Gaussian process regression in vital-sign early warning systems.
The current standard of clinical practice for patient monitoring in most developed nations is connection of patients to vital-sign monitors, combined with frequent manual observation. In some nations, such as the UK, manual early warning score (EWS) systems have been mandated for use, in which score...
| Main Authors: | , , , , |
|---|---|
| Format: | Journal article |
| Language: | English |
| Published: |
2012
|
| _version_ | 1826274086388498432 |
|---|---|
| author | Clifton, L Clifton, D Pimentel, M Watkinson, P Tarassenko, L |
| author_facet | Clifton, L Clifton, D Pimentel, M Watkinson, P Tarassenko, L |
| author_sort | Clifton, L |
| collection | OXFORD |
| description | The current standard of clinical practice for patient monitoring in most developed nations is connection of patients to vital-sign monitors, combined with frequent manual observation. In some nations, such as the UK, manual early warning score (EWS) systems have been mandated for use, in which scores are assigned to the manual observations, and care escalated if the scores exceed some pre-defined threshold. We argue that this manual system is far from ideal, and can be improved using machine learning techniques. We propose a system based on Gaussian process regression for improving the efficacy of existing EWS systems, and then demonstrate the method using manual observation of vital signs from a large-scale clinical study. |
| first_indexed | 2024-03-06T22:38:06Z |
| format | Journal article |
| id | oxford-uuid:5a9d8448-fe34-4e3a-adbd-5c5b3cf2ab2c |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-06T22:38:06Z |
| publishDate | 2012 |
| record_format | dspace |
| spelling | oxford-uuid:5a9d8448-fe34-4e3a-adbd-5c5b3cf2ab2c2022-03-26T17:16:49ZGaussian process regression in vital-sign early warning systems.Journal articlehttp://purl.org/coar/resource_type/c_dcae04bcuuid:5a9d8448-fe34-4e3a-adbd-5c5b3cf2ab2cEnglishSymplectic Elements at Oxford2012Clifton, LClifton, DPimentel, MWatkinson, PTarassenko, LThe current standard of clinical practice for patient monitoring in most developed nations is connection of patients to vital-sign monitors, combined with frequent manual observation. In some nations, such as the UK, manual early warning score (EWS) systems have been mandated for use, in which scores are assigned to the manual observations, and care escalated if the scores exceed some pre-defined threshold. We argue that this manual system is far from ideal, and can be improved using machine learning techniques. We propose a system based on Gaussian process regression for improving the efficacy of existing EWS systems, and then demonstrate the method using manual observation of vital signs from a large-scale clinical study. |
| spellingShingle | Clifton, L Clifton, D Pimentel, M Watkinson, P Tarassenko, L Gaussian process regression in vital-sign early warning systems. |
| title | Gaussian process regression in vital-sign early warning systems. |
| title_full | Gaussian process regression in vital-sign early warning systems. |
| title_fullStr | Gaussian process regression in vital-sign early warning systems. |
| title_full_unstemmed | Gaussian process regression in vital-sign early warning systems. |
| title_short | Gaussian process regression in vital-sign early warning systems. |
| title_sort | gaussian process regression in vital sign early warning systems |
| work_keys_str_mv | AT cliftonl gaussianprocessregressioninvitalsignearlywarningsystems AT cliftond gaussianprocessregressioninvitalsignearlywarningsystems AT pimentelm gaussianprocessregressioninvitalsignearlywarningsystems AT watkinsonp gaussianprocessregressioninvitalsignearlywarningsystems AT tarassenkol gaussianprocessregressioninvitalsignearlywarningsystems |