Modeling Large Sparse Data for Feature Selection: Hospital Admission Predictions of the Dementia Patients Using Primary Care Electronic Health Records
- Submitting institution
-
Swansea University / Prifysgol Abertawe
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 55654
- Type
- D - Journal article
- DOI
-
10.1109/jtehm.2020.3040236
- Title of journal
- IEEE Journal of Translational Engineering in Health and Medicine
- Article number
- -
- First page
- 1
- Volume
- 9
- Issue
- -
- ISSN
- 2168-2372
- Open access status
- Compliant
- Month of publication
- November
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
https://saildatabank.com
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
-
- Research group(s)
-
-
- Citation count
- 0
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Predicting hospitalisation and mining risk factors for dementia patients have a material impact on NHS resource management and proactive patient care. Over-65s with dementia are using up to one quarter of hospital beds at any one time. There is an urgent need to improve post-diagnostic care. We propose a novel machine learning methodology that produces high predictive performance whilst enabling an interpretable heuristic analysis. This is the first large scale study with the initial findings published in The Lancet (Vol 392:S9). The work is cross validated on over 59K patients with a total of 52.5M medical events.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -