MétaCan
Menu
Back to cohort
Record W4410014583 · doi:10.1016/j.landig.2025.02.008

Non-invasive biopsy diagnosis of diabetic kidney disease via deep learning applied to retinal images: a population-based study

2025· article· en· W4410014583 on OpenAlexfundno aff
Ziyao Meng, Zhouyu Guan, Shujie Yu, Yi-Lan Wu, Jie Shen, Cynthia Ciwei Lim, Ting‐Li Chen, Dawei Yang, An Ran Ran, Feng He, Haslina Hamzah, Sarkaaj Singh, Anis Syazwani Abd Raof, Jian Wen Samuel Lee-Boey, Soo Kun Lim, Xufang Sun, Shuwang Ge, Gang Xu, Hua Su, Feng Lu, Xiaofei Liao, Hai Jin, Chenxin Deng, Lei Ruan, Cuntai Zhang, Chan Wu, Rongping Dai, Yixiao Jin, Wenxiao Wang, Tingyao Li, Ruhan Liu, Jiajia Li, Jia Shu, Yuwei Lu, Xiangning Wang, Qiang Wu, Yiming Qin, Jin Tang, Xiaohua Sheng, Qiong Jiao, Xiaokang Yang, Minyi Guo, Gareth J. McKay, Ruth Hogg, Gerald Liew, Evelyn Chee, Wynne Hsu, Mong Li Lee, Simon Szeto, Andrea O. Y. Luk, Juliana C.N. Chan, Carol Y. Cheung, Gavin Siew Wei Tan, Yih Chung Tham, Ching‐Yu Cheng, Charumathi Sabanayagam, Lee‐Ling Lim, Weiping Jia, Huating Li, Bin Sheng, Tien Yin Wong

Bibliographic record

VenueThe Lancet Digital Health · 2025
Typearticle
Languageen
FieldMedicine
TopicRetinal Imaging and Analysis
Canadian institutionsnot available
FundersNational Key Research and Development Program of ChinaSchool of Medicine, Shanghai Jiao Tong UniversityEconomic and Social Research CouncilTongji Medical College, Huazhong University of Science and TechnologyNatural Science Foundation for Young Scientists of Shanxi ProvinceNational Science and Technology Major ProjectMacau University of Science and TechnologyPeking Union Medical College HospitalShanghai Jiao Tong UniversityCenter for High Performance Computing, Shanghai Jiao Tong UniversityOffice of the First Minister and Deputy First MinisterMinistry of Water ResourcesPeking Union Medical CollegeChinese University of Hong KongHuazhong University of Science and TechnologyQueen's UniversityHealth and Social Care Research and Development DivisionPublic Health AgencyUnited Kingdom Clinical Research CollaborationNatural Science Foundation of Beijing MunicipalityCentre for Ageing Research and Development in IrelandNational University of SingaporeYoung Scientists FundWolfson FoundationQueen's University BelfastWellcome TrustShanghai Municipal Health CommissionTongji UniversityNational Natural Science Foundation of ChinaChinese Academy of Medical SciencesInnovative Research Team of High-level Local University in Shanghai
KeywordsMedicineRetinalDiseaseKidney diseasePopulationBiopsyPathologyRadiologyArtificial intelligenceComputer scienceOphthalmologyInternal medicine

Abstract

fetched live from OpenAlex

BACKGROUND: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images. METHODS: In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD; and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up. FINDINGS: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838-0·846) on the internal validation dataset and AUCs of 0·791-0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825-0·966) on the internal validation dataset and AUCs of 0·733-0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD with higher sensitivity (89·8% vs 66·3%, p<0·0001). In the longitudinal study, participants with isolated diabetic nephropathy and participants with NDKD identified by DeepDKD had a significant difference in renal function outcomes (proportion of estimated glomerular filtration rate decline: 27·45% vs 52·56%, p=0·0010). INTERPRETATION: Among diverse multi-ethnic populations with diabetes, a retinal image-based AI-deep learning system showed its potential for detecting DKD and differentiating isolated diabetic nephropathy from NDKD in clinical practice. FUNDING: National Key R & D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Municipal Key Clinical Specialty, Shanghai Research Centre for Endocrine and Metabolic Diseases, Innovative research team of high-level local universities in Shanghai, Noncommunicable Chronic Diseases-National Science and Technology Major Project, Clinical Special Program of Shanghai Municipal Health Commission, and the three-year action plan to strengthen the construction of public health system in Shanghai.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.008
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.007
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.008
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0010.001
Scholarly communication0.0010.001
Open science0.0010.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.014
GPT teacher head0.311
Teacher spread0.298 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations27
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueThe Lancet Digital HealthSame topicRetinal Imaging and AnalysisFrench-language works237,207