Deep Learning for Freezing of Gait Assessment using Inertial Measurement Units: A Multicentre Study
Yang, P.-K.; Carlon, J.; Goris, M.; Klaver, E.; Nonnekes, J.; van Wezel, R. J. A.; Alcock, L.; Yarnall, A. J.; Rochester, L.; Hansen, C.; Schlenstedt, C.; Maetzler, W.; Buzaglo, D.; Brozgol, M.; Hausdorff, J. M.; Nieuwboer, A.; Gilat, M.; Ginis, P.; Vanrumste, B.; Filtjens, B.
Show abstract
Video annotation is the gold-standard method to assess Freezing of Gait (FOG) in Parkinsonian disorders, but it is time-consuming. Deep learning (DL)-based assessment of FOG using inertial measurement units ameliorates these problems but poses challenges. Particularly, the large heterogeneity between patients and assessment methods potentially affects detection performance between independent cohorts. To evaluate heterogeneity effects, we developed a DL model on a local cohort (85 participants; 2043 trials) and validated it across six external cohorts (256 participants; 1058 trials). Model-expert agreement on the percentage-of-time-frozen was strong locally (ICC=0.886 [0.79,0.90]) but reduced in external cohorts (ICC=0.562{+/-}0.141). Fine-tuning the DL model with just 50 minutes of external cohort data improved the ICC to 0.732{+/-}0.138, falling within the borderline of the inter-rater agreement (ICC=0.73-0.99). Therefore, while unified standards are still being developed, we propose an expert-in-the-loop workflow as an effective intermediary and present a proof-of-concept web-based platform for fine-tuning and expert review (aidfog.be).
Matching journals
The top 2 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Machine-Learning Based Objective Measure for ALS Disease Severity 95%
- Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge 94%
- Quantifying Device Type and Handedness Biases in a Remote Parkinson’s Disease AI-Powered Assessment 93%
Similar papers in this journal
- An explainable spatial-temporal graphical convolutional network to score freezing of gait in parkinsonian patients 95%
- Motor signatures in digitized cognitive and memory tests enhances characterization of Parkinson’s disease 91%
- Development of a Tremor Detection Algorithm for use in an Academic Movement Disorders Center 91%
Similar papers in this journal
- Playing the piano with a robotic third thumb: Assessing constraints of human augmentation 92%
- An Open-Source Tool for Automated Human-Level Circling Behavior Detection 92%
- An infection prediction model developed from inpatient data can predict out-of-hospital COVID-19 infections from wearable data when controlled for dataset shift 92%
Similar papers in this journal
- Investigating Age-Related Decline in Sensorimotor Control Using Robotic Tasks 90%
- Dropout in Neural Networks Simulates theParadoxical Effects of Deep Brain Stimulation onMemory 89%
- Extended Effects of a Wearable Sensory Prosthesis on Gait, Balance Function and Falls After 26 Weeks of Use in Persons with Peripheral Neuropathy and High Fall Risk – The walk2Wellness Trial 88%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.