Computer-aided diagnosis of renal obstruction: utility of log-linear modeling versus standard ROC and kappa analysis
2011

Evaluating Computer-Aided Diagnosis for Renal Obstruction

Sample size: 185 publication Evidence: high

Author Information

Author(s): Manatunga Amita K, G Binongo José Nilo, Taylor Andrew T

Primary Institution: Emory University

Hypothesis

Is the performance of the CAD tool RENEX equivalent to that of expert readers in diagnosing renal obstruction?

Conclusion

Log-linear modeling showed that RENEX was equivalent to any expert in rating kidneys, particularly in the obstructed and non-obstructed categories.

Supporting Evidence

  • RENEX showed beyond-chance agreement with expert consensus in non-obstructed and obstructed readings.
  • Pairwise agreement between experts and RENEX was not significantly different.
  • The log-linear analysis provided additional evidence that RENEX can assist in interpreting diuresis renography studies.

Takeaway

This study found that a computer program for diagnosing kidney problems works just as well as human experts.

Methodology

Log-linear modeling was used to analyze a database comparing CAD interpretations with expert consensus on kidney scans.

Limitations

The study relied on previously published data and did not have a gold standard for comparison.

Participant Demographics

The study included 95 patients (55 males and 40 females) with a mean age of 58.6 years.

Statistical Information

P-Value

p<0.0001

Statistical Significance

p<0.0001

Digital Object Identifier (DOI)

10.1186/2191-219X-1-5

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication