Öppna denna publikation i ny flik eller fönster >>Pediatric Neurosurgery Department, CCMR Neurogenetique, European Reference Network Brainteam Member, Rothschild Foundation Hospital, Paris, France.
Service of Neurology, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland.
Service of Neurology, Department of Clinical Neurosciences, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland.
Department of Neurology, University Hospital of Strasbourg, Strasbourg, France; Strasbourg Neuroscience Institute, Strasbourg University, Strasbourg, France; Institute of Genetics and Cellular and Molecular Biology, INSERM-U964, CNRS-UMR7104, University of Strasbourg, Illkirch-Graffenstaden, France.
Umeå universitet, Medicinska fakulteten, Institutionen för klinisk vetenskap, Neurovetenskaper.
Department of Neurology, CHU Montpellier, Montpellier, France.
Department of Neurology, CHU Montpellier, Montpellier, France.
Institut du Neurone, Montferrier sur Lez, France; Department of Neurosurgery, Military University Hospital of Sfax, Sfax, Tunisia.
Edinburgh Medical School, University of Edinburgh, Scotland, Edinburgh, United Kingdom.
Institute for Medical Engineering and Medical Informatics, School of Life Sciences, University of Applied Sciences and Arts Northwestern Switzerland, Muttenz, Switzerland.
Institut du Neurone, Montferrier sur Lez, France.
NeuroRestore, Ecole Polytechnique Fédérale de Lausanne, University Hospital Lausanne, University of Lausanne, Lausanne, Switzerland; Neuro-X Institute, Ecole Polytechnique Fédérale de Lausanne, Geneva, Switzerland.
NeuroRestore, Ecole Polytechnique Fédérale de Lausanne, University Hospital Lausanne, University of Lausanne, Lausanne, Switzerland; Department of Neurosurgery, Lausanne University Hospital (CHUV), University of Lausanne (UNIL), Lausanne, Switzerland.
Institut du Neurone, Montferrier sur Lez, France.
Visa övriga...
2026 (Engelska)Ingår i: Annals of Clinical and Translational Neurology, E-ISSN 2328-9503Artikel i tidskrift (Refereegranskat) Epub ahead of print
Abstract [en]
Objective: To explore whether routine outpatient video combined with deep learning-based pose estimation and clinically interpretable kinematic features can support multi-label phenotyping of co-occurring hyperkinetic movement disorders (HMDs).
Methods: In this exploratory single-centre proof-of-concept study, videos from 21 patients with HMDs and 4 healthy controls were processed with markerless pose estimation (YOLOv8) and 2-dimensional keypoint trajectories transformed into kinematic descriptors spanning statistical, temporal, spectral, and complexity domains. Ten-second windows were aligned to expert annotations for eight hyperkinetic phenomenologies. Conventional supervised classifiers were trained on these tabular descriptors. Window-level predictions were aggregated to the patient level, and label-specific thresholds were tuned on training participants only.
Results: In patient-level multi-label performance reporting, (i) the best single pipeline selected by discrimination (StandardScaler + MLP) achieved a macro-AUPRC of 0.821 ± 0.019 and a macro–receiver operating characteristic area under the curve of 0.830 ± 0.029. (ii) The best single pipeline selected by Hamming accuracy (MinMaxScaler + SVM) reached 0.764 ± 0.041. (iii) Under prespecified nested cross-validation with per-label model selection within training folds (primary analysis), macro-AUPRC was 0.717 ± 0.030, macro-AUROC was 0.767 ± 0.069, Hamming accuracy was 0.764 ± 0.014 and patient–label agreement was 153/200 (76.5%). (iv) Post hoc per-label selection of the best-performing pipeline defined an exploratory upper bound of 172/200 (86.0%).
Interpretation: In this exploratory study, a hybrid pipeline combining deep learning pose estimation with feature-engineered supervised classification produced encouraging patient-level multi-label performance for co-occurring HMDs. These findings are proof-of-concept; external, multicentre, prospective validation is required before clinical or trial use.
Ort, förlag, år, upplaga, sidor
John Wiley & Sons, 2026
Nyckelord
co-occurring, deep learning, hyperkinetic movement disorders, phenotyping, pose estimation
Nationell ämneskategori
Neurologi
Identifikatorer
urn:nbn:se:umu:diva-257268 (URN)10.1002/acn3.70474 (DOI)001829673400001 ()42501059 (PubMedID)2-s2.0-105045677058 (Scopus ID)
2026-08-112026-08-112026-08-11