Application of digital tools and artificial intelligence in the Myasthenia Gravis Core Examination

Abstract

Background: Advances in video image analysis and artificial intelligence provide opportunities to transform how patients are evaluated. In this study, we assessed the ability to quantify Zoom video recordings of a standardized neurological examination- the Myasthenia Gravis Core Examination (MG-CE)-designed for telemedicine evaluations.

Methods: We used Zoom (Zoom Video Communications) videos of patients with myasthenia gravis (MG) who underwent the MG-CE. Computer vision, in combination with artificial intelligence methods, was used to develop algorithms to analyze the videos, with a focus on eye and body motions. To assess the examinations involving vocalization, signal processing methods, such as natural language processing (NLP), were developed. A series of algorithms were developed to automatically compute the metrics of the MG-CE.

Results: A total of 51 patients with MG were assessed, with videos recorded twice on separate days, while 15 control subjects were evaluated once. We successfully quantified the positions of the lids, eyes, and arms and developed respiratory metrics based on breath counts. The cheek puff exercise was found to have limited value for quantification. Technical limitations included variations in illumination, bandwidth, and the fact that the recording was conducted from the examiner's side rather than the patient's side.

Conclusion: Several aspects of the MG-CE can be quantified to produce continuous measurements using standard Zoom video recordings. Further development of the technology will enable trained non-physician healthcare providers to conduct precise examinations of patients with MG outside of conventional clinical settings, including for the purpose of clinical trials.

Keywords: clinical trial; computer vision; deep learning; diplopia; myasthenia gravis; neurological disease; ptosis; telehealth.

Figure 1

(A) Distribution of the percentage of change from the maximum separation of the upper and lower eyelids during the examination. The controls are represented using two adjacent black bars, one for each eye. Similarly, the patient results are shown in blue or red bars. The most severe ptosis cases from the two evaluations are presented here. Red columns represent the participants who were significantly different from the controls (one standard deviation from the mean). Green circles represent the individuals older than 70 years. Yellow horizontal lines represent the mean metric output for the control, with the mean minus one standard deviation serving as the threshold to mark the presence of ptosis. (B,C) Two examples of the variation in the distance between the upper lid and lower lid (black curve) and the distance from the bottom of the iris to the lower lid (red curve), measured in pixels, over the course of the exercise. The horizontal axis represents the time elapsed during the exercise, in seconds. Figure (B) shows a progressive, linear, and continuous eyelid fatigue well fitted by a linear square (green curve), while (C) shows the measurements of a participant struggling to keep the eyes open. It is important to note that the number of pixels representing the eye opening differs between these two participants, which reflects the dataset, where the distance between the participant and the camera was not standardized. The participant in (B) was assessed to have moderate ptosis, while the participant in (C) was graded from no ptosis to mild and moderate ptosis.

Figure 2

Ocular alignment was assessed by the difference in the barycentric coordinate (0 = no misalignment). The progressive misalignment between both eyes used the least squares approximation of the barycentric coordinate change during the exercise. The controls are represented using a black bar. The patient results are shown using blue bars if there is no significant misalignment developed during the examination and red bars if misalignment was present. The green circle represents the participants older than 70 years. Yellow horizontal lines represent the mean metric output for the control, with the mean plus one standard deviation serving as the threshold to mark the presence of eye misalignment.

Figure 3

(A) Maximum arm extension time. All controls reached the 120-s limit. Nine MG patients (marked with a red bar) were unable to do so. The green circle represents the patients older than 70 years. (B) Linear drift of the arm extension, in radians, for the participants who could extend their arms for 120 s. The black bar represents the control group, and the blue bar represents MG patients who were similar to the controls. The red bar represents the MG patients with significantly greater drift. We show the maximum drift for both arms at both visits for MG patients. The green circle represents the participants older than 70 years. Yellow horizontal lines represent the mean metric output for the control group, with the mean minus one standard deviation serving as the threshold to mark the presence of shoulder muscular weakness.

Figure 4

Ascending time for the sit-to-stand exercise. The control results are represented in black, while the results of the MG patients are represented in blue, with red bars indicating significantly worse performance than controls. The green circle represents the patients older than 70 years. Yellow horizontal lines represent the mean metric output for the control group, with the mean plus one standard deviation serving as the threshold to mark the presence of leg muscular weakness.

Figure 5

Average variation of the acceleration (normalized distance/s square) of the vertical movement of the upper lip during the count-to-50 exercise. Black bars represent the controls, blue bars represent the MG patients, and red bars indicate significantly worse performance than the controls. The green circle represents the participants older than 70 years. Yellow horizontal lines represent the mean metric output for the control group, with the mean minus one standard deviation serving as the threshold to mark the presence of lip/facial muscular weakness.