Feasibility of video/audio monitoring in the analysis of motion and treatment effects on night-time seizures – Interventional study

Ojanen, Petri; Zabihi, Morteza; Knight, Andrew; Roivanen, Reina; Lamusuo, Salla; Peltola, Jukka

doi:10.1016/j.eplepsyres.2022.106949

Cited by 6 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unequivocal seizures from previous recording sessions of enrolled patients were utilized only if they lacked unequivocal seizures in the latest monitoring period. Training patients were selected partly from a recent interventional study (22) and partly from Nelli R post-market surveillance (PMS) recordings, and testing patients were selected from Nelli R PMS recordings with the requirement that, for each subject, at least three unequivocal seizures of these three seizure types of interest were recorded during Nelli R registration and they had been described in detail in previous video-EEG reports. Due to the exclusion criteria listed above, 130 seizures from 10 patients formed a cohort for the model training, including four patients from the previous study (22).…”

Section: Methods Patient Populationmentioning

confidence: 99%

“…Training patients were selected partly from a recent interventional study (22) and partly from Nelli R post-market surveillance (PMS) recordings, and testing patients were selected from Nelli R PMS recordings with the requirement that, for each subject, at least three unequivocal seizures of these three seizure types of interest were recorded during Nelli R registration and they had been described in detail in previous video-EEG reports. Due to the exclusion criteria listed above, 130 seizures from 10 patients formed a cohort for the model training, including four patients from the previous study (22). The testing patient cohort consisted of 98 seizures from 17 patients, who were not included in the training phase, to evaluate the performance of the model.…”

Section: Methods Patient Populationmentioning

confidence: 99%

“…The Nelli seizure monitoring system is an audio/video-based semi-automated (hybrid) seizure monitoring platform that uses computer vision and machine learning to identify kinematic data (motion, oscillation, and audio) commonly associated with seizures with a positive motor component and human experts to visually assess these epochs (22). Moreover, the utility of the hybrid (algorithm-human) system for reviewing nocturnal video recordings to significantly decrease the workload and to provide accurate classification of major motor seizures (tonic-clonic, clonic, and focal motor seizures) has been demonstrated (23).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Ojanen,

Kertész,

Morales

et al. 2023

Front. Neurol.

Self Cite

View full text Add to dashboard Cite

IntroductionThis study evaluated the accuracy of motion signals extracted from video monitoring data to differentiate epileptic motor seizures in patients with drug-resistant epilepsy. 3D near-infrared video was recorded by the Nelli® seizure monitoring system (Tampere, Finland).Methods10 patients with 130 seizures were included in the training dataset, and 17 different patients with 98 seizures formed the testing dataset. Only seizures with unequivocal hyperkinetic, tonic, and tonic-clonic semiology were included. Motion features from the catch22 feature collection extracted from video were explored to transform the patients' videos into numerical time series for clustering and visualization.ResultsChanges in feature generation provided incremental discrimination power to differentiate between hyperkinetic, tonic, and tonic-clonic seizures. Temporal motion features showed the best results in the unsupervised clustering analysis. Using these features, the system differentiated hyperkinetic, tonic and tonic-clonic seizures with 91, 88, and 45% accuracy after 100 cross-validation runs, respectively. F1-scores were 93, 90, and 37%, respectively. Overall accuracy and f1-score were 74%.ConclusionThe selected features of motion distinguished semiological differences within epileptic seizure types, enabling seizure classification to distinct motor seizure types. Further studies are needed with a larger dataset and additional seizure types. These results indicate the potential of video-based hybrid seizure monitoring systems to facilitate seizure classification improving the algorithmic processing and thus streamlining the clinical workflow for human annotators in hybrid (algorithmic-human) seizure monitoring systems.

show abstract

Section: Methods Patient Populationmentioning

confidence: 99%

Section: Methods Patient Populationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Ojanen,

