A genetic programming approach to development of clinical prediction models: a case study in symptomatic cardiovascular disease
- Submitting institution
-
Cardiff University / Prifysgol Caerdydd
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 96673006
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0202685
- Title of journal
- PLoS ONE
- Article number
- e0202685
- First page
- -
- Volume
- 13
- Issue
- 9
- ISSN
- 1932-6203
- Open access status
- Compliant
- Month of publication
- September
- Year of publication
- 2018
- URL
-
https://doi.org/10.1371/journal.pone.0202685
- 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
-
4
- Research group(s)
-
A - Artificial intelligence and data analytics
- Citation count
- 2
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- The novelty of this work is in demonstrating the utility of genetic programming for the automated development of clinical prediction models for diagnostic and prognostic purposes. The research addresses an unmet clinical need demonstrated by our earlier work where we show the principal glycaemic parameter promoted by the UK Prospective Diabetes Study (UKPDS) to be completely uncorrelated to health outcomes in a representative sample of primary care patients (https://doi.org/10.2337/dc13-1159). This work was featured in an article on Phys.Org (https://phys.org/news/2019-01-artificial-intelligence-patient-nhs.html)
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -