{"doi":"10.1007/s00125-021-05617-x","title":"Artificial intelligence utilising corneal confocal microscopy for the diagnosis of peripheral neuropathy in diabetes mellitus and prediabetes","abstract":"AIMS/HYPOTHESIS: We aimed to develop an artificial intelligence (AI)-based deep learning algorithm (DLA) applying attribution methods without image segmentation to corneal confocal microscopy images and to accurately classify peripheral neuropathy (or lack of). METHODS: The AI-based DLA utilised convolutional neural networks with data augmentation to increase the algorithm's generalisability. The algorithm was trained using a high-end graphics processor for 300 epochs on 329 corneal nerve images and tested on 40 images (1 image/participant). Participants consisted of healthy volunteer (HV) participants (n = 90) and participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141) and prediabetes (n = 50) (defined as impaired fasting glucose, impaired glucose tolerance or a combination of both), and were classified into HV, those without neuropathy (PN-) (n = 149) and those with neuropathy (PN+) (n = 130). For the AI-based DLA, a modified residual neural network called ResNet-50 was developed and used to extract features from images and perform classification. The algorithm was tested on 40 participants (15 HV, 13 PN-, 12 PN+). Attribution methods gradient-weighted class activation mapping (Grad-CAM), Guided Grad-CAM and occlusion sensitivity displayed the areas within the image that had the greatest impact on the decision of the algorithm. RESULTS: -score of 0.91 (95% CI 0.74, 1.0). The features displayed by the attribution methods demonstrated more corneal nerves in HV, a reduction in corneal nerves for PN- and an absence of corneal nerves for PN+ images. CONCLUSIONS/INTERPRETATION: We demonstrate promising results in the rapid classification of peripheral neuropathy using a single corneal image. A large-scale multicentre validation study is required to assess the utility of AI-based DLA in screening and diagnostic programmes for diabetic neuropathy.","journal":"Diabetologia","year":2021,"id":153453,"datarank":2.006506443271619,"base_score":4.248495242049359,"endowment":4.248495242049359,"self_citation_contribution":0.637274286307404,"citation_network_contribution":1.369232156964215,"self_endowment_contribution":0.637274286307404,"citer_contribution":1.369232156964215,"corpus_percentile":null,"corpus_rank":null,"citation_count":69,"citer_count":57,"citers_with_citation_signal":44,"citers_with_endowment":44,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.9588,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2021-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":651057,"name":"Yanda Meng","orcid":"0000-0001-7344-2174","position":1,"is_corresponding":false},{"id":651058,"name":"Jamie Burgess","orcid":"0000-0002-7165-6918","position":2,"is_corresponding":false},{"id":328361,"name":"Maryam Ferdousi","orcid":"0000-0002-7989-8233","position":3,"is_corresponding":false},{"id":328364,"name":"Shazli Azmi","orcid":"0000-0002-1789-6988","position":4,"is_corresponding":false},{"id":328363,"name":"Ioannis N. Petropoulos","orcid":"0000-0002-1126-7638","position":5,"is_corresponding":false},{"id":651059,"name":"Stephen B. Kaye","orcid":"0000-0003-0390-0592","position":6,"is_corresponding":false},{"id":292135,"name":"Rayaz A. Malik","orcid":"0000-0002-7188-8903","position":7,"is_corresponding":false},{"id":651060,"name":"Yalin Zheng","orcid":"0000-0002-7873-0922","position":8,"is_corresponding":false},{"id":347619,"name":"Uazman Alam","orcid":"0000-0002-3190-1122","position":9,"is_corresponding":false},{"id":651056,"name":"Frank Preston","orcid":"0000-0002-3953-331X","position":0,"is_corresponding":true}],"reference_count":47,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-07-18T23:43:44.759273Z","pmid":"34806115","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}