Artificial neural network (ANN) velocity better identifies benign prostatic hyperplasia but not prostate cancer compared with PSA velocity
2008

Using Artificial Neural Networks to Differentiate Between Prostate Cancer and Benign Prostatic Hyperplasia

Sample size: 199 publication 10 minutes Evidence: moderate

Author Information

Author(s): Stephan Carsten, Büker Nicola, Cammann Henning, Meyer Hellmuth-Alexander, Lein Michael, Jung Klaus

Primary Institution: Charité – Universitätsmedizin Berlin, Germany

Hypothesis

Can an artificial neural network (ANN) improve the differentiation between prostate cancer and benign prostatic hyperplasia compared to PSA velocity alone?

Conclusion

The study found that while PSA velocity has limited usefulness for detecting prostate cancer, the ANN may help reduce unnecessary biopsies in benign prostatic hyperplasia patients.

Supporting Evidence

  • 71% of prostate cancer patients typically have an increasing PSA velocity.
  • The ANN velocity showed stable values in 83% of benign prostatic hyperplasia patients.
  • Using ANN may save 11-17% of unnecessary prostate biopsies in benign prostatic hyperplasia patients.

Takeaway

Doctors used a computer program to help tell the difference between two types of prostate problems, and it might help avoid some unnecessary tests.

Methodology

The study analyzed data from 199 patients with prostate cancer or benign prostatic hyperplasia, using PSA and ANN measurements over time.

Potential Biases

Potential biases may arise from the selection criteria and the reliance on specific PSA assays.

Limitations

The study had a relatively small number of prostate cancer patients and focused on follow-up data.

Participant Demographics

Patients aged 44 to 85 years, with 49 diagnosed with prostate cancer and 150 with benign prostatic hyperplasia.

Statistical Information

P-Value

p<0.0001

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2490-8-10

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication