Multi-classifier prediction of knee osteoarthritis progression from incomplete imbalanced longitudinal data
- Submitting institution
-
University of Newcastle upon Tyne
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 266764-176193-1292
- Type
- D - Journal article
- DOI
-
10.1038/s41598-020-64643-8
- Title of journal
- Scientific Reports
- Article number
- 8427
- First page
- -
- Volume
- 10
- Issue
- -
- ISSN
- 2045-2322
- Open access status
- Compliant
- Month of publication
- May
- Year of publication
- 2020
- URL
-
https://doi.org/10.1038/s41598-020-64643-8
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
9
- Research group(s)
-
B - Interdisciplinary Computing and Complex Biosystems (ICOS)
- Citation count
- 5
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Crucial for the design of clinical studies is the definition of their inclusion criteria, traditionally specified as hand-crafted rules. Suboptimal criteria lead to the inclusion of uninteresting participants that can distort the outcomes of the study. In this paper we design and evaluate machine learning pipelines for the prediction of Osteoarthitis disease progression, as the core of an automated patient ranking system for clinical studies recruitment. Simulations based on historical data show that our approach is superior to the inclusion criteria designed by clinical experts. This methodology was used for the recruitment of the €15M EU-funded APPROACH clinical study.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -