
02:27Predicting Molecular Geometry
01:23Cardiopulmonary Resuscitation III: AED Use
01:03Prediction Intervals
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
01:25Cardiopulmonary Resuscitation IV: Pharmacological Management
01:14Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...