DESIRE at Erasmus MC
DESIRE predicts on day two after surgery whether a patient can safely be discharged home or to a nursing facility, in order to shorten length of stay.
- What this means:
- A curator has read the source and confirmed our reading of it — the classifications that let this record be compared with others — along with the AI product and the clinical use. That is a check of our work, not a judgement on the AI.
- What would change it:
- The pair enters the AIH factory, where clinical, technical and governance findings are worked section by section.
- Who established it:
- A named AIH Lab reviewer read the source and settled our reading of it — the classifications that make this record comparable with others, which no public source provides. This is an independent check.
- Submitted
- 2Curated
- 3Maturing
- 4Validated
- 5Scaled
Plain-language summary
AIChoose an audience and generate a tailored summary on demand. The AI uses only what is on this page.
- Clinical problem
- Predict a future risk
- Point of care
- Follow-up
- Nature of AI output
- A risk score
- Clinical specialty
- Surgery
- Care setting
- Hospital — inpatient
- Patient population
- Not specified in source (hospital harvest)
- Intended use
- DESIRE predicts on day two after surgery whether a patient can safely be discharged home or to a nursing facility, in order to shorten length of stay.
Full study description
Live pilot on real gastro-enterological and oncological surgery patients over a four-month evaluation period. Decision support only - the discharge decision remains with doctors and nurses. Erasmus MC quotes potential savings of "260 opnamedagen" per year on one ward and a reduction from an average stay "van vijf dagen"; these are the hospital own projections, not our measurement, and are not written to any structured metric field. IN-HOUSE model, no external vendor named, so Erasmus MC is recorded as its own vendor organisation. Modelling technique is not stated in the source; recorded as classical_ml without claiming deep learning.
- AI technique
- Classical machine learning
- Input data
- Structured EHR data
- Output type
- Risk score
- Autonomy level
- Informs a human (advisory)
- Model provenance
- Built in-house
- Status
- Pilot
- Country
- Netherlands
- Deployment date
- 1 January 2022
- Data identifiability
- Not stated in the source
Similar deployments
AIContributors
- Deploying organisation
- Erasmus MC · Hospital / health system · Netherlands
- AI vendor
- Erasmus MC · Netherlands
- Product name
- DESIRE
- Source record
- amazingerasmusmc.nl · hh-erasmusmc-desire