An interventional study of Artificial Intelligence-Based Digital Pathology Assessment in Prostate Cancer and mCRPC (Metastatic Castration-resistant Prostate Cancer), sponsored by Xiangya Hospital of Central South University. Active, not recruiting at 1 site in China. Open to male participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-11-09.
Sponsored by Xiangya Hospital of Central South University · Not applicable, Interventional, and Other
The goal of this multicenter observational study is to develop and validate an artificial intelligence-based digital pathology model to predict treatment response and prognosis in adult men with metastatic hormone-sensitive prostate cancer treated with androgen deprivation therapy plus androgen receptor signaling inhibitors.
The main questions it aims to answer are:
Can digital pathology-based artificial intelligence predict deep prostate-specific antigen response, defined as prostate-specific antigen less than 0.2 ng/mL at 6 to 7 months after treatment? Can digital pathology-based artificial intelligence predict progression to metastatic castration-resistant prostate cancer and time to metastatic castration-resistant prostate cancer? Researchers will compare artificial intelligence-defined low-risk and high-risk groups to evaluate whether the model can improve prediction of treatment response and prognosis beyond conventional clinicopathological risk stratification.
Participants will not receive any additional intervention as part of this study. Researchers will retrospectively collect clinical characteristics, treatment records, prostate-specific antigen response data, follow-up outcomes, and archived prostate biopsy slides from participating centers. The biopsy slides will be scanned into whole-slide images and analyzed using artificial intelligence to develop and validate predictive models.
7,046 studies on the registry are indexed under Prostatic Neoplasms; 1,580 are open to participants now.
This study's planned enrollment of 1,115 is above the median of 60 across 5,348 interventional studies indexed under Prostatic Neoplasms.
Browse Prostatic Neoplasms studies →Xiangya Hospital of Central South University is the lead sponsor of 174 studies on the registry; 77 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Go through the criteria one by one — yes, no or not sure — and take the list to your doctor or the study team. Kept in this browser only.
Exclusion Criteria:
Incomplete follow-up information, including inability to determine the date of progression to castration-resistant prostate cancer or lack of adequate follow-up data for outcome assessment.
-Receipt of additional systemic therapies that may substantially affect prostate-specific antigen levels during the treatment course, such as poly adenosine diphosphate-ribose polymerase inhibitors, unless such therapies were initiated after the defined outcome assessment period or after progression.
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
The diagnosis was confirmed by looking at a sample under a microscope: tissue from a biopsy or surgery (histology), or cells from a fluid or needle sample (cytology).
Your pathology report is the document that shows this.
Cancer that has spread from where it began to other parts of the body. “Metastatic” cancer is cancer that has spread this way.
A line of therapy is one course of treatment, which may combine several drugs. First-line is the first course given; second-line follows when that stops working or is not tolerated.
“Two prior lines” means two courses that count separately under the study’s rules — not simply two drugs. Ask the study team if you are unsure how yours are counted.
A biopsy takes a small piece of tissue to examine. “Archival tissue” is a sample already taken, for example at diagnosis, and kept by the hospital.
Whether a stored sample will do depends on when it was taken, how much there is and what the study needs. Ask whether the study accepts your stored sample or needs a new biopsy.
A scale of how much an illness limits everyday activity. For people being assessed to join a study, scores run from 0 (fully active) to 4; lower is more active.
Studies most often ask for 0–1 or 0–2. Your doctor gives the score; the WHO scale uses the same steps. The full scale also has 5, which records death.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Malignancy means cancer. Criteria about another or earlier malignancy ask whether you have had a different cancer, usually within a set number of years.
Some are commonly allowed, such as treated skin cancers other than melanoma and early cancers removed completely — check the exceptions this study lists.
Histologically or cytologically confirmed
The diagnosis was confirmed by looking at a sample under a microscope: tissue from a biopsy or surgery (histology), or cells from a fluid or needle sample (cytology).
Your pathology report is the document that shows this.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Metastases
Cancer that has spread from where it began to other parts of the body. “Metastatic” cancer is cancer that has spread this way.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Line of therapy
A line of therapy is one course of treatment, which may combine several drugs. First-line is the first course given; second-line follows when that stops working or is not tolerated.
“Two prior lines” means two courses that count separately under the study’s rules — not simply two drugs. Ask the study team if you are unsure how yours are counted.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Biopsy and archival tissue
A biopsy takes a small piece of tissue to examine. “Archival tissue” is a sample already taken, for example at diagnosis, and kept by the hospital.
Whether a stored sample will do depends on when it was taken, how much there is and what the study needs. Ask whether the study accepts your stored sample or needs a new biopsy.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
ECOG performance status
A scale of how much an illness limits everyday activity. For people being assessed to join a study, scores run from 0 (fully active) to 4; lower is more active.
Studies most often ask for 0–1 or 0–2. Your doctor gives the score; the WHO scale uses the same steps. The full scale also has 5, which records death.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Cancer (malignancy)
Malignancy means cancer. Criteria about another or earlier malignancy ask whether you have had a different cancer, usually within a set number of years.
Some are commonly allowed, such as treated skin cancers other than melanoma and early cancers removed completely — check the exceptions this study lists.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Adult men diagnosed with metastatic hormone-sensitive prostate cancer and treated with androgen deprivation therapy combined with androgen receptor signaling inhibitors. Clinical data, treatment response, follow-up outcomes, and archived prostate biopsy whole-slide images will be collected for artificial intelligence model development and validation.
Other: Artificial Intelligence-Based Digital Pathology Assessment
Archived prostate biopsy pathology slides will be digitized as whole-slide images and analyzed using an artificial intelligence-based digital pathology model. The model will be developed and validated to predict treatment response and prognosis in patients with metastatic hormone-sensitive prostate cancer treated with androgen deprivation therapy plus androgen receptor signaling inhibitors. No study-mandated treatment intervention will be assigned, and the artificial intelligence results will not be used to guide clinical treatment decisions during this observational study.
Predictive Performance of the AI-Based Digital Pathology Model for Deep PSA Response
The primary outcome measure is the area under the receiver operating characteristic curve of the artificial intelligence-based digital pathology model for predicting deep prostate-specific antigen response. Deep PSA response is defined as a prostate-specific antigen level of less than 0.2 ng/mL at 6 to 7 months after initiation of androgen deprivation therapy plus androgen receptor signaling inhibitors. Model performance will be evaluated in the validation cohort.
Time frame: 6 to 7 months after initiation of ADT plus ARSI
Concordance Index of the Artificial Intelligence-Based Digital Pathology Model for Predicting Metastatic Castration-Resistant Prostate Cancer
The secondary outcome measure is the concordance index of the artificial intelligence-based digital pathology model for predicting time to metastatic castration-resistant prostate cancer. Time to metastatic castration-resistant prostate cancer is defined as the interval from initiation of androgen deprivation therapy plus androgen receptor signaling inhibitors to the development of metastatic castration-resistant prostate cancer