Artificial Intelligence Methods for Rapid Vascular Access Aneurysm Classification in Remote or In-Person Settings.

BACKGROUND: Innovations in artificial intelligence (AI) have proven to be effective contributors to high-quality health care. We examined the beneficial role AI can play in noninvasively grading vascular access aneurysms to reduce high-morbidity events, such as rupture, in ESRD patients on hemodialysis. METHODS: Our AI instrument noninvasively examines and grades aneurysms in both arteriovenous fistulas and arteriovenous grafts. Aneurysm stages were adjudicated by 3 vascular specialists, based on a grading system that focuses on actions that need to be taken. Our automatic classification of aneurysms builds on 2 components: (a) the use of smartphone technology to capture aneurysm appearance and (b) the analysis of these images using a cloud-based convolutional neural network (CNN). RESULTS: There was a high degree of correlation between our noninvasive AI instrument and the results of the adjudication by the vascular experts. Our results indicate that CNN can automatically classify aneurysms. We achieved a >90% classification accuracy in the validation images. CONCLUSION: This is the first quality improvement project to show that an AI instrument can reliably grade vascular access aneurysms in a noninvasive way, allowing rapid assessments to be made on patients who would otherwise be at risk for highly morbid events. Moreover, these AI-assisted assessments can be made without having to schedule separate appointments and potentially even via telehealth.

Nerve atrophy in severe trigeminal neuralgia: noninvasive confirmation at MR imaging--initial experience.

PURPOSE: To retrospectively evaluate the size of the trigeminal nerve on magnetic resonance (MR) images of patients with unilateral trigeminal neuralgia. MATERIALS AND METHODS: Institutional review board approval was obtained and informed consent was waived for this HIPAA-compliant study. The sizes of the trigeminal nerves in 31 patients (18 men and 13 women; mean age, 68 years; age range, 44-84 years) with clinically confirmed intractable unilateral trigeminal neuralgia were measured before treatment with gamma knife radiosurgery. Images were analyzed separately by two neuroradiologists who were blinded to the side of the face with symptoms. Coronal projection images were used to determine the diameter and cross-sectional area of the trigeminal nerves at 5 mm from the entry point of the nerve into the pons. Comparisons were made by using a paired t test. Interobserver variability was assessed by using the Pearson correlation coefficient. RESULTS: The mean diameter of the trigeminal nerve on the symptomatic side was significantly smaller than the mean diameter on the asymptomatic side in 30 of 31 patients (2.11 mm +/- 0.40 [standard deviation] and 2.62 mm +/- 0.56, P < .001, 95% confidence interval: -0.35, -0.67 mm). The mean cross-sectional area on the symptomatic side was significantly smaller than the area on the asymptomatic side in 27 of 31 patients (4.50 mm(2) +/- 1.75 and 6.28 mm(2) +/- 2.19, P < .001, 95% confidence interval: -2.41, -1.16 mm(2)). CONCLUSION: The results indicate that trigeminal nerve atrophy can be depicted noninvasively in patients with trigeminal neuralgia.