Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population
PurposeThe primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP).ParticipantsImages were collected from infants enrolled in the KIDROP tele-ROP screening program.MethodsWe developed a deep learning (DL) a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Pediatrics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fped.2023.1197237/full |
| _version_ | 1797678044782002176 |
|---|---|
| author | Divya Parthasarathy Rao Florian M. Savoy Joshua Zhi En Tan Brian Pei-En Fung Chiran Mandula Bopitiya Anand Sivaraman Anand Vinekar |
| author_facet | Divya Parthasarathy Rao Florian M. Savoy Joshua Zhi En Tan Brian Pei-En Fung Chiran Mandula Bopitiya Anand Sivaraman Anand Vinekar |
| author_sort | Divya Parthasarathy Rao |
| collection | DOAJ |
| description | PurposeThe primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP).ParticipantsImages were collected from infants enrolled in the KIDROP tele-ROP screening program.MethodsWe developed a deep learning (DL) algorithm with 227,326 wide-field images from multiple camera systems obtained from the KIDROP tele-ROP screening program in India over an 11-year period. 37,477 temporal retina images were utilized with the dataset split into train (n = 25,982, 69.33%), validation (n = 4,006, 10.69%), and an independent test set (n = 7,489, 19.98%). The algorithm consists of a binary classifier that distinguishes between the presence of ROP (Stages 1–3) and the absence of ROP. The image labels were retrieved from the daily registers of the tele-ROP program. They consist of per-eye diagnoses provided by trained ROP graders based on all images captured during the screening session. Infants requiring treatment and a proportion of those not requiring urgent referral had an additional confirmatory diagnosis from an ROP specialist.ResultsOf the 7,489 temporal images analyzed in the test set, 2,249 (30.0%) images showed the presence of ROP. The sensitivity and specificity to detect ROP was 91.46% (95% CI: 90.23%–92.59%) and 91.22% (95% CI: 90.42%–91.97%), respectively, while the positive predictive value (PPV) was 81.72% (95% CI: 80.37%–83.00%), negative predictive value (NPV) was 96.14% (95% CI: 95.60%–96.61%) and the AUROC was 0.970.ConclusionThe novel ROP screening algorithm demonstrated high sensitivity and specificity in detecting the presence of ROP. A prospective clinical validation in a real-world tele-ROP platform is under consideration. It has the potential to lower the number of screening sessions required to be conducted by a specialist for a high-risk preterm infant thus significantly improving workflow efficiency. |
| first_indexed | 2024-03-11T22:53:45Z |
| format | Article |
| id | doaj.art-b162b8bebd7f45178681efb50d5dcd67 |
| institution | Directory Open Access Journal |
| issn | 2296-2360 |
| language | English |
| last_indexed | 2024-03-11T22:53:45Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pediatrics |
| spelling | doaj.art-b162b8bebd7f45178681efb50d5dcd672023-09-21T20:17:20ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602023-09-011110.3389/fped.2023.11972371197237Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian populationDivya Parthasarathy Rao0Florian M. Savoy1Joshua Zhi En Tan2Brian Pei-En Fung3Chiran Mandula Bopitiya4Anand Sivaraman5Anand Vinekar6Artificial Intelligence Research and Development, Remidio Innovative Solutions Inc., Glen Allen, VA, United StatesArtificial Intelligence Research and Development, Medios Technologies Pvt. Ltd., Singapore, SingaporeArtificial Intelligence Research and Development, Medios Technologies Pvt. Ltd., Singapore, SingaporeArtificial Intelligence Research and Development, Medios Technologies Pvt. Ltd., Singapore, SingaporeArtificial Intelligence Research and Development, Medios Technologies Pvt. Ltd., Singapore, SingaporeArtificial Intelligence Research and Development, Remidio Innovative Solutions Pvt. Ltd., Bangalore, IndiaDepartment of Pediatric Retina, Narayana Nethralaya Eye Institute, Bangalore, IndiaPurposeThe primary objective of this study was to develop and validate an AI algorithm as a screening tool for the detection of retinopathy of prematurity (ROP).ParticipantsImages were collected from infants enrolled in the KIDROP tele-ROP screening program.MethodsWe developed a deep learning (DL) algorithm with 227,326 wide-field images from multiple camera systems obtained from the KIDROP tele-ROP screening program in India over an 11-year period. 37,477 temporal retina images were utilized with the dataset split into train (n = 25,982, 69.33%), validation (n = 4,006, 10.69%), and an independent test set (n = 7,489, 19.98%). The algorithm consists of a binary classifier that distinguishes between the presence of ROP (Stages 1–3) and the absence of ROP. The image labels were retrieved from the daily registers of the tele-ROP program. They consist of per-eye diagnoses provided by trained ROP graders based on all images captured during the screening session. Infants requiring treatment and a proportion of those not requiring urgent referral had an additional confirmatory diagnosis from an ROP specialist.ResultsOf the 7,489 temporal images analyzed in the test set, 2,249 (30.0%) images showed the presence of ROP. The sensitivity and specificity to detect ROP was 91.46% (95% CI: 90.23%–92.59%) and 91.22% (95% CI: 90.42%–91.97%), respectively, while the positive predictive value (PPV) was 81.72% (95% CI: 80.37%–83.00%), negative predictive value (NPV) was 96.14% (95% CI: 95.60%–96.61%) and the AUROC was 0.970.ConclusionThe novel ROP screening algorithm demonstrated high sensitivity and specificity in detecting the presence of ROP. A prospective clinical validation in a real-world tele-ROP platform is under consideration. It has the potential to lower the number of screening sessions required to be conducted by a specialist for a high-risk preterm infant thus significantly improving workflow efficiency.https://www.frontiersin.org/articles/10.3389/fped.2023.1197237/fullretinopathy of prematurityartificial intelligencescreeningdeep learningaccessibilityROP |
| spellingShingle | Divya Parthasarathy Rao Florian M. Savoy Joshua Zhi En Tan Brian Pei-En Fung Chiran Mandula Bopitiya Anand Sivaraman Anand Vinekar Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population Frontiers in Pediatrics retinopathy of prematurity artificial intelligence screening deep learning accessibility ROP |
| title | Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population |
| title_full | Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population |
| title_fullStr | Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population |
| title_full_unstemmed | Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population |
| title_short | Development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a South Indian population |
| title_sort | development and validation of an artificial intelligence based screening tool for detection of retinopathy of prematurity in a south indian population |
| topic | retinopathy of prematurity artificial intelligence screening deep learning accessibility ROP |
| url | https://www.frontiersin.org/articles/10.3389/fped.2023.1197237/full |
| work_keys_str_mv | AT divyaparthasarathyrao developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT florianmsavoy developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT joshuazhientan developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT brianpeienfung developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT chiranmandulabopitiya developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT anandsivaraman developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation AT anandvinekar developmentandvalidationofanartificialintelligencebasedscreeningtoolfordetectionofretinopathyofprematurityinasouthindianpopulation |