Knowledge-Based Patient Screening for Rare and Emerging Infectious/Parasitic Diseases: A Case Study of Brucellosis and Murine Typhus
1997

Using Decision Support Systems to Diagnose Rare Diseases

Sample size: 296 publication Evidence: moderate

Author Information

Author(s): Craig N. Carter, Norman C. Ronald, James H. Steele, Ed Young, Jeffery P. Taylor, Leon H. Russell, Jr., A. K. Eugster, Joe E. West

Primary Institution: Texas A&M University

Hypothesis

Can a knowledge-based medical decision support system improve the diagnosis of rare infectious and parasitic diseases?

Conclusion

The study shows that using a decision support system significantly reduces the time to diagnose murine typhus and brucellosis.

Supporting Evidence

  • The average time to diagnose brucellosis decreased from 17.9 days to 4.5 days.
  • The average time to diagnose murine typhus decreased from 11.5 days to 8.6 days.
  • In 88% of missed brucellosis cases, the system suggested the correct diagnosis.
  • In 48% of missed murine typhus cases, the system suggested the correct diagnosis.

Takeaway

This study found that a computer program can help doctors quickly figure out if someone has a rare disease, making it easier to treat them.

Methodology

The study analyzed historical records of cases and used a decision support system to suggest diagnoses based on clinical data.

Potential Biases

Potential bias due to reliance on historical records and the nature of the data collected.

Limitations

The study relied on extrapolated data for some cases and did not evaluate the specificity of the system.

Participant Demographics

Cases were from Texas, involving human brucellosis and murine typhus patients from 1980 to 1989.

Statistical Information

P-Value

0.0001

Statistical Significance

p<0.001

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication