Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders
Objective. To evaluate diabetic retinopathy (DR) screening via deep learning (DL) and trained human graders (HG) in a longitudinal cohort, as case spectrum shifts based on treatment referral and new-onset DR. Methods. We randomly selected patients with diabetes screened twice, two years apart within...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2020-01-01
|
| Series: | Journal of Diabetes Research |
| Online Access: | http://dx.doi.org/10.1155/2020/8839376 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832554109705650176 |
|---|---|
| author | Jirawut Limwattanayingyong Variya Nganthavee Kasem Seresirikachorn Tassapol Singalavanija Ngamphol Soonthornworasiri Varis Ruamviboonsuk Chetan Rao Rajiv Raman Andrzej Grzybowski Mike Schaekermann Lily H. Peng Dale R. Webster Christopher Semturs Jonathan Krause Rory Sayres Fred Hersch Richa Tiwari Yun Liu Paisan Ruamviboonsuk |
| author_facet | Jirawut Limwattanayingyong Variya Nganthavee Kasem Seresirikachorn Tassapol Singalavanija Ngamphol Soonthornworasiri Varis Ruamviboonsuk Chetan Rao Rajiv Raman Andrzej Grzybowski Mike Schaekermann Lily H. Peng Dale R. Webster Christopher Semturs Jonathan Krause Rory Sayres Fred Hersch Richa Tiwari Yun Liu Paisan Ruamviboonsuk |
| author_sort | Jirawut Limwattanayingyong |
| collection | DOAJ |
| description | Objective. To evaluate diabetic retinopathy (DR) screening via deep learning (DL) and trained human graders (HG) in a longitudinal cohort, as case spectrum shifts based on treatment referral and new-onset DR. Methods. We randomly selected patients with diabetes screened twice, two years apart within a nationwide screening program. The reference standard was established via adjudication by retina specialists. Each patient’s color fundus photographs were graded, and a patient was considered as having sight-threatening DR (STDR) if the worse eye had severe nonproliferative DR, proliferative DR, or diabetic macular edema. We compared DR screening via two modalities: DL and HG. For each modality, we simulated treatment referral by excluding patients with detected STDR from the second screening using that modality. Results. There were 5,738 patients (12.3% STDR) in the first screening. DL and HG captured different numbers of STDR cases, and after simulated referral and excluding ungradable cases, 4,148 and 4,263 patients remained in the second screening, respectively. The STDR prevalence at the second screening was 5.1% and 6.8% for DL- and HG-based screening, respectively. Along with the prevalence decrease, the sensitivity for both modalities decreased from the first to the second screening (DL: from 95% to 90%, p=0.008; HG: from 74% to 57%, p<0.001). At both the first and second screenings, the rate of false negatives for the DL was a fifth that of HG (0.5-0.6% vs. 2.9-3.2%). Conclusion. On 2-year longitudinal follow-up of a DR screening cohort, STDR prevalence decreased for both DL- and HG-based screening. Follow-up screenings in longitudinal DR screening can be more difficult and induce lower sensitivity for both DL and HG, though the false negative rate was substantially lower for DL. Our data may be useful for health-economics analyses of longitudinal screening settings. |
| format | Article |
| id | doaj-art-b29a136307114397b10f73edbaa2e694 |
| institution | Kabale University |
| issn | 2314-6745 2314-6753 |
| language | English |
| publishDate | 2020-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Diabetes Research |
| spelling | doaj-art-b29a136307114397b10f73edbaa2e6942025-02-03T05:52:25ZengWileyJournal of Diabetes Research2314-67452314-67532020-01-01202010.1155/2020/88393768839376Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human GradersJirawut Limwattanayingyong0Variya Nganthavee1Kasem Seresirikachorn2Tassapol Singalavanija3Ngamphol Soonthornworasiri4Varis Ruamviboonsuk5Chetan Rao6Rajiv Raman7Andrzej Grzybowski8Mike Schaekermann9Lily H. Peng10Dale R. Webster11Christopher Semturs12Jonathan Krause13Rory Sayres14Fred Hersch15Richa Tiwari16Yun Liu17Paisan Ruamviboonsuk18Department of Ophthalmology, College of Medicine, Rangsit University, Rajavithi Hospital, Bangkok, ThailandDepartment of Ophthalmology, College of Medicine, Rangsit University, Rajavithi Hospital, Bangkok, ThailandDepartment of Ophthalmology, College of Medicine, Rangsit University, Rajavithi Hospital, Bangkok, ThailandDepartment of Ophthalmology, Chulabhorn Hospital, HRH Princess Chulabhorn College of Medical Science, Chulabhorn Royal Academy, Bangkok, ThailandDepartment of Tropical Hygiene, Faculty of Tropical Medicine, Mahidol University, Bangkok, ThailandDepartment of Biochemistry, Faculty of Medicine, Chulalongkorn University, Bangkok, ThailandShri Bhagwan Mahavir Vitreoretinal Services, Sankara Nethralaya, Chennai, Tamil Nadu, IndiaShri Bhagwan Mahavir Vitreoretinal Services, Sankara