ESMAC BEST PAPER 2017
| Autor: | Michael H. Schwartz, Meghan E. Munger |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
030506 rehabilitation
business.industry Computer science Rehabilitation Biophysics Gross Motor Function Classification System Machine learning computer.software_genre Random forest 03 medical and health sciences Broad spectrum 0302 clinical medicine Functional abilities Orthopedics and Sports Medicine Functional ability Artificial intelligence 0305 other medical science business True positive rate computer Classifier (UML) 030217 neurology & neurosurgery |
| Zdroj: | Gait & Posture. 63:290-295 |
| ISSN: | 0966-6362 |
| DOI: | 10.1016/j.gaitpost.2018.04.017 |
| Popis: | We used the random forest classifier to predict Gross Motor Function Classification System (GMFCS) levels I-IV from patient reported abilities recorded on the Gillette Functional Assessment Questionnaire (FAQ). The classifier exhibited outstanding accuracy across GMFCS levels I-IV, with 83%-91% true positive rate (TPR), area under the receiver operation characteristic (ROC) curve greater than 0.96 for all levels, and misclassification by more than one level only occurring 1.2% of the time. This new approach to GMFCS level assignment overcomes several difficulties with the current method: (i) it is based on a broad spectrum of functional abilities, (ii) it resolves functional ability profiles that conflict with existing GMFCS level definitions, (iii) it is based entirely on self-reported abilities, and (iv) it removes complex age dependence. Further work is needed to examine inter-center differences in classifier performance-which would most likely reflect interpretive differences in GMFCS level definitions between centers. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect