Determining the Degree of Perceptible Static Eyelid Asymmetry and Effect of Face Inversion: A Cross-sectional Pilot Study.

PURPOSE: To determine the degree of static eyelid asymmetry required to be perceptible and whether this is affected by image inversion. METHODS: Images of 3 volunteers were digitally manipulated to have eyelid asymmetry of 0.5 mm, 1 mm, or 1.5 mm of 3 different types, upper lid ptosis, upper lid retraction, and lower lid retraction. Forty-nine laypersons stated whether the images were symmetrical or asymmetrical. A separate inversion survey, completed by 29 clinicians, consisted of symmetrical images and 1 mm asymmetrical images, with half being inverted. RESULTS: Upper lid ptosis, upper lid retraction, and lower lid retraction were not detected by most laypeople at 0.5 mm of severity (18.9%, 6.7%, 18.9% detection, respectively) but all 3 were detected by the majority of participants once asymmetry reached 1 mm severity (65.7%, 61.8%, 51.0% detection, respectively) and rose to over 70% identification at 1.5 mm (92.2%, 73.5%, 73.5% detection, respectively). Inversion of the images led to 19.7% lower rates of correct identification of asymmetrical faces compared with images presented in the correct orientation (80.7% asymmetry identified in normal images, 61.0% inverted, p < 0.001). CONCLUSIONS: All asymmetries were detectable by a majority of laypersons at a severity of 1 mm. Image inversion decreases a clinician's ability to detect a 1 mm asymmetry, indicating an impaired asymmetry perception in the intraoperative view. This study provides research to counsel patients with varying degrees of eyelid asymmetry.

Painful Diabetic Peripheral Neuropathy: Practical Guidance and Challenges for Clinical Management.

Painful diabetic peripheral neuropathy (PDPN) is present in nearly a quarter of people with diabetes. It is estimated to affect over 100 million people worldwide. PDPN is associated with impaired daily functioning, depression, sleep disturbance, financial instability, and a decreased quality of life. Despite its high prevalence and significant health burden, it remains an underdiagnosed and undertreated condition. PDPN is a complex pain phenomenon with the experience of pain associated with and exacerbated by poor sleep and low mood. A holistic approach to patient-centred care alongside the pharmacological therapy is required to maximise benefit. A key treatment challenge is managing patient expectation, as a good outcome from treatment is defined as a reduction in pain of 30-50%, with a complete pain-free outcome being rare. The future for the treatment of PDPN holds promise, despite a 20-year void in the licensing of new analgesic agents for neuropathic pain. There are over 50 new molecular entities reaching clinical development and several demonstrating benefit in early-stage clinical trials. We review the current approaches to its diagnosis, the tools, and questionnaires available to clinicians, international guidance on PDPN management, and existing pharmacological and non-pharmacological treatment options. We synthesise evidence and the guidance from the American Association of Clinical Endocrinology, American Academy of Neurology, American Diabetes Association, Diabetes Canada, German Diabetes Association, and the International Diabetes Federation into a practical guide to the treatment of PDPN and highlight the need for future research into mechanistic-based treatments in order to prioritise the development of personalised medicine.

Informed Consent In Facial Photograph Publishing: A Cross-sectional Pilot Study To Determine The Effectiveness Of Deidentification Methods.

This study determined the effectiveness of three deidentification methods: use of a) a black box to obscure facial landmarks, b) a letterbox view to display restricted facial landmarks and c) a half letterbox view. Facial images of well-known celebrities were used to create a series of decreasingly deidentified images and displayed to participants in a structured interview session. 55.5% were recognised when all facial features were covered using a black box, leaving only the hair and neck exposed. The letterbox view proved more effective, reaching over 50% recognition only once the periorbital region, eyebrows, and forehead were visible. The half letterbox was the most effective, requiring the nose to be revealed before recognition reached over 50%, and should be the option of choice where appropriate. These findings provide valuable information for informed consent discussions, and we recommend consent to publish forms should stipulate the deidentification method that will be used.

Artificial intelligence utilising corneal confocal microscopy for the diagnosis of peripheral neuropathy in diabetes mellitus and prediabetes.

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: The results were as follows: HV: recall of 1.0 (95% CI 1.0, 1.0), precision of 0.83 (95% CI 0.65, 1.0), F1-score of 0.91 (95% CI 0.79, 1.0); PN-: recall of 0.85 (95% CI 0.62, 1.0), precision of 0.92 (95% CI 0.73, 1.0), F1-score of 0.88 (95% CI 0.71, 1.0); PN+: recall of 0.83 (95% CI 0.58, 1.0), precision of 1.0 (95% CI 1.0, 1.0), F1-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.