Optimizing intensive care capacity using individual length-of-stay prediction models
2007

Predicting ICU Length of Stay for Oesophagectomy Patients

Sample size: 583 publication 10 minutes Evidence: moderate

Author Information

Author(s): Mark Van Houdenhoven, Duy-Tien Nguyen, Marinus J. Eijkemans, Ewout W. Steyerberg, Hugo W. Tilanus, Diederik Gommers, Gerhard Wullink, Jan Bakker, Geert Kazemier

Primary Institution: Erasmus University Medical Center

Hypothesis

Can individual patient characteristics be used to accurately predict length of stay in the ICU for patients undergoing oesophagectomy?

Conclusion

Using patient characteristics to predict ICU length of stay can lead to more efficient use of ICU beds and fewer cancellations of surgical procedures.

Supporting Evidence

  • The intra-ICU model had an r2 of 45% after internal validation.
  • Using the model reduced the deficit number of ICU days by 65.
  • 15% of cancelled procedures could have been prevented with the model.

Takeaway

Doctors can use information about patients to guess how long they'll need to stay in the ICU, which helps make sure there are enough beds for everyone.

Methodology

Retrospective data from 518 patients were analyzed to create predictive models for ICU length of stay, validated with a second cohort of 65 patients.

Potential Biases

Potential biases may arise from the retrospective nature of the data collection and the specific patient population studied.

Limitations

The study was conducted at a single center, which may limit the generalizability of the results.

Participant Demographics

Patients undergoing elective oesophagectomy for carcinoma, with a mean age of 63 years.

Statistical Information

P-Value

p<0.001

Confidence Interval

0.5 to 2.5

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/cc5730

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication