Artificial intelligence can analyze myoclonus severity from video footage

February 07, 2020

Fast, reliable and automatic assessment of the severity of myoclonic jerks from video footage is now possible, thanks to an algorithm using deep convolutional neural network architecture and pretrained models that identify and track keypoints in the human body. Published in Seizure, the study is a joint effort by the Epilepsy Centre at Kuopio University Hospital, the University of Eastern Finland and Neuro Event Labs.

Myoclonus refers to brief, involuntary twitching of muscles and it is the most disabling and progressive drug-resistant symptom in patients with progressive myoclonus epilepsy type 1 (EPM1). It is stimulus sensitive and its severity fluctuates during the day. In addition, stress, sleep deprivation and anxiety can cause significant aggravation of myoclonic symptoms. Clinical objective follow-up of myoclonus is challenging and requires extensive expertise from the treating physician. Therefore, physicians and the medical industry have been seeking automatic tools to improve the consistency and reliability of serial myoclonus evaluations in order to reliably estimate treatment effect and disease progression.

Unified myoclonus rating scale (UMRS), a clinical videorecorded test panel, is the gold standard currently used to evaluate myoclonus. The researchers analysed 10 videorecorded UMRS test panels using automatic pose estimation and keypoint detection methods. The automatic methods were successful in detecting and tracking predefined keypoints in the human body during movement. The researchers also analysed speed changes and the smoothness of movement to detect and quantify myoclonic jerks during an active seizure. The scores obtained using automatic myoclonus detection correlated well with the clinical UMRS myoclonus with action and functional tests scores evaluated by an experienced clinical researcher.

The study showed that the automatic method involving keypoint detection and pose estimation from video footage reliably quantified myoclonic jerks in EPM1 patients. The automatic quantification of myoclonus correlated well with the clinical evaluation. It also effectively quantified the smoothness of movement, and was sensitive enough to detect small-amplitude and high-frequency myoclonic jerks.
For further information, please contact:
Jelena Hyppönen jelena.hypponen (at)
CEO Kaapo Annala kaapo.annala (at),
Professor Reetta Kälviäinen reetta.kalviainen (at), tel. +358405839249

Article: J. Hyppönen, A. Hakala, K. Annala, H. Zhang, J. Peltola, E. Mervaala, R. Kälviäinen Automatic assessment of the myoclonus severity from videos recorded according to standardized Unified Myoclonus Rating Scale protocol and using human pose and body movement analysis. Seizure: European Journal of Epilepsy. DOI: 10.1016/j.seizure.2020.01.014

University of Eastern Finland

Related Human Body Articles from Brightsurf:

Human norovirus strains differ in sensitivity to the body's first line of defense
Human norovirus strains differ in sensitivity to interferon, one of the body's first line of defense.

"Hotspots" of a corona infection in the human body
An infection with the coronavirus SARS-CoV-2 can affect multiple organs.

UTEP researchers develop nanohybrid vehicle to optimally deliver drugs into the human body
The researchers discovered that encapsulating ellagic acid in chitosan, a sugar, reduces its inherent cytotoxicity while enhancing its antioxidant properties.

Protecting thin, flexible brain interfaces from the human body
Researchers have demonstrated the ability to implant an ultrathin, flexible neural interface with thousands of electrodes into the brain with a projected lifetime of more than six years.

The human body as an electrical conductor, a new method of wireless power transfer
The project Electronic AXONs: wireless microstimulators based on electronic rectification of epidermically applied currents (eAXON, 2017-2022), funded by a European Research Council (ERC) Consolidator Grant awarded to Antoni Ivorra, head of the Biomedical Electronics Research Group (BERG) of the Department of Information and Communication Technologies (DTIC) at UPF principally aims to 'develop very thin, flexible, injectable microstimulators to restore movement in paralysis', says Ivorra, principal investigator of the project.

Wake Forest scientists create world's most sophisticated lab model of the human body
Scientists at the Wake Forest Institute for Regenerative Medicine (WFIRM) have developed the world's most sophisticated laboratory model of the human body, creating a system of miniaturized organs that can be used to detect harmful and adverse effects of drugs before they are prescribed to patients.

Enhancing drug testing with human body-on-chip systems
Scientists at Tel Aviv University and Harvard University have devised a functioning comprehensive multi-Organ-on-a-Chip (Organ Chip) platform that enables effective preclinical drug testing of human drug pharmacology.

Human Body-on-Chip platform enables in vitro prediction of drug behaviors in humans
Wyss Institute researchers have created a human Body-on-Chips platform that lays the foundation for better and faster drug testing.

Machine keeps human livers alive for one week outside of the body
Researchers from the University Hospital Zurich, ETH Zurich, Wyss Zurich and the University of Zurich have developed a machine that repairs injured human livers and keeps them alive outside the body for one week.

Developed a band-aid-like sensor to detect human body conditions in real-time
DGIST announced that Professor Hyuk-Jun Kwon in the Department of Information and Communication Engineering developed a 'patch-based health diagnosis sensor system' that is easily attached to skin with Professor Sunkook Kim's research team at Sungkyunkwan University.

Read More: Human Body News and Human Body Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to