Nethralaya, Chennai, Tamil Nadu, IndiaDepartment of Ophthalmology, University of Warmia and Mazury, Olsztyn, PolandGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAGoogle Health, Palo Alto, CA, USAWork done at Google via Optimum Solutions Pte Ltd, SingaporeGoogle Health, Palo Alto, CA, USADepartment of Ophthalmology, College of Medicine, Rangsit University, Rajavithi Hospital, Bangkok, ThailandObjective. To evaluate diabetic retinopathy (DR) screening via deep learning (DL) and trained human graders (HG) in a longitudinal cohort, as case spectrum shifts based on treatment referral and new-onset DR. Methods. We randomly selected patients with diabetes screened twice, two years apart within a nationwide screening program. The reference standard was established via adjudication by retina specialists. Each patient’s color fundus photographs were graded, and a patient was considered as having sight-threatening DR (STDR) if the worse eye had severe nonproliferative DR, proliferative DR, or diabetic macular edema. We compared DR screening via two modalities: DL and HG. For each modality, we simulated treatment referral by excluding patients with detected STDR from the second screening using that modality. Results. There were 5,738 patients (12.3% STDR) in the first screening. DL and HG captured different numbers of STDR cases, and after simulated referral and excluding ungradable cases, 4,148 and 4,263 patients remained in the second screening, respectively. The STDR prevalence at the second screening was 5.1% and 6.8% for DL- and HG-based screening, respectively. Along with the prevalence decrease, the sensitivity for both modalities decreased from the first to the second screening (DL: from 95% to 90%, p=0.008; HG: from 74% to 57%, p<0.001). At both the first and second screenings, the rate of false negatives for the DL was a fifth that of HG (0.5-0.6% vs. 2.9-3.2%). Conclusion. On 2-year longitudinal follow-up of a DR screening cohort, STDR prevalence decreased for both DL- and HG-based screening. Follow-up screenings in longitudinal DR screening can be more difficult and induce lower sensitivity for both DL and HG, though the false negative rate was substantially lower for DL. Our data may be useful for health-economics analyses of longitudinal screening settings.http://dx.doi.org/10.1155/2020/8839376 |
| spellingShingle | Jirawut Limwattanayingyong Variya Nganthavee Kasem Seresirikachorn Tassapol Singalavanija Ngamphol Soonthornworasiri Varis Ruamviboonsuk Chetan Rao Rajiv Raman Andrzej Grzybowski Mike Schaekermann Lily H. Peng Dale R. Webster Christopher Semturs Jonathan Krause Rory Sayres Fred Hersch Richa Tiwari Yun Liu Paisan Ruamviboonsuk Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders Journal of Diabetes Research |
| title | Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders |
| title_full | Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders |
| title_fullStr | Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders |
| title_full_unstemmed | Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders |
| title_short | Longitudinal Screening for Diabetic Retinopathy in a Nationwide Screening Program: Comparing Deep Learning and Human Graders |
| title_sort | longitudinal screening for diabetic retinopathy in a nationwide screening program comparing deep learning and human graders |
| url | http://dx.doi.org/10.1155/2020/8839376 |
| work_keys_str_mv | AT jirawutlimwattanayingyong longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT variyanganthavee longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT kasemseresirikachorn longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT tassapolsingalavanija longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT ngampholsoonthornworasiri longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT varisruamviboonsuk longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT chetanrao longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT rajivraman longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT andrzejgrzybowski longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT mikeschaekermann longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT lilyhpeng longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT dalerwebster longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT christophersemturs longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT jonathankrause longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT rorysayres longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT fredhersch longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT richatiwari longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT yunliu longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders AT paisanruamviboonsuk longitudinalscreeningfordiabeticretinopathyinanationwidescreeningprogramcomparingdeeplearningandhumangraders |