Application of Data Mining to Intensive Care Unit Microbiologic Data
1999

Data Mining for Hospital Infection Control

Sample size: 1 publication Evidence: moderate

Author Information

Author(s): Stephen A. Moser, Warren T. Jones, Stephen E. Brossette

Primary Institution: University of Alabama at Birmingham

Hypothesis

Can a new data mining process identify unexpected patterns in hospital infection control data?

Conclusion

The Data Mining Surveillance System (DMSS) can identify previously unknown patterns in infection control data.

Supporting Evidence

  • DMSS can identify potentially interesting and previously unknown patterns in infection control data.
  • Statistical tests were used to compare incidence proportions over time.
  • Templates were used to filter out uninteresting association rules.

Takeaway

Researchers created a system that helps hospitals find hidden patterns in infection data, which can help them control infections better.

Methodology

The study used a data mining process to analyze infection control data from the University of Alabama at Birmingham Hospital.

Limitations

Future work is needed to determine the usefulness of DMSS in clinical studies and to improve user interface and data handling.

Participant Demographics

Data was extracted from patients in intensive care units at the University of Alabama at Birmingham Hospital.

Statistical Information

P-Value

0.01

Statistical Significance

p<0.01

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication