Multiple-Instance Learning for In-The-Wild Parkinsonian Tremor Detection.
Annu Int Conf IEEE Eng Med Biol Soc
; 2019: 6188-6191, 2019 Jul.
Article
en En
| MEDLINE
| ID: mdl-31947256
Parkinson's Disease (PD) is a neurodegenerative disorder that manifests through slowly progressing symptoms, such as tremor, voice degradation and bradykinesia. Automated detection of such symptoms has recently received much attention by the research community, owing to the clinical benefits associated with the early diagnosis of the disease. Unfortunately, most of the approaches proposed so far, operate under a strictly laboratory setting, thus limiting their potential applicability in real world conditions. In this work, we present a method for automatically detecting tremorous episodes related to PD, based on acceleration signals. We propose to address the problem at hand, as a case of Multiple-Instance Learning, wherein a subject is represented as an unordered bag of signal segments and a single, expert-provided, ground-truth. We employ a deep learning approach that combines feature learning and a learnable pooling stage and is trainable end-to-end. Results on a newly introduced dataset of accelerometer signals collected in-the-wild confirm the validity of the proposed approach.
Texto completo:
1
Colección:
01-internacional
Base de datos:
MEDLINE
Asunto principal:
Enfermedad de Parkinson
/
Temblor
/
Acelerometría
/
Aprendizaje Automático
Tipo de estudio:
Diagnostic_studies
/
Screening_studies
Límite:
Humans
Idioma:
En
Revista:
Annu Int Conf IEEE Eng Med Biol Soc
Año:
2019
Tipo del documento:
Article
Pais de publicación:
Estados Unidos