RESUMEN
BACKGROUND: Retinopathy of prematurity (ROP), a leading cause of childhood blindness, is diagnosed through interval screening by paediatric ophthalmologists. However, improved survival of premature neonates coupled with a scarcity of available experts has raised concerns about the sustainability of this approach. We aimed to develop bespoke and code-free deep learning-based classifiers for plus disease, a hallmark of ROP, in an ethnically diverse population in London, UK, and externally validate them in ethnically, geographically, and socioeconomically diverse populations in four countries and three continents. Code-free deep learning is not reliant on the availability of expertly trained data scientists, thus being of particular potential benefit for low resource health-care settings. METHODS: This retrospective cohort study used retinal images from 1370 neonates admitted to a neonatal unit at Homerton University Hospital NHS Foundation Trust, London, UK, between 2008 and 2018. Images were acquired using a Retcam Version 2 device (Natus Medical, Pleasanton, CA, USA) on all babies who were either born at less than 32 weeks gestational age or had a birthweight of less than 1501 g. Each images was graded by two junior ophthalmologists with disagreements adjudicated by a senior paediatric ophthalmologist. Bespoke and code-free deep learning models (CFDL) were developed for the discrimination of healthy, pre-plus disease, and plus disease. Performance was assessed internally on 200 images with the majority vote of three senior paediatric ophthalmologists as the reference standard. External validation was on 338 retinal images from four separate datasets from the USA, Brazil, and Egypt with images derived from Retcam and the 3nethra neo device (Forus Health, Bengaluru, India). FINDINGS: Of the 7414 retinal images in the original dataset, 6141 images were used in the final development dataset. For the discrimination of healthy versus pre-plus or plus disease, the bespoke model had an area under the curve (AUC) of 0·986 (95% CI 0·973-0·996) and the CFDL model had an AUC of 0·989 (0·979-0·997) on the internal test set. Both models generalised well to external validation test sets acquired using the Retcam for discriminating healthy from pre-plus or plus disease (bespoke range was 0·975-1·000 and CFDL range was 0·969-0·995). The CFDL model was inferior to the bespoke model on discriminating pre-plus disease from healthy or plus disease in the USA dataset (CFDL 0·808 [95% CI 0·671-0·909, bespoke 0·942 [0·892-0·982]], p=0·0070). Performance also reduced when tested on the 3nethra neo imaging device (CFDL 0·865 [0·742-0·965] and bespoke 0·891 [0·783-0·977]). INTERPRETATION: Both bespoke and CFDL models conferred similar performance to senior paediatric ophthalmologists for discriminating healthy retinal images from ones with features of pre-plus or plus disease; however, CFDL models might generalise less well when considering minority classes. Care should be taken when testing on data acquired using alternative imaging devices from that used for the development dataset. Our study justifies further validation of plus disease classifiers in ROP screening and supports a potential role for code-free approaches to help prevent blindness in vulnerable neonates. FUNDING: National Institute for Health Research Biomedical Research Centre based at Moorfields Eye Hospital NHS Foundation Trust and the University College London Institute of Ophthalmology. TRANSLATIONS: For the Portuguese and Arabic translations of the abstract see Supplementary Materials section.
Asunto(s)
Aprendizaje Profundo , Retinopatía de la Prematuridad , Recién Nacido , Lactante , Humanos , Niño , Estudios Retrospectivos , Retinopatía de la Prematuridad/diagnóstico , Sensibilidad y Especificidad , Recien Nacido PrematuroRESUMEN
OBJECTIVE: To determine the accuracy in the identification of infants with treatment-warranted retinopathy of prematurity (ROP) by a trained and experienced ROP neonatal nurse specialist compared with skilled ophthalmologists. METHODS: A single-centre, prospective, blinded, agreement study was performed on a cohort of infants undergoing ROP screening. An experienced ROP neonatal nurse specialist obtained retinal images using a wide field digital retinal imaging system (WFDRI) on 127 infants and identified those with treatment-warranted ROP. This interpretation was compared with the interpretation of the same images by skilled ophthalmologists. The accuracy of the ROP nurse specialist's interpretation was assessed for sensitivity and specificity compared with the gold standard interpretation by the ophthalmologists. RESULTS: The ROP nurse specialist performed 345 ROP screens on both eyes of 127 infants. The mean (SD) gestation age (weeks) and birth weight (g) of the infants screened was 26.8 (2.8) and 929 (327), respectively. The nurse specialist correctly identified all 8 infants with treatment-warranted ROP and 118/119 infants without. The sensitivity and specificity (95% CI) of ROP screening episodes were 100% (63% to 100%) and 99.7% (98.4% to 100.0%), respectively. CONCLUSION: A trained and experienced ROP neonatal nurse specialist can correctly identify infants with treatment-warranted ROP using WFDRI. Further work is required to examine the generalisability of this finding and its impact on ROP screening services.