Kertész,

Morales

et al. 2023

Front. Neurol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…HVEM cost1, HVEM cost2, and HVEM cost3 are the HVEM cost after 1, 2, and 3 weeks of monitoring respectively; P1, P2, and P3 are the proportions of patients who achieve the diagnostic goal after 1, 2, and 3 weeks respectively. Therefore, the mean HVEM-DRE cost was calculated as follows: Mean HVEM-DRE cost1 = HVEM cost1 * P1 + (HVEM cost1 + In-hospital VEM cost) * (1-P1) (15) Mean HVEM-DRE cost2 = HVEM cost1 * P1 + HVEM cost2 * (P2 -P1) + (HVEM cost2 + In-hospital VEM cost) * (1-P2) (16) Mean HVEM-DRE costn = HVEM cost1 * P1 + HVEM cost2 * (P2 -P1) + …+ HVEM costn * (Pn -Pn-1) + (HVEM costn + In-hospital VEM cost) * (1-Pn)(17)…”

mentioning

confidence: 99%

Economic aspects of prolonged home video-EEG monitoring: a simulation study

Vander,

Bikmulina,

Froimovich

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction Video EEG monitoring (VEM) is an important tool to characterize clinical events suspected as seizures. It is also used for pre-surgical workup in patients with drug-resistant epilepsy (DRE). The high cost and inconvenience of in-hospital VEM led to interest in home VEM (HVEM). However, because antiseizure medications cannot be reduced at home, HVEM may require longer monitoring. While the economic aspect is one of the main motivations for HVEM, the cost of HVEM lasting several weeks has not been assessed. Methods We modeled the cost of HVEM during eight weeks and compared it to the cost of one-week in-hospital VEM. Additionally, we modeled the per-patient cost for a combination of HVEM and in-hospital VEM, considering that if in a proportion of patients HVEM fails to achieve its goal, they should undergo in-hospital VEM with drug reduction. Results The average cost of HVEM up to 4–6 weeks of monitoring was lower than that for the one-week in-hospital VEM. The combination of the three-week HVEM with one-week in-hospital VEM (if needed) reduced the per-patient cost by 6.6–28.6% as compared to the situation when all the patients with DRE were referred to the in-hospital VEM. Conclusions A prolonged intermittent HVEM can be economically efficient, which justifies directing the efforts into clinical trials and technology development.

show abstract

Characteristics of motion signal profiles of tonic–clonic, tonic, hyperkinetic, and motor seizures extracted from nocturnal video recordings

Ojanen,

Kertész,

Peltola

2024

Epileptic Disorders

View full text Add to dashboard Cite

ObjectiveIn this study, characteristics of signal profiles formed by motion, oscillation, and sound signals were analyzed to evaluate generalizability and variability in a single patient setting (intra‐patient variability) and between patients (inter‐patient variability). As a secondary objective, the effect of brivaracetam intervention on signal profiles was explored.MethodsPatient data included 13 hyperkinetic seizures, 65 tonic seizures, 13 tonic–clonic seizures, and 138 motor seizures from 11 patients. All patients underwent an 8‐week monitoring, and after a 3‐week baseline, brivaracetam was initiated. Motion, oscillation, and sound features extracted from the video were used to form signal profiles. Variance of signals was calculated, and combined median and quartile visualizations were used to visualize the results. Similarly, the effect of intervention was visualized.ResultsHyperkinetic motion signals showed a rapid increase in motion and sound signals without oscillations and achieved low intra‐patient variance. Tonic component created a recognizable peak in motion signal typical for tonic and tonic–clonic seizures. For tonic seizures, inter‐patient variance was low. Motor signal profiles were varying, and they did not form a generalizable signal profile. Visually recognizable changes were observed in the signal profiles of two patients.SignificanceVideo‐based motion signal analysis enabled the extraction of motion features characteristic for different motor seizure types which might be useful in further development of this system. Tonic component formed a recognizable seizure signature in the motion signal. Hyperkinetic and motor seizures may have not only significantly different motion signal amplitude but also overlapping signal profile characteristics which might hamper their automatic differentiation. Motion signals might be useful in the assessment of movement intensity changes to evaluate the treatment effect. Further research is needed to test generalizability and to increase reliability of the results.

show abstract

Feasibility of video/audio monitoring in the analysis of motion and treatment effects on night-time seizures – Interventional study

Cited by 6 publications

References 27 publications

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Automatic classification of hyperkinetic, tonic, and tonic-clonic seizures using unsupervised clustering of video signals

Economic aspects of prolonged home video-EEG monitoring: a simulation study

Characteristics of motion signal profiles of tonic–clonic, tonic, hyperkinetic, and motor seizures extracted from nocturnal video recordings

Contact Info

Product

Resources

About