Follow us on twitter

An artificial intelligence-based deep learning algorithm for the diagnosis of diabetic neuropathy using corneal confocal microscopy: a development and validation study – published online 12/11/2019

Bryan M. Williams, Davide Borroni, Rongjun Liu, Yitian Zhao, Jiong Zhang, Jonathan Lim, Baikai Ma, Vito Romano, Hong Qi, Maryam Ferdousi, Ioannis N. Petropoulos, Georgios Ponirakis, Stephen Kaye, Rayaz A. Malik, Uazman Alam, Yalin Zheng

Diabetic neuropathy is the strongest initiating risk factor for foot ulceration and amputations. Current ‘screening’ practices are highly subjective and only diagnose diabetic neuropathy when well-established, which is in stark contrast to the tools available for the early diagnosis of other diabetic complications, such as retinopathy. Future development of valid screening programmes utilising technology that detects early neuropathy is, therefore, of paramount importance and clinical need. In this issue, Williams et al (https://doi.org/10.1007/s00125-019-05023-4) present an artificial intelligence-based algorithm that accurately and rapidly detects diabetic neuropathy through non-invasive assessment of the corneal sub-basal nerve plexus using corneal confocal microscopy. They show that this approach outperforms the currently used automated software, with superior intraclass correlation coefficients for all major corneal nerve biomarkers. The authors conclude that these findings indicate that corneal confocal microscopy is now primed for population-based screening of diabetic neuropathy.

All News
Top