Greater small nerve fibre damage in the skin and cornea of type 1 diabetic patients with painful compared to painless diabetic neuropathy.

BACKGROUND AND AIM: Damage to small nociceptive fibres may contribute to painful diabetic neuropathy. We aimed to compare large and small nerve fibre measurements together with skin biopsy and corneal confocal microscopy in patients with type 1 diabetes and painful or painless diabetic neuropathy. METHODS: We have assessed the McGill pain questionnaire, neuropathy disability score, vibration perception threshold, warm and cold sensation thresholds, electrophysiology, corneal confocal microscopy and skin biopsy in participants with type 1 diabetes and painful (n = 41) or painless (n = 50) diabetic neuropathy and control subjects (n = 50). RESULTS: The duration of diabetes, body mass index, glycated haemoglobin (HbA1c), blood pressure and lipid profile did not differ between subjects with painful and painless neuropathy. Neuropathy disability score and vibration perception threshold were higher and sural nerve conduction velocity was lower, but sural nerve amplitude, peroneal nerve amplitude and conduction velocity and cold and warm sensation thresholds did not differ between patients with painful compared to painless diabetic neuropathy. However, intraepidermal nerve fibre density, corneal nerve fibre density, corneal nerve branch density and corneal nerve fibre length were significantly lower in subjects with painful compared to painless diabetic neuropathy. CONCLUSIONS: There is evidence of more severe neuropathy, particularly small fibre damage in the skin and cornea, of patients with painful compared to painless diabetic neuropathy.

Artificial Intelligence Based Analysis of Corneal Confocal Microscopy Images for Diagnosing Peripheral Neuropathy: A Binary Classification Model.

Diabetic peripheral neuropathy (DPN) is the leading cause of neuropathy worldwide resulting in excess morbidity and mortality. We aimed to develop an artificial intelligence deep learning algorithm to classify the presence or absence of peripheral neuropathy (PN) in participants with diabetes or pre-diabetes using corneal confocal microscopy (CCM) images of the sub-basal nerve plexus. A modified ResNet-50 model was trained to perform the binary classification of PN (PN+) versus no PN (PN-) based on the Toronto consensus criteria. A dataset of 279 participants (149 PN-, 130 PN+) was used to train (n = 200), validate (n = 18), and test (n = 61) the algorithm, utilizing one image per participant. The dataset consisted of participants with type 1 diabetes (n = 88), type 2 diabetes (n = 141), and pre-diabetes (n = 50). The algorithm was evaluated using diagnostic performance metrics and attribution-based methods (gradient-weighted class activation mapping (Grad-CAM) and Guided Grad-CAM). In detecting PN+, the AI-based DLA achieved a sensitivity of 0.91 (95%CI: 0.79-1.0), a specificity of 0.93 (95%CI: 0.83-1.0), and an area under the curve (AUC) of 0.95 (95%CI: 0.83-0.99). Our deep learning algorithm demonstrates excellent results for the diagnosis of PN using CCM. A large-scale prospective real-world study is required to validate its diagnostic efficacy prior to implementation in screening and diagnostic programmes.

Corneal Confocal Microscopy Detects Small Fibre Neuropathy in Patients with Upper Gastrointestinal Cancer and Nerve Regeneration in Chemotherapy Induced Peripheral Neuropathy.

There are multiple neurological complications of cancer and its treatment. This study assessed the utility of the novel non-invasive ophthalmic technique of corneal confocal microscopy in identifying neuropathy in patients with upper gastrointestinal cancer before and after platinum based chemotherapy. In this study, 21 subjects with upper gastrointestinal (oesophageal or gastric) cancer and 21 healthy control subjects underwent assessment of neuropathy using the neuropathy disability score, quantitative sensory testing for vibration perception threshold, warm and cold sensation thresholds, cold and heat induced pain thresholds, nerve conduction studies and corneal confocal microscopy. Patients with gastro-oesophageal cancer had higher heat induced pain (P = 0.04) and warm sensation (P = 0.03) thresholds with a significantly reduced sural sensory (P<0.01) and peroneal motor (P<0.01) nerve conduction velocity, corneal nerve fibre density (CNFD), nerve branch density (CNBD) and nerve fibre length (CNFL) (P<0.0001). Furthermore, CNFD correlated significantly with the time from presentation with symptoms to commencing chemotherapy (r = -0.54, P = 0.02), and CNFL (r = -0.8, P<0.0001) and CNBD (r = 0.63, P = 0.003) were related to the severity of lymph node involvement. After the 3rd cycle of chemotherapy, there was no change in any measure of neuropathy, except for a significant increase in CNFL (P = 0.003). Corneal confocal microscopy detects a small fibre neuropathy in this cohort of patients with upper gastrointestinal cancer, which was related to disease severity. Furthermore, the increase in CNFL after the chemotherapy may indicate nerve regeneration.