Alzheimer’s disease assessments optimised for diagnostic accuracy and administration time

Niamh McCombe, Xuemei Ding, Girijesh Prasad, Paddy Gillespie, David Finn, Stephen Todd, Paula McClean, KongFatt Wong-Lin

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)
90 Downloads (Pure)

Abstract

Objective: Despite the potential of machine learning techniques to improve dementia diagnostic processes, research outcomes are often not readily translated to or adopted in clinical practice. Importantly, the time taken to administer diagnostic assessment has yet to be taken into account in feature-selection based optimisation for dementia diagnosis. We address these issues by considering the impact of assessment time as a practical constraint for feature selection of cognitive and functional assessments in Alzheimer’s disease diagnosis.

Methods: We use three different feature selection algorithms to select informative subsets of dementia assessment items from a large open-source dementia dataset. We use cost-sensitive feature selection to optimise our feature selection results for assessment time as well as diagnostic accuracy. To encourage clinical adoption and further evaluation of our proposed accuracy-vs-cost optimisation algorithms, we also implement a sandbox-like toolbox with graphical user interface to evaluate user-chosen subsets of assessment items.

Results: We find that there are subsets of accuracy-cost optimised assessment items that can perform better in terms of diagnostic accuracy and/or total assessment time than most other standard assessments.

Discussion: Overall, our analysis and accompanying sandbox tool can facilitate clinical users and other stakeholders to apply their own domain knowledge to analyse and decide which dementia diagnostic assessment items are useful, and aid the redesigning of dementia diagnostic assessments.

Clinical Impact (Clinical Research): By optimising diagnostic accuracy and assessment time, we redesign predictive and efficient dementia diagnostic assessments and develop a sandbox interface to facilitate evaluation and testing by clinicians and non-specialists.
Original languageEnglish
Article number4900809
Pages (from-to)4900809
Number of pages9
JournalIEEE Journal of Translational Engineering in Health and Medicine
Volume10
Early online date5 Apr 2022
DOIs
Publication statusPublished (in print/issue) - 5 Apr 2022

Bibliographical note

Funding Information:
This work was supported in part by the European Union's Interreg VA Program through the Special European Union (EU) Programmes Body-SEUPB (Centre for Personalised Medicine, IVA 5036), in part by the Alzheimer's Disease Neuroimaging Initiative (ADNI) through the National Institutes of Health under Grant U01 AG024904, and in part by the Department of Defense (DOD) ADNI under Award W81XWH-12-2-0012. The work of Xuemei Ding, Stephen Todd, Paula L. Mcclean, and Kongfatt Wong-Lin was supported in part by the Alzheimer's Research U.K. (ARUK) Northern Ireland (NI) Pump Priming and in part by the Ulster University Research Challenge Fund

Publisher Copyright:
© 2013 IEEE.

Keywords

  • Feature extraction
  • Alzheimer disease
  • Costs
  • Machine Learning
  • Prediction algorithms
  • optimization
  • graphical user interface

Fingerprint

Dive into the research topics of 'Alzheimer’s disease assessments optimised for diagnostic accuracy and administration time'. Together they form a unique fingerprint.

Cite this