In chronical neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor patients’ disease. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase reliability in severity ratings. With these recordings automated, quantitative disability assessments by machine learning algorithms (MLA) may be created. Creation of these algorithms involves non-healthcare professionals, which is a challenge for keeping data privacy. Autoencoders may overcome this issue.
The aim of this proof of concept study was to test whether coded frame vectors of autoencoders contain relevant information for analysing videos of motor performance of MS patients.
In this study, twenty pre-rated videos of patients performing the finger-to-nose test (FNT) were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. Original and decoded videos were shown to 10 neurologists of an academic MS centre in Basel, Switzerland. Neurologists tested whether these 200 videos in total were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-EDSS definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between original and decoded videos.
In total, 172 from 200 (86%) videos had sufficient quality to be ratable. The intra-rater agreement between the original and decoded videos was 0.317 (Cohen’s weighted kappa). The average difference of ratings between original and decoded videos was 0.26 , in which the original videos were rated as more severe. The inter-rater agreement between the original and decoded videos was 0.459 (Cohen’s weighted kappa) and 0.302 (Cohen’s weighted kappa), respectively. The agreement was higher when no deficits or very severe deficits were present.
The vast majority of videos decoded by an auto-encoder contained clinically relevant information and had a fair intra-rater agreement with the original video. Autoencoders are a potential method for enabling the use of patient videos while preserving data privacy, especially when non-healthcare professionals are involved.