Abstract | ||
---|---|---|
The incidence of neurodegenerative diseases such as Parkinson's is increasing rapidly around the world, yet the symptoms and pathology of these diseases remain incompletely understood. As a consequence, it is challenging for clinicians to provide patients with accurate diagnoses or prognoses. In this work, we use multi-objective evolutionary algorithms to explore recordings of patients drawing neurological assessment figures, with the aim of identifying patterns of cognitive and motor signals that discriminate different disease states. As a proof of principle, we demonstrate how this approach can be used to explore the trade-off between predicting clinical measures of motor and cognitive deficit. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1145/2908961.2909026 | GECCO (Companion) |
Keywords | Field | DocType |
Multi-objective evolutionary algorithms, Predictive modelling, Parkinson's disease, Polynomial regression | Cognitive deficit,Parkinson's disease,Disease,Evolutionary algorithm,Computer science,Artificial intelligence,Cognition,Machine learning,Medical diagnosis | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marta Vallejo | 1 | 12 | 2.96 |
Jeremy Cosgrove | 2 | 4 | 2.81 |
Jane E. Alty | 3 | 37 | 7.58 |
Stephen L Smith | 4 | 1163 | 83.01 |
David W. Corne | 5 | 2161 | 152.00 |
Michael A. Lones | 6 | 168 | 20.42 |