Development and Prospective Validation of a Pathology-Based Artificial Intelligence Model for Predicting the Time to Castration Resistance of Prostate Cancer

Condition(s) studied

Investigational drug(s) / intervention(s)

Artificial intelligence (AI)-based predictive model (developed): Collect pathological slides of prostate biopsy of the enrolled patients. Digitise these slides into whole-slide images (WSIs). Analyze the WSIs using the AI model to generate predictive results (within 12 months, between 12 to 24months or over 24 months). No intervention to patients would be performed in this predictive test study.

Study summary

The goal of this predictive test is to prospectively test the performance of pre-developed artificial intelligence (AI) predictive model for predicting the time to castration resistance of prostate cancer. Investigators had developed this AI model based on deep learning algorithms in preliminary research, and it performed well in retrospective tests.

Eligibility

Primary outcome measure(s)

• C-index (Concordance Index) — For each enrolled patient, the predictive results of AI model will be obtained in not long after prostate biopsy, and the C-index of the AI model will be evaluated through study completion, an average of 3 year.
  The proportion of all patient pairs in which the predicted outcome order matches the actual outcome order. It estimates the probability that the predicted results are consistent with the observed outcomes.

Trial sites (1)

More Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University trials in China

Other trials for the same condition