Toggle Main Menu Toggle Search

Open Access padlockePrints

PD Disease State Assessment in Naturalistic Environments using Deep Learning

Lookup NU author(s): Nils Hammerla, Dr James Fisher, Professor Peter Andras, Professor Lynn Rochester, Rowena Walker, Dr Thomas Ploetz

Downloads


Licence

This is the final published version of a conference proceedings (inc. abstract) that has been published in its final definitive form by Association for the Advancement of Artificial Intelligence, 2015.

For re-use rights please refer to the publisher's terms and conditions.


Abstract

Management of Parkinson’s Disease (PD) could be improved significantly if reliable, objective information about fluctuations in disease severity can be obtained in ecologically valid surroundings such as the private home. Although automatic assessment in PD has been studied extensively, so far no approach has been devised that is useful for clinical practice. Analysis approaches common for the field lack the capability of exploiting data from realistic environments, which represents a major barrier towards practical assessment systems. The very unreliable and infrequent labelling of ambiguous, low resolution movement data collected in such environments represents a very challenging analysis setting, where advances would have significant societal impact in our ageing population. In this work we propose an assessment system that abides practical usability constraints and applies deep learning to differentiate disease state in data collected in naturalistic settings. Based on a large data-set collected from 34 people with PD we illustrate that deep learning outperforms other approaches in generalisation performance, despite the un- reliable labelling characteristic for this problem setting, and how such systems could improve current clinical practice.Introduction


Publication metadata

Author(s): Hammerla N, Fisher J, Andras P, Rochester L, Walker R, Ploetz T

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: Twenty-ninth AAAI Conference on Artificial Intelligence (AAAI-2015)

Year of Conference: 2015

Print publication date: 01/06/2015

Acceptance date: 01/01/1900

Date deposited: 12/02/2015

Publisher: Association for the Advancement of Artificial Intelligence

URL: https://aaai.org/Press/Proceedings/aaai15.php

Sponsor(s): Association for the Advancement of Artificial Intelligence


Share