Predicting hospital mortality for ICU patients: time series analysis
- Submitting institution
-
University of Portsmouth
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 7157637
- Type
- D - Journal article
- DOI
-
10.1177/1460458219850323
- Title of journal
- Health Informatics Journal
- Article number
- -
- First page
- 1043
- Volume
- 26
- Issue
- 2
- ISSN
- 1460-4582
- Open access status
- Compliant
- Month of publication
- July
- Year of publication
- 2019
- URL
-
-
- 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 - Centre for Healthcare Modelling and Informatics
- Citation count
- 4
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- A result of collaboration between teams from the University of Portsmouth and Portsmouth Hospitals University NHS Trust. The study was conducted on one of the largest Intensive Care Unit (ICU) research datasets. By using machine-learning strategies for missing data, the paper shows that ICUs may have sufficient data to predict the patient's outcome within 6 hours of admission rather than the conventional 48 hours. This may result in a change of practice regarding patient prioritisation in ICUs.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -