Prediction of early unplanned intensive care unit readmission in a UK tertiary-care hospital: A cross-sectional machine learning approach
MetadataShow full item record
Desautels, T., Das, R., Calvert, J., Trivedi, M., Summers, C., Wales, D., & Ercole, A. (2017). Prediction of early unplanned intensive care unit readmission in a UK tertiary-care hospital: A cross-sectional machine learning approach. BMJ Open, 7 (9. e017199) https://doi.org/10.1136/bmjopen-2017-017199
Objectives: Unplanned readmissions to the intensive care unit (ICU) are highly undesirable, increasing variance in care, making resource planning difficult, and potentially increasing length of stay and mortality in some settings. Identifying patients who are likely to suffer unplanned ICU readmission could reduce the frequency of this adverse event. Setting: A single academic, tertiary care hospital in the United Kingdom. Participants: A set of 3,326 ICU episodes collected between October 2014 and August 2016. All records were of patients who visited an ICU at some point during their stay. We excluded patients who: were ≤ 16 years of age; visited intensive care units other than the general and neurosciences ICU; were missing crucial electronic patient record measurements; or had indeterminate ICU discharge outcomes or very early or extremely late discharge times. After exclusion, 2,018 outcome-labeled episodes remained. Primary and Secondary Outcome Measures: Area under the receiver operating characteristic curve (AUROC) for prediction of unplanned ICU readmission or in-hospital death within 48 hours of first ICU discharge. Results: In ten-fold cross-validation, an ensemble predictor was trained on data from both the target hospital and the MIMIC-III database and tested on the target hospital’s data. This predictor discriminated between patients with the unplanned ICU readmission or death outcome and those without this outcome, attaining mean AUROC of 0.7095 (SE 0.0260), superior to the purpose-built SWIFT score (AUROC = 0.6082, SE 0.0249; p = 0.014, pairwise t-test). Conclusions: Despite the inherent difficulties, we demonstrate that a novel ML algorithm based on transfer learning could achieve good discrimination, over and above that of the treating clinicians or the value added by the SWIFT score. Accurate prediction of unplanned readmission could be used to target resources more efficiently.
esearch reported in this publication was supported by the National Institute of Nursing Research, of the National Institutes of Health, under award number R43NR015945.
Embargo Lift Date
External DOI: https://doi.org/10.1136/bmjopen-2017-017199
This record's URL: https://www.repository.cam.ac.uk/handle/1810/269905
Attribution-NonCommercial 4.0 International, Attribution-NonCommercial 4.0 International