Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms
The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability...
Gespeichert in:
| Veröffentlicht in: | The Lancet. Digital health Jg. 2; H. 10; S. e526 - e536 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
England
Elsevier Ltd
01.10.2020
Elsevier |
| Schlagworte: | |
| ISSN: | 2589-7500, 2589-7500 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored.
With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development.
In addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51–0·53) in the internal test set, and of 0·33 (0·30–0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40–0·43), of bodyweight was 0·36 (0·34–0·37), and of creatinine was 0·38 (0·37–0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R2≤0·14 across all external test sets).
Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms.
Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. |
|---|---|
| AbstractList | The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored.
With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development.
In addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51–0·53) in the internal test set, and of 0·33 (0·30–0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40–0·43), of bodyweight was 0·36 (0·34–0·37), and of creatinine was 0·38 (0·37–0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R2≤0·14 across all external test sets).
Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms.
Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. SummaryBackgroundThe application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored. MethodsWith use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development. FindingsIn addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51–0·53) in the internal test set, and of 0·33 (0·30–0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40–0·43), of bodyweight was 0·36 (0·34–0·37), and of creatinine was 0·38 (0·37–0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning ( R2≤0·14 across all external test sets). InterpretationOur work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms. FundingAgency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. Background: The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored. Methods: With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development. Findings: In addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51–0·53) in the internal test set, and of 0·33 (0·30–0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40–0·43), of bodyweight was 0·36 (0·34–0·37), and of creatinine was 0·38 (0·37–0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R2≤0·14 across all external test sets). Interpretation: Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms. Funding: Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored.BACKGROUNDThe application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored.With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development.METHODSWith use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development.In addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51-0·53) in the internal test set, and of 0·33 (0·30-0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40-0·43), of bodyweight was 0·36 (0·34-0·37), and of creatinine was 0·38 (0·37-0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R2≤0·14 across all external test sets).FINDINGSIn addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R2 of 0·52 (95% CI 0·51-0·53) in the internal test set, and of 0·33 (0·30-0·35) in one external test set with muscle mass measurement available. The R2 value for the prediction of height was 0·42 (0·40-0·43), of bodyweight was 0·36 (0·34-0·37), and of creatinine was 0·38 (0·37-0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R2 values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R2≤0·14 across all external test sets).Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms.INTERPRETATIONOur work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms.Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology.FUNDINGAgency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters. However, the broader applicability of retinal photograph-based deep learning for predicting other systemic biomarkers and the generalisability of this approach to various populations remains unexplored. With use of 236 257 retinal photographs from seven diverse Asian and European cohorts (two health screening centres in South Korea, the Beijing Eye Study, three cohorts in the Singapore Epidemiology of Eye Diseases study, and the UK Biobank), we evaluated the capacities of 47 deep-learning algorithms to predict 47 systemic biomarkers as outcome variables, including demographic factors (age and sex); body composition measurements; blood pressure; haematological parameters; lipid profiles; biochemical measures; biomarkers related to liver function, thyroid function, kidney function, and inflammation; and diabetes. The standard neural network architecture of VGG16 was adopted for model development. In addition to previously reported systemic biomarkers, we showed quantification of body composition indices (muscle mass, height, and bodyweight) and creatinine from retinal photographs. Body muscle mass could be predicted with an R of 0·52 (95% CI 0·51-0·53) in the internal test set, and of 0·33 (0·30-0·35) in one external test set with muscle mass measurement available. The R value for the prediction of height was 0·42 (0·40-0·43), of bodyweight was 0·36 (0·34-0·37), and of creatinine was 0·38 (0·37-0·40) in the internal test set. However, the performances were poorer in external test sets (with the lowest performance in the European cohort), with R values ranging between 0·08 and 0·28 for height, 0·04 and 0·19 for bodyweight, and 0·01 and 0·26 for creatinine. Of the 47 systemic biomarkers, 37 could not be predicted well from retinal photographs via deep learning (R ≤0·14 across all external test sets). Our work provides new insights into the potential use of retinal photographs to predict systemic biomarkers, including body composition indices and serum creatinine, using deep learning in populations with a similar ethnic background. Further evaluations are warranted to validate these findings and evaluate the clinical utility of these algorithms. Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. |
| Author | Lee, Chan Joo Wang, Ya Xing Jonas, Jost B Cheng, Ching-Yu Lee, Byoung Kwon Park, Sungha Kim, Sung Soo Kim, Youngnam Rim, Tyler Hyungtaek Kim, Hyeon Chang Ting, Daniel S W Yu, Marco Deshmukh, Mihir Tham, Yih-Chung Lee, Geunyoung Baik, Su Jung Kim, Young Ah Sabayanagam, Charumathi Wong, Tien Yin |
| Author_xml | – sequence: 1 givenname: Tyler Hyungtaek surname: Rim fullname: Rim, Tyler Hyungtaek organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 2 givenname: Geunyoung surname: Lee fullname: Lee, Geunyoung organization: Medi Whale, Seoul, South Korea – sequence: 3 givenname: Youngnam surname: Kim fullname: Kim, Youngnam organization: Medi Whale, Seoul, South Korea – sequence: 4 givenname: Yih-Chung surname: Tham fullname: Tham, Yih-Chung organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 5 givenname: Chan Joo surname: Lee fullname: Lee, Chan Joo organization: Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Seoul, South Korea – sequence: 6 givenname: Su Jung surname: Baik fullname: Baik, Su Jung organization: Healthcare Research Team, Health Promotion Center, Severance Gangnam Hospital, Yonsei University College of Medicine, Seoul, South Korea – sequence: 7 givenname: Young Ah surname: Kim fullname: Kim, Young Ah organization: Division of Medical Information and Technology, Yonsei University College of Medicine, Seoul, South Korea – sequence: 8 givenname: Marco surname: Yu fullname: Yu, Marco organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 9 givenname: Mihir surname: Deshmukh fullname: Deshmukh, Mihir organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 10 givenname: Byoung Kwon surname: Lee fullname: Lee, Byoung Kwon organization: Division of Cardiology, Severance Gangnam Hospital, Yonsei University College of Medicine, Seoul, South Korea – sequence: 11 givenname: Sungha surname: Park fullname: Park, Sungha organization: Division of Cardiology, Severance Cardiovascular Hospital, Yonsei University College of Medicine, Seoul, South Korea – sequence: 12 givenname: Hyeon Chang surname: Kim fullname: Kim, Hyeon Chang organization: Department of Preventive Medicine, Yonsei University College of Medicine, Seoul, South Korea – sequence: 13 givenname: Charumathi surname: Sabayanagam fullname: Sabayanagam, Charumathi organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 14 givenname: Daniel S W surname: Ting fullname: Ting, Daniel S W organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 15 givenname: Ya Xing surname: Wang fullname: Wang, Ya Xing organization: Beijing Institute of Ophthalmology, Beijing Tongren Eye Center, Beijing Tongren Hospital, Capital Medical University, Beijing, China – sequence: 16 givenname: Jost B surname: Jonas fullname: Jonas, Jost B organization: Department of Ophthalmology, Medical Faculty Mannheim, Heidelberg University, Mannheim, Germany – sequence: 17 givenname: Sung Soo surname: Kim fullname: Kim, Sung Soo email: semekim@yuhs.ac organization: Department of Ophthalmology, Institute of Vision Research, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea – sequence: 18 givenname: Tien Yin surname: Wong fullname: Wong, Tien Yin organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore – sequence: 19 givenname: Ching-Yu surname: Cheng fullname: Cheng, Ching-Yu email: chingyu.cheng@duke-nus.edu.sg organization: Singapore Eye Research Institute, Singapore National Eye Centre, Singapore |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33328047$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkl1rFDEYhQep2A_7E5S5rBej-ZjszCgqUvwoFBTU6_BO8s5utplkTLIL---b3W0XKUi9Sng550lyTk6LI-cdFsULSl5TQmdvfjLRdlUjCLlg5BUnjM6q9klxchgf_bU_Ls5jXBJCGKO8aZpnxTHnnLWkbk6K8COgNioZ70o_lHETE45Glb3xI4QbDLEcgh_LgMk4sOW08MnPA0yL-LbUuEbrpxFdKsHpcg3WaLhnacSpsgjBGTcvwc59MGkxxufF0wFsxPO79az4_eXzr8tv1fX3r1eXn64rJdomVZSTvheshk73VCvQjA4tAO1510CDMAjEoRYdFQ3lQDV02HOFooMsJ1rxs-Jqz9UelnIKJj9oIz0YuRv4MJcQklEWZS-GNp9QM-zbWs9EP9CeccY1tDNKWJdZF3vWFPyfFcYkRxMVWgsO_SpKVjek7bqZoFn68k666kfUh4PvM88CsReo4GMMOBwklMhtvXJXr9x2JxmRu3plm33vHviUSbu0UwBjH3V_3LsxR742GGRUBp3K7QdUKWdiHiV8eEBQ1jijwN7gBuPSr0L-IVFSGZkke8iWwciOsAW8_zfgPy5wCzWy6O0 |
| CitedBy_id | crossref_primary_10_1038_s41433_024_03085_2 crossref_primary_10_1097_APO_0000000000000515 crossref_primary_10_4103_tjo_TJO_D_23_00018 crossref_primary_10_1001_jamaophthalmol_2023_2921 crossref_primary_10_1007_s13042_021_01419_0 crossref_primary_10_1038_s41433_023_02724_4 crossref_primary_10_1038_s41598_024_71517_w crossref_primary_10_1186_s12933_024_02564_w crossref_primary_10_1007_s13167_022_00292_3 crossref_primary_10_1016_j_media_2025_103628 crossref_primary_10_1007_s00371_025_03977_8 crossref_primary_10_3390_ijerph182010798 crossref_primary_10_1038_s41746_025_01801_0 crossref_primary_10_3389_fmed_2025_1580583 crossref_primary_10_1097_ICU_0000000000000877 crossref_primary_10_1016_j_compbiomed_2022_106277 crossref_primary_10_1186_s12916_022_02684_8 crossref_primary_10_1007_s00592_022_01941_9 crossref_primary_10_1177_11206721231199848 crossref_primary_10_1186_s40537_023_00777_6 crossref_primary_10_21518_akh2025_009 crossref_primary_10_1161_STROKEAHA_123_044026 crossref_primary_10_3390_app14198823 crossref_primary_10_1097_WNO_0000000000001800 crossref_primary_10_1136_bjophthalmol_2021_319807 crossref_primary_10_3390_diagnostics13010068 crossref_primary_10_1007_s40123_024_00942_x crossref_primary_10_1016_j_ejca_2025_115752 crossref_primary_10_1016_j_heliyon_2024_e36592 crossref_primary_10_1093_pnasnexus_pgad290 crossref_primary_10_1038_s41467_024_52003_3 crossref_primary_10_1097_ICU_0000000000001174 crossref_primary_10_1186_s12938_023_01110_1 crossref_primary_10_1016_j_jbi_2023_104365 crossref_primary_10_1007_s40123_024_00981_4 crossref_primary_10_3390_jcdd12060230 crossref_primary_10_1016_j_ccr_2022_214486 crossref_primary_10_1097_ICU_0000000000000886 crossref_primary_10_1016_j_preteyeres_2025_101350 crossref_primary_10_3390_bios15030139 crossref_primary_10_1016_j_jcjo_2025_07_008 crossref_primary_10_1038_s41746_023_00860_5 crossref_primary_10_1186_s12967_023_04543_3 crossref_primary_10_1038_s41598_023_32164_9 crossref_primary_10_3390_cells11193037 crossref_primary_10_1007_s13721_023_00438_x crossref_primary_10_1016_j_cvdhj_2023_12_004 crossref_primary_10_4103_sjopt_sjopt_153_23 crossref_primary_10_1093_eurheartj_ehab874 crossref_primary_10_1002_VIW_20220070 crossref_primary_10_1136_bjo_2024_325846 crossref_primary_10_1002_widm_1506 crossref_primary_10_1016_j_fhj_2024_100183 crossref_primary_10_1038_s41467_025_62273_0 crossref_primary_10_1016_j_heliyon_2024_e33813 crossref_primary_10_3390_jcm12010152 crossref_primary_10_7759_cureus_48977 crossref_primary_10_1038_s41572_022_00342_0 crossref_primary_10_3390_healthcare11121739 crossref_primary_10_2196_25165 crossref_primary_10_3390_biomedicines12092150 crossref_primary_10_1038_s41433_022_02298_7 crossref_primary_10_1038_s41551_021_00745_6 crossref_primary_10_1038_s41551_021_00747_4 crossref_primary_10_1007_s00371_024_03619_5 crossref_primary_10_3390_diagnostics13050900 crossref_primary_10_1007_s00246_024_03561_2 crossref_primary_10_1016_j_engappai_2025_111734 crossref_primary_10_1016_j_ebiom_2023_104467 crossref_primary_10_3389_fmed_2023_1145522 crossref_primary_10_1016_j_jare_2024_11_018 crossref_primary_10_1038_s41433_024_03135_9 crossref_primary_10_3389_fdgth_2022_889445 crossref_primary_10_1093_jamia_ocad199 crossref_primary_10_1109_ACCESS_2025_3562433 crossref_primary_10_3390_diagnostics15050643 crossref_primary_10_3389_fmed_2025_1614321 crossref_primary_10_1016_j_numecd_2022_01_010 crossref_primary_10_1038_s41551_025_01413_9 crossref_primary_10_1038_s41551_022_00867_5 crossref_primary_10_1097_ICU_0000000000000784 crossref_primary_10_1097_CORR_0000000000002986 crossref_primary_10_1371_journal_pdig_0000640 crossref_primary_10_1016_j_jacadv_2024_101410 crossref_primary_10_1371_journal_pone_0295073 crossref_primary_10_1038_s41598_025_11017_7 crossref_primary_10_1097_APO_0000000000000400 |
| Cites_doi | 10.1038/s41598-019-43670-0 10.1038/s41551-019-0487-z 10.1046/j.1467-789X.2002.00063.x 10.1007/s12603-018-1139-9 10.1016/j.ajo.2020.03.027 10.1097/WNO.0000000000000888 10.1136/bjophthalmol-2018-313173 10.1016/S2589-7500(19)30132-3 10.1016/S0039-6257(01)00234-X 10.1016/S0140-6736(01)06253-5 10.1016/S2589-7500(20)30063-7 10.1159/000502387 10.1093/ije/dym276 10.1016/j.ajo.2019.05.006 10.1080/09286580600878844 10.1167/tvst.9.2.6 10.1038/s41551-018-0195-0 10.1111/j.1755-3768.2008.01385.x 10.3109/09286580903144738 10.1167/tvst.9.2.4 10.1038/ki.2013.153 10.1186/s12916-019-1426-2 10.1016/j.oret.2020.03.007 10.1016/j.ophtha.2010.08.045 |
| ContentType | Journal Article |
| Copyright | 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved. |
| Copyright_xml | – notice: 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license – notice: The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license – notice: Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved. |
| DBID | 6I. AAFTH AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 DOA |
| DOI | 10.1016/S2589-7500(20)30216-8 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Public Health |
| EISSN | 2589-7500 |
| EndPage | e536 |
| ExternalDocumentID | oai_doaj_org_article_b5f8cad42eb84d65bf1b2323da861029 33328047 10_1016_S2589_7500_20_30216_8 S2589750020302168 1_s2_0_S2589750020302168 |
| Genre | Validation Study Research Support, Non-U.S. Gov't Journal Article |
| GeographicLocations | Beijing United Kingdom Singapore Asia Europe Republic of Korea |
| GeographicLocations_xml | – name: United Kingdom – name: Singapore – name: Beijing – name: Republic of Korea – name: Asia – name: Europe |
| GrantInformation | Agency for Science, Technology, and Research and National Medical Research Council, Singapore; Korea Institute for Advancement of Technology. |
| GrantInformation_xml | – fundername: Medical Research Council grantid: MC_PC_17228 – fundername: Medical Research Council grantid: MC_QA137853 |
| GroupedDBID | .1- .FO 0R~ 53G AAEDW AALRI AAMRU AAXUO ACLIJ ACVFH ADCNI AEUPX AEXQZ AFPUW AFRHN AIGII AITUG AJUYK AKBMS AKYEP ALMA_UNASSIGNED_HOLDINGS APXCP EBS EJD FDB GROUPED_DOAJ M41 M~E OK1 ROL W2D Z5R NCXOZ 0SF 6I. AAFTH AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 |
| ID | FETCH-LOGICAL-c587t-130bb524a9db1dcad21f8aa1b397a7eaf5eef45915713a1da9eb3ce59ab1d0dc3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 108 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000581145100010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2589-7500 |
| IngestDate | Fri Oct 03 12:51:09 EDT 2025 Sun Nov 09 09:02:02 EST 2025 Mon Jul 21 05:35:01 EDT 2025 Thu Nov 13 04:36:57 EST 2025 Tue Nov 18 20:29:09 EST 2025 Wed May 17 00:08:41 EDT 2023 Sun Feb 23 10:19:02 EST 2025 Tue Aug 26 20:17:41 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 10 |
| Language | English |
| License | This is an open access article under the CC BY license. Copyright © 2020 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY 4.0 license. Published by Elsevier Ltd.. All rights reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c587t-130bb524a9db1dcad21f8aa1b397a7eaf5eef45915713a1da9eb3ce59ab1d0dc3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3 |
| OpenAccessLink | https://doaj.org/article/b5f8cad42eb84d65bf1b2323da861029 |
| PMID | 33328047 |
| PQID | 2470899651 |
| PQPubID | 23479 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b5f8cad42eb84d65bf1b2323da861029 proquest_miscellaneous_2470899651 pubmed_primary_33328047 crossref_primary_10_1016_S2589_7500_20_30216_8 crossref_citationtrail_10_1016_S2589_7500_20_30216_8 elsevier_sciencedirect_doi_10_1016_S2589_7500_20_30216_8 elsevier_clinicalkeyesjournals_1_s2_0_S2589750020302168 elsevier_clinicalkey_doi_10_1016_S2589_7500_20_30216_8 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-10-01 |
| PublicationDateYYYYMMDD | 2020-10-01 |
| PublicationDate_xml | – month: 10 year: 2020 text: 2020-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | England |
| PublicationPlace_xml | – name: England |
| PublicationTitle | The Lancet. Digital health |
| PublicationTitleAlternate | Lancet Digit Health |
| PublicationYear | 2020 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Vaghefi, Yang, Hill, Humphrey, Walker, Squirrell (bib10) 2019; 9 Foong, Saw, Loo (bib14) 2007; 14 Chang, Ko, Park (bib8) 2020 Atkins (bib21) 2019 Mitani, Huang, Venugopalan (bib6) 2020; 4 Yamashita, Asaoka, Terasaki (bib9) 2020; 9 Dent, Morley, Cruz-Jentoft (bib22) 2018; 22 Zhang, Yuan, An (bib11) 2020; 15 Lewington, Cerdá, Mehta (bib23) 2013; 84 Wagner, Fu, Faes (bib3) 2020; 9 Kim, Noh, Byun (bib7) 2020; 10 Yu, Tham, Rim, Ting, Wong, Cheng (bib20) 2019; 1 James, Chunming, Inoue (bib27) 2002; 3 Cheung, Zheng, Hsu (bib25) 2011; 118 Rim, Soh, Tham (bib17) 2020; 4 Poplin, Varadarajan, Blumer (bib5) 2018; 2 Lavanya, Jeganathan, Zheng (bib15) 2009; 16 Elliott, Peakman (bib16) 2008; 37 Simonyan, Zisserman (bib18) 2015 Wong, Tham, Sabanayagam, Cheng (bib28) 2019; 206 Ting, Pasquale, Peng (bib4) 2019; 103 Sabanayagam, Xu, Ting (bib24) 2020; 2 Kelly, Karthikesalingam, Suleyman, Corrado, King (bib12) 2019; 17 Jonas, Xu, Wang (bib13) 2009; 87 Xu, Ba, Kiros (bib19) 2016 Wong, Sabanayagam (bib29) 2020; 243 Wong, Klein, Couper (bib1) 2001; 358 Rim, Teo, Yang, Cheung, Wong (bib2) 2020; 40 Wong, Klein, Klein, Tielsch, Hubbard, Nieto (bib26) 2001; 46 Yu (10.1016/S2589-7500(20)30216-8_bib20) 2019; 1 Wong (10.1016/S2589-7500(20)30216-8_bib28) 2019; 206 Foong (10.1016/S2589-7500(20)30216-8_bib14) 2007; 14 Poplin (10.1016/S2589-7500(20)30216-8_bib5) 2018; 2 Mitani (10.1016/S2589-7500(20)30216-8_bib6) 2020; 4 Wong (10.1016/S2589-7500(20)30216-8_bib29) 2020; 243 Simonyan (10.1016/S2589-7500(20)30216-8_bib18) 2015 Zhang (10.1016/S2589-7500(20)30216-8_bib11) 2020; 15 Jonas (10.1016/S2589-7500(20)30216-8_bib13) 2009; 87 Kim (10.1016/S2589-7500(20)30216-8_bib7) 2020; 10 Wong (10.1016/S2589-7500(20)30216-8_bib1) 2001; 358 Ting (10.1016/S2589-7500(20)30216-8_bib4) 2019; 103 Kelly (10.1016/S2589-7500(20)30216-8_bib12) 2019; 17 Xu (10.1016/S2589-7500(20)30216-8_bib19) 2016 Rim (10.1016/S2589-7500(20)30216-8_bib17) 2020; 4 Wong (10.1016/S2589-7500(20)30216-8_bib26) 2001; 46 Dent (10.1016/S2589-7500(20)30216-8_bib22) 2018; 22 Vaghefi (10.1016/S2589-7500(20)30216-8_bib10) 2019; 9 Lewington (10.1016/S2589-7500(20)30216-8_bib23) 2013; 84 Cheung (10.1016/S2589-7500(20)30216-8_bib25) 2011; 118 Wagner (10.1016/S2589-7500(20)30216-8_bib3) 2020; 9 James (10.1016/S2589-7500(20)30216-8_bib27) 2002; 3 Lavanya (10.1016/S2589-7500(20)30216-8_bib15) 2009; 16 Sabanayagam (10.1016/S2589-7500(20)30216-8_bib24) 2020; 2 Yamashita (10.1016/S2589-7500(20)30216-8_bib9) 2020; 9 Elliott (10.1016/S2589-7500(20)30216-8_bib16) 2008; 37 Rim (10.1016/S2589-7500(20)30216-8_bib2) 2020; 40 Chang (10.1016/S2589-7500(20)30216-8_bib8) 2020 Atkins (10.1016/S2589-7500(20)30216-8_bib21) 2019 |
| References_xml | – volume: 3 start-page: 139 year: 2002 ident: bib27 article-title: Appropriate Asian body mass indices? publication-title: Obes Rev – volume: 87 start-page: 247 year: 2009 end-page: 261 ident: bib13 article-title: The Beijing eye study publication-title: Acta Ophthalmol – volume: 358 start-page: 1134 year: 2001 end-page: 1140 ident: bib1 article-title: Retinal microvascular abnormalities and incident stroke: the Atherosclerosis Risk in Communities Study publication-title: Lancet – volume: 37 start-page: 234 year: 2008 end-page: 244 ident: bib16 article-title: The UK Biobank sample handling and storage protocol for the collection, processing and archiving of human blood and urine publication-title: Int J Epidemiol – volume: 15 year: 2020 ident: bib11 article-title: Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: a cross-sectional study of chronic diseases in central China publication-title: PLoS One – volume: 206 start-page: 48 year: 2019 end-page: 73 ident: bib28 article-title: Patterns and risk factor profiles of visual loss in a multiethnic Asian population: the Singapore Epidemiology of Eye Diseases study publication-title: Am J Ophthalmol – volume: 84 start-page: 457 year: 2013 end-page: 467 ident: bib23 article-title: Raising awareness of acute kidney injury: a global perspective of a silent killer publication-title: Kidney Int – volume: 243 start-page: 9 year: 2020 end-page: 20 ident: bib29 article-title: Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence publication-title: Ophthalmologica – year: 2016 ident: bib19 article-title: Show, attend and tell: neural image caption generation with visual attention publication-title: arXiv – volume: 4 start-page: 793 year: 2020 end-page: 800 ident: bib17 article-title: Deep learning for automated sorting of retinal photographs publication-title: Ophthalmol Retina – volume: 40 start-page: 44 year: 2020 end-page: 59 ident: bib2 article-title: Retinal vascular signs and cerebrovascular diseases publication-title: J Neuroophthalmol – volume: 22 start-page: 1148 year: 2018 end-page: 1161 ident: bib22 article-title: International clinical practice guidelines for sarcopenia (ICFSR): screening, diagnosis and management publication-title: J Nutr Health Aging – volume: 118 start-page: 812 year: 2011 end-page: 818 ident: bib25 article-title: Retinal vascular tortuosity, blood pressure, and cardiovascular risk factors publication-title: Ophthalmology – year: 2020 ident: bib8 article-title: Association of cardiovascular mortality and deep learning-funduscopic atherosclerosis score derived from retinal fundus images publication-title: Am J Ophthalmol – volume: 46 start-page: 59 year: 2001 end-page: 80 ident: bib26 article-title: Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality publication-title: Surv Ophthalmol – volume: 2 start-page: e295 year: 2020 end-page: e302 ident: bib24 article-title: A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations publication-title: Lancet Digit Health – volume: 9 start-page: 4 year: 2020 ident: bib9 article-title: Factors in color fundus photographs that can be used by humans to determine sex of individuals publication-title: Transl Vis Sci Technol – start-page: 93 year: 2019 end-page: 103 ident: bib21 article-title: Effects of sarcopenic obesity on cardiovascular disease and all-cause mortality publication-title: Nutrition and skeletal muscle – volume: 4 start-page: 18 year: 2020 end-page: 27 ident: bib6 article-title: Detection of anaemia from retinal fundus images via deep learning publication-title: Nat Biomed Eng – volume: 14 start-page: 25 year: 2007 end-page: 35 ident: bib14 article-title: Rationale and methodology for a population-based study of eye diseases in Malay people: the Singapore Malay eye study (SiMES) publication-title: Ophthalmic Epidemiol – year: 2015 ident: bib18 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv – volume: 1 start-page: e328 year: 2019 end-page: e329 ident: bib20 article-title: Reporting on deep learning algorithms in health care publication-title: Lancet Digital Health – volume: 17 start-page: 195 year: 2019 ident: bib12 article-title: Key challenges for delivering clinical impact with artificial intelligence publication-title: BMC Med – volume: 10 year: 2020 ident: bib7 article-title: Effects of hypertension, diabetes, and smoking on age and sex prediction from retinal fundus images publication-title: Sci Rep – volume: 9 start-page: 6 year: 2020 ident: bib3 article-title: Insights into systemic disease through retinal imaging-based oculomics publication-title: Transl Vis Sci Technol – volume: 103 start-page: 167 year: 2019 end-page: 175 ident: bib4 article-title: Artificial intelligence and deep learning in ophthalmology publication-title: Br J Ophthalmol – volume: 9 year: 2019 ident: bib10 article-title: Detection of smoking status from retinal images; a Convolutional Neural Network study publication-title: Sci Rep – volume: 2 start-page: 158 year: 2018 end-page: 164 ident: bib5 article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning publication-title: Nat Biomed Eng – volume: 16 start-page: 325 year: 2009 end-page: 336 ident: bib15 article-title: Methodology of the Singapore Indian Chinese Cohort (SICC) eye study: quantifying ethnic variations in the epidemiology of eye diseases in Asians publication-title: Ophthalmic Epidemiol – start-page: 93 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib21 article-title: Effects of sarcopenic obesity on cardiovascular disease and all-cause mortality – volume: 9 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib10 article-title: Detection of smoking status from retinal images; a Convolutional Neural Network study publication-title: Sci Rep doi: 10.1038/s41598-019-43670-0 – volume: 4 start-page: 18 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib6 article-title: Detection of anaemia from retinal fundus images via deep learning publication-title: Nat Biomed Eng doi: 10.1038/s41551-019-0487-z – volume: 3 start-page: 139 year: 2002 ident: 10.1016/S2589-7500(20)30216-8_bib27 article-title: Appropriate Asian body mass indices? publication-title: Obes Rev doi: 10.1046/j.1467-789X.2002.00063.x – volume: 22 start-page: 1148 year: 2018 ident: 10.1016/S2589-7500(20)30216-8_bib22 article-title: International clinical practice guidelines for sarcopenia (ICFSR): screening, diagnosis and management publication-title: J Nutr Health Aging doi: 10.1007/s12603-018-1139-9 – year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib8 article-title: Association of cardiovascular mortality and deep learning-funduscopic atherosclerosis score derived from retinal fundus images publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2020.03.027 – volume: 40 start-page: 44 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib2 article-title: Retinal vascular signs and cerebrovascular diseases publication-title: J Neuroophthalmol doi: 10.1097/WNO.0000000000000888 – volume: 103 start-page: 167 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib4 article-title: Artificial intelligence and deep learning in ophthalmology publication-title: Br J Ophthalmol doi: 10.1136/bjophthalmol-2018-313173 – volume: 1 start-page: e328 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib20 article-title: Reporting on deep learning algorithms in health care publication-title: Lancet Digital Health doi: 10.1016/S2589-7500(19)30132-3 – volume: 15 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib11 article-title: Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: a cross-sectional study of chronic diseases in central China publication-title: PLoS One – volume: 46 start-page: 59 year: 2001 ident: 10.1016/S2589-7500(20)30216-8_bib26 article-title: Retinal microvascular abnormalities and their relationship with hypertension, cardiovascular disease, and mortality publication-title: Surv Ophthalmol doi: 10.1016/S0039-6257(01)00234-X – volume: 358 start-page: 1134 year: 2001 ident: 10.1016/S2589-7500(20)30216-8_bib1 article-title: Retinal microvascular abnormalities and incident stroke: the Atherosclerosis Risk in Communities Study publication-title: Lancet doi: 10.1016/S0140-6736(01)06253-5 – volume: 2 start-page: e295 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib24 article-title: A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations publication-title: Lancet Digit Health doi: 10.1016/S2589-7500(20)30063-7 – year: 2015 ident: 10.1016/S2589-7500(20)30216-8_bib18 article-title: Very deep convolutional networks for large-scale image recognition publication-title: arXiv – volume: 243 start-page: 9 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib29 article-title: Strategies to tackle the global burden of diabetic retinopathy: from epidemiology to artificial intelligence publication-title: Ophthalmologica doi: 10.1159/000502387 – volume: 37 start-page: 234 year: 2008 ident: 10.1016/S2589-7500(20)30216-8_bib16 article-title: The UK Biobank sample handling and storage protocol for the collection, processing and archiving of human blood and urine publication-title: Int J Epidemiol doi: 10.1093/ije/dym276 – volume: 206 start-page: 48 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib28 article-title: Patterns and risk factor profiles of visual loss in a multiethnic Asian population: the Singapore Epidemiology of Eye Diseases study publication-title: Am J Ophthalmol doi: 10.1016/j.ajo.2019.05.006 – volume: 14 start-page: 25 year: 2007 ident: 10.1016/S2589-7500(20)30216-8_bib14 article-title: Rationale and methodology for a population-based study of eye diseases in Malay people: the Singapore Malay eye study (SiMES) publication-title: Ophthalmic Epidemiol doi: 10.1080/09286580600878844 – volume: 9 start-page: 6 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib3 article-title: Insights into systemic disease through retinal imaging-based oculomics publication-title: Transl Vis Sci Technol doi: 10.1167/tvst.9.2.6 – volume: 10 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib7 article-title: Effects of hypertension, diabetes, and smoking on age and sex prediction from retinal fundus images publication-title: Sci Rep – volume: 2 start-page: 158 year: 2018 ident: 10.1016/S2589-7500(20)30216-8_bib5 article-title: Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning publication-title: Nat Biomed Eng doi: 10.1038/s41551-018-0195-0 – volume: 87 start-page: 247 year: 2009 ident: 10.1016/S2589-7500(20)30216-8_bib13 article-title: The Beijing eye study publication-title: Acta Ophthalmol doi: 10.1111/j.1755-3768.2008.01385.x – volume: 16 start-page: 325 year: 2009 ident: 10.1016/S2589-7500(20)30216-8_bib15 article-title: Methodology of the Singapore Indian Chinese Cohort (SICC) eye study: quantifying ethnic variations in the epidemiology of eye diseases in Asians publication-title: Ophthalmic Epidemiol doi: 10.3109/09286580903144738 – volume: 9 start-page: 4 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib9 article-title: Factors in color fundus photographs that can be used by humans to determine sex of individuals publication-title: Transl Vis Sci Technol doi: 10.1167/tvst.9.2.4 – year: 2016 ident: 10.1016/S2589-7500(20)30216-8_bib19 article-title: Show, attend and tell: neural image caption generation with visual attention publication-title: arXiv – volume: 84 start-page: 457 year: 2013 ident: 10.1016/S2589-7500(20)30216-8_bib23 article-title: Raising awareness of acute kidney injury: a global perspective of a silent killer publication-title: Kidney Int doi: 10.1038/ki.2013.153 – volume: 17 start-page: 195 year: 2019 ident: 10.1016/S2589-7500(20)30216-8_bib12 article-title: Key challenges for delivering clinical impact with artificial intelligence publication-title: BMC Med doi: 10.1186/s12916-019-1426-2 – volume: 4 start-page: 793 year: 2020 ident: 10.1016/S2589-7500(20)30216-8_bib17 article-title: Deep learning for automated sorting of retinal photographs publication-title: Ophthalmol Retina doi: 10.1016/j.oret.2020.03.007 – volume: 118 start-page: 812 year: 2011 ident: 10.1016/S2589-7500(20)30216-8_bib25 article-title: Retinal vascular tortuosity, blood pressure, and cardiovascular risk factors publication-title: Ophthalmology doi: 10.1016/j.ophtha.2010.08.045 |
| SSID | ssj0002213777 |
| Score | 2.5213816 |
| Snippet | The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological parameters.... SummaryBackgroundThe application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and... Background: The application of deep learning to retinal photographs has yielded promising results in predicting age, sex, blood pressure, and haematological... |
| SourceID | doaj proquest pubmed crossref elsevier |
| SourceType | Open Website Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | e526 |
| SubjectTerms | Algorithms Area Under Curve Asia Beijing Biomarkers Body Composition Creatinine - blood Deep Learning Ethnicity Europe Female Humans Image Processing, Computer-Assisted - methods Informatics Internal Medicine Male Middle Aged Models, Biological Muscles Neural Networks, Computer Photography Public Health Republic of Korea Retina ROC Curve Singapore United Kingdom |
| Title | Prediction of systemic biomarkers from retinal photographs: development and validation of deep-learning algorithms |
| URI | https://www.clinicalkey.com/#!/content/1-s2.0-S2589750020302168 https://www.clinicalkey.es/playcontent/1-s2.0-S2589750020302168 https://dx.doi.org/10.1016/S2589-7500(20)30216-8 https://www.ncbi.nlm.nih.gov/pubmed/33328047 https://www.proquest.com/docview/2470899651 https://doaj.org/article/b5f8cad42eb84d65bf1b2323da861029 |
| Volume | 2 |
| WOSCitedRecordID | wos000581145100010&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2589-7500 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002213777 issn: 2589-7500 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2589-7500 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002213777 issn: 2589-7500 databaseCode: M~E dateStart: 20190101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Nb9QwELWg4sAFgfhaPiojcYBDqOPYscMNUCsOUFUCpL1Zdmy3i0qySrYc-e3M2Nm0lUDLgcseorxkNTPreV7PvCHkZeVqroJAhUsbC1FbVuhW-ULqlpcROK-2aWrJJ3V8rJfL5uTKqC-sCcvywNlwB05G3VoveHBa-Fq6WDpgAZW3GjI_T617wHqubKa-J1EXVNLDXmkudVNAWmSX7TsHX-aLrzh7XUGaqwt9LTEl_f5r-elv_DPloaO75M5EIOm7_MXvkRuhu0-GkwEPXNDItI80yzOvWorN9Vh_M4wU-0gotiwien3Wb7JW9fiW-su6IWo7TyH2VnnSEj7Lh7AuptkSp9Sen_bDanP2Y3xAvh0dfv3wsZimKRSt1ApnzjPnJBe28a70YFLwhba2dMBIrAo2yhCikE0pYd9qS28b2Gdjk5aF25lvq4dkr-u78JhQEZvGMmeV8rWISltgOZ5VNjYC1gjeLIjYmtK0k9Q4Trw4N3NNGXrAoAcMZyZ5wOgFeTPD1llrYxfgPfppvhmlstMFCCAzBZDZFUALUm-9bLbdqLB-woNWu96u_gQM47QKjKY0IzcsoxHMWYICUs_IiehkAvMvL32xDUQDCwGe7tgu9Bej4ULhEW4tywV5lCN0NkxVVVwzoZ78D4M9Jbc5_umQKhqfkb3NcBGek1vtz81qHPbJTbXU--nXCJ-ffx3-BiUCMy8 |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Prediction+of+systemic+biomarkers+from+retinal+photographs%3A+development+and+validation+of+deep-learning+algorithms&rft.jtitle=The+Lancet.+Digital+health&rft.au=Tyler+Hyungtaek+Rim%2C+MD&rft.au=Geunyoung+Lee%2C+BS&rft.au=Youngnam+Kim%2C+MSc&rft.au=Yih-Chung+Tham%2C+PhD&rft.date=2020-10-01&rft.pub=Elsevier&rft.issn=2589-7500&rft.volume=2&rft.issue=10&rft.spage=e526&rft.epage=e536&rft_id=info:doi/10.1016%2FS2589-7500%2820%2930216-8&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_b5f8cad42eb84d65bf1b2323da861029 |
| thumbnail_m | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=https%3A%2F%2Fcdn.clinicalkey.com%2Fck-thumbnails%2F25897500%2FS2589750020X00100%2Fcov150h.gif |