The early warning paradox
Machine learning models in healthcare aim to predict critical outcomes but often overlook existing Early Warning Systems’ impact. Using data from King’s College Hospital, we demonstrate how current evaluation methods can lead to paradoxical results. We discuss challenges in developing ML models from...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-02-01
|
| Series: | npj Digital Medicine |
| Online Access: | https://doi.org/10.1038/s41746-024-01408-x |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823861606649430016 |
|---|---|
| author | Hugh Logan Ellis Edward Palmer James T. Teo Martin Whyte Kenneth Rockwood Zina Ibrahim |
| author_facet | Hugh Logan Ellis Edward Palmer James T. Teo Martin Whyte Kenneth Rockwood Zina Ibrahim |
| author_sort | Hugh Logan Ellis |
| collection | DOAJ |
| description | Machine learning models in healthcare aim to predict critical outcomes but often overlook existing Early Warning Systems’ impact. Using data from King’s College Hospital, we demonstrate how current evaluation methods can lead to paradoxical results. We discuss challenges in developing ML models from retrospective data and propose a novel approach focused on identifying when patients enter a ‘risk state’ through latent health representations, potentially transforming clinical decision-making. |
| format | Article |
| id | doaj-art-f18ce6de300947509efb06babf9509a8 |
| institution | Kabale University |
| issn | 2398-6352 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Digital Medicine |
| spelling | doaj-art-f18ce6de300947509efb06babf9509a82025-02-09T12:55:38ZengNature Portfolionpj Digital Medicine2398-63522025-02-01811210.1038/s41746-024-01408-xThe early warning paradoxHugh Logan Ellis0Edward Palmer1James T. Teo2Martin Whyte3Kenneth Rockwood4Zina Ibrahim5King’s College LondonInstitute of Health InformaticsKing’s College Hospital NHS Foundation TrustUniversity of SurreyDalhousie UniversityKing’s College LondonMachine learning models in healthcare aim to predict critical outcomes but often overlook existing Early Warning Systems’ impact. Using data from King’s College Hospital, we demonstrate how current evaluation methods can lead to paradoxical results. We discuss challenges in developing ML models from retrospective data and propose a novel approach focused on identifying when patients enter a ‘risk state’ through latent health representations, potentially transforming clinical decision-making.https://doi.org/10.1038/s41746-024-01408-x |
| spellingShingle | Hugh Logan Ellis Edward Palmer James T. Teo Martin Whyte Kenneth Rockwood Zina Ibrahim The early warning paradox npj Digital Medicine |
| title | The early warning paradox |
| title_full | The early warning paradox |
| title_fullStr | The early warning paradox |
| title_full_unstemmed | The early warning paradox |
| title_short | The early warning paradox |
| title_sort | early warning paradox |
| url | https://doi.org/10.1038/s41746-024-01408-x |
| work_keys_str_mv | AT hughloganellis theearlywarningparadox AT edwardpalmer theearlywarningparadox AT jamestteo theearlywarningparadox AT martinwhyte theearlywarningparadox AT kennethrockwood theearlywarningparadox AT zinaibrahim theearlywarningparadox AT hughloganellis earlywarningparadox AT edwardpalmer earlywarningparadox AT jamestteo earlywarningparadox AT martinwhyte earlywarningparadox AT kennethrockwood earlywarningparadox AT zinaibrahim earlywarningparadox |