A Novel Method to Improve Inter-Clinician Variation in the Diagnosis of Retinopathy of Prematurity Using Machine Learning

Nisha, K. L.; Ganapathy, Sreelekha; Savithri, Sathidevi Puthumangalathu; Idaguri, Madhu; Mohanachandran, Poornima; Vinekar, Anand; Chandra, Parijat; Kulkarni, Sucheta; Dogra, Mangat R

doi:10.1080/02713683.2022.2139847

Cited by 7 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study compared the accuracy of autorefraction with subjective refraction for diagnosing refractive error. It was found that autorefractors caused minus over-correction leaves to overestimate myopia (Nisha et al, 2023). In the current study, 36% and 88.3% of eyes accepted AR and retinoscopy sphere estimates, respectively.…”

Section: Figure 1: Distribution Of Gender In the Study Populationsupporting

confidence: 41%

Comparison Between Autorefraction and Retinoscopy for Subjective Correction in Children

YAR,

ZAHID,

NAWAB

et al. 2023

Biol Clin Sci Res J

View full text Add to dashboard Cite

The study's objective was to compare the accuracy of retinoscopy and autorefraction for subjective correction in children. The study was conducted in the Department of Ophthalmology at Nishtar Medical Hospital from June 2021 to May 2022, and it was a prospective study. The study included 60 children aged between 6 to 15 years who had asthenopic symptoms and blurring of vision. The children were given cyclopentolate 1% eyedrops thrice at intervals of 10 minutes to achieve cycloplegia. After an hour of instilling eye drops, cycloplegic retinoscopy, and autorefractometry were performed. Three values of each technique were recorded, and the average was calculated. After three days, binocular and monocular subjective refraction was performed until the best-corrected visual acuity (BCVA) was achieved. Results showed that 40.8% (49 eyes) were hypermetric, and 50% (60 eyes) were myopic based on subjective refraction. Comparison of spherical error by subjective refraction and retinoscopy showed that myopic eyes had a mean of -1.36 ± .98 and -1.08± .82 on subjective correction and retinoscopy, respectively (P=.07), and hypermetropic eyes had a mean of 2.5± .22 and 2.45± .22 on subjective correction and retinoscopy, respectively (P=0.07). Comparison of spherical error by subjective refraction and autorefractometer showed myopic eyes had a mean value of -1.51 ± 1.3 on autorefraction (P=.0001) while hypermetropic eyes had a mean of 2.39± .37 on autorefraction (P=0.0001). Mean cylindrical error values by retinoscopy were -.0729± .304, and by the subjective method, were -.167± .384 (P =0.0007). Mean cylindrical error values by autorefraction were .207± .487 compared to -.167± .384 by the subjective method (P =0.0088). In conclusion, conventional retinoscopy is the most accurate and reliable method for estimating the refractive status. However, autorefraction also has acceptable accuracy and can be used for cylindrical correction.

show abstract

Section: Figure 1: Distribution Of Gender In the Study Populationsupporting

confidence: 41%

Comparison Between Autorefraction and Retinoscopy for Subjective Correction in Children

YAR,

ZAHID,

NAWAB

et al. 2023

Biol Clin Sci Res J

View full text Add to dashboard Cite

show abstract

“…As seen previously in the literature, most ML applications in pediatric ophthalmology have focused on ROP ( 16 ). Nisha et al observed that machine learning algorithms can measure the differences in decision-making between ROP experts and trainees, thus increasing the accuracy of diagnosis and helping to control the training process ( 21 ). In another study, retinal vasculature in a model of oxygen-induced retinopathy was automatically assessed using an MLA ( 22 ).…”

Section: Discussionmentioning

confidence: 99%

Retinopathy of Prematurity in Late Preterm Twins with a Birth Weight Discordance: Can it be Predicted by Artificial Intelligence?

Kiran Yenice

2023

Beyoglu Eye J

View full text Add to dashboard Cite

Objectives: The objective is to predict the development of retinopathy of prematurity (ROP) in discordant twins using a machine learning approach. Methods: The records of 640 twin pairs born at 32–35 weeks gestational age (GA) with birth weight (BW) discordance were evaluated retrospectively. The infants’ gender, GA, postmenstruel age at examination, BW, discordance rate, ROP Stages and Zones, and treatment options were recorded. The variables were used to develop a model to predict the development of ROP. Machine learning models were used for algorithm training and 10-fold cross-validation (CV) was applied for validation. The main measures were reported as sensitivity, specificity, receiver operating characteristic curve, and the area under the curve. Results: A total of 640 twin pairs underwent ophthalmic examination, of which 55 (4.3%) were ROP. The infants’ GA was 33.56±1.01 weeks (32–35 weeks) and BW was 1996±335 g (1000–3400 g). The mean discordance rate of the infants was 11.8±9.7% (0.0–53.9%). Using operating points, the Decision Tree algorithm detected ROP prediction with 71% sensitivity and 80% specificity in CV, while the Multi-Layer Perceptron algorithm detected 70% sensitivity and specificity. In addition, the X-Tree and Random Forest algorithms detected ROP prediction with 84% and 80% specificity, respectively. Conclusion: The results of this study support that BW discordance may be effective in the development of ROP in preterm twins and that artificial intelligence models can predict the development of ROP in accordance with clinical findings.

show abstract

“…Preterm birth, low birth weight, and inhalation of high concentrations of oxygen are high-risk factors for ROP ( Ramanathan et al, 2022 ). The clinical manifestations of children with ROP vary according to the course of the disease, which is divided into three areas according to the location of the lesion: area Ⅰ, a circular area with a radius of 2 times the distance from the optic disc to the fovea of the macula ( Bai et al, 2022 ); area Ⅱ, a circular area centered on the optic disc to the sawtooth margin of the nasal side ( Eilts et al, 2023 ); and area Ⅲ, the area excluding areas I and II ( Nisha et al, 2023 ). According to the severity of the lesion, it was divided into five stages: stage 1, dividing line stage; stage 2, critical stage; stage 3, increment stage; stage 4, subpanretinal detachment stage; and stage 5, panretinal detachment stage ( Gensure et al, 2020 ).…”

Section: Application Of Artificial Intelligence In Retinal Vascular D...mentioning

confidence: 99%

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

Liu

et al. 2023

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

As the only blood vessels that can directly be seen in the whole body, pathological changes in retinal vessels are related to the metabolic state of the whole body and many systems, which seriously affect the vision and quality of life of patients. Timely diagnosis and treatment are key to improving vision prognosis. In recent years, with the rapid development of artificial intelligence, the application of artificial intelligence in ophthalmology has become increasingly extensive and in-depth, especially in the field of retinal vascular diseases. Research study results based on artificial intelligence and fundus images are remarkable and provides a great possibility for early diagnosis and treatment. This paper reviews the recent research progress on artificial intelligence in retinal vascular diseases (including diabetic retinopathy, hypertensive retinopathy, retinal vein occlusion, retinopathy of prematurity, and age-related macular degeneration). The limitations and challenges of the research process are also discussed.

show abstract

A Novel Method to Improve Inter-Clinician Variation in the Diagnosis of Retinopathy of Prematurity Using Machine Learning

Cited by 7 publications

References 31 publications

Comparison Between Autorefraction and Retinoscopy for Subjective Correction in Children

Comparison Between Autorefraction and Retinoscopy for Subjective Correction in Children

Retinopathy of Prematurity in Late Preterm Twins with a Birth Weight Discordance: Can it be Predicted by Artificial Intelligence?

Research progress on diagnosing retinal vascular diseases based on artificial intelligence and fundus images

Contact Info

Product

Resources

About