Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity

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

doi:10.1016/j.xops.2023.100417

Cited by 4 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…oxygen concentration and prolonged mechanical ventilation [3]. Some predictive models include the latter variable [4].…”

Section: Study Populationmentioning

confidence: 99%

“…Among the many risk factors associated with the need for ROP treatment [1] are low gestational age, low birth weight, poor weight gain, postnatal sepsis, transfusions, multiple births, bronchopulmonary dysplasia and perinatal morbidity [2]. Other factors that have been studied in this context include fluctuations in oxygenation, high levels of oxygen concentration and prolonged mechanical ventilation [3]. Some predictive models include the latter variable [4].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mechanical Ventilation, Retinal Avascularity and Rate of Vascularisation: A Triad of Predictors for Retinopathy of Prematurity Treatment

Protsyk,

García Serrano

2024

JPM

View full text Add to dashboard Cite

Aim: The temporal avascular area of the retina and the duration of mechanical ventilation (DMV) may predict the need to treat retinopathy of prematurity (ROP). This study considers whether the rate of retinal vascularisation and related risk factors should be included in a predictive model of the need for ROP treatment. Methods: This single-centre, observational retrospective case–control study was conducted on 276 preterm infants included in an ROP screening programme. All had undergone at least three examinations of the fundus. The main outcome measures considered were DMV (in days of treatment), the temporal avascular area (in disc diameters, DD) and the rate of temporal retinal vascularisation (DD/week). Results: The multivariate logistic model that best explains ROP treatment (R2 = 63.1%) has three significant risk factors: each additional day of mechanical ventilation (OR, 1.05 [95% CI, 1.02–1.09]; p = 0.001); each additional DD of temporal avascular area (OR, 2.2 [95% CI, 1.7–2.9]; p < 0.001) and a vascularisation rate <0.5 DD/week (OR, 19.0 [95% CI, 6.5–55.5]; p < 0.001). Two tables are presented for calculating the expected need for ROP treatment according to these three risk factors. Conclusions: A greater DMV, a broad avascular area of the temporal retina at the first binocular screening and slow retinal vascularisation strongly predict the need for ROP treatment. The predictive model we describe must be validated externally in other centres.

show abstract

“…oxygen concentration and prolonged mechanical ventilation [3]. Some predictive models include the latter variable [4].…”

Section: Study Populationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Mechanical Ventilation, Retinal Avascularity and Rate of Vascularisation: A Triad of Predictors for Retinopathy of Prematurity Treatment

Protsyk,

García Serrano

2024

JPM

View full text Add to dashboard Cite

show abstract

Risk factors for the time to development of retinopathy of prematurity in premature infants in Iran: a machine learning approach

Tapak,

Farahani,

Taleghani

et al. 2024

BMC Ophthalmol

View full text Add to dashboard Cite

An Interpretable System for Screening the Severity Level of Retinopathy in Premature Infants Using Deep Learning

Yang,

Zhou,

Zhang

et al. 2024

Bioengineering

View full text Add to dashboard Cite

Accurate evaluation of retinopathy of prematurity (ROP) severity is vital for screening and proper treatment. Current deep-learning-based automated AI systems for assessing ROP severity do not follow clinical guidelines and are opaque. The aim of this study is to develop an interpretable AI system by mimicking the clinical screening process to determine ROP severity level. A total of 6100 RetCam Ⅲ wide-field digital retinal images were collected from Guangdong Women and Children Hospital at Panyu (PY) and Zhongshan Ophthalmic Center (ZOC). A total of 3330 images of 520 pediatric patients from PY were annotated to train an object detection model to detect lesion type and location. A total of 2770 images of 81 pediatric patients from ZOC were annotated for stage, zone, and the presence of plus disease. Integrating stage, zone, and the presence of plus disease according to clinical guidelines yields ROP severity such that an interpretable AI system was developed to provide the stage from the lesion type, the zone from the lesion location, and the presence of plus disease from a plus disease classification model. The ROP severity was calculated accordingly and compared with the assessment of a human expert. Our method achieved an area under the curve (AUC) of 0.95 (95% confidence interval [CI] 0.90–0.98) in assessing the severity level of ROP. Compared with clinical doctors, our method achieved the highest F1 score value of 0.76 in assessing the severity level of ROP. In conclusion, we developed an interpretable AI system for assessing the severity level of ROP that shows significant potential for use in clinical practice for ROP severity level screening.

show abstract

Oxygenation Fluctuations Associated with Severe Retinopathy of Prematurity

Cited by 4 publications

References 41 publications

Mechanical Ventilation, Retinal Avascularity and Rate of Vascularisation: A Triad of Predictors for Retinopathy of Prematurity Treatment

Mechanical Ventilation, Retinal Avascularity and Rate of Vascularisation: A Triad of Predictors for Retinopathy of Prematurity Treatment

Risk factors for the time to development of retinopathy of prematurity in premature infants in Iran: a machine learning approach

An Interpretable System for Screening the Severity Level of Retinopathy in Premature Infants Using Deep Learning

Contact Info

Product

Resources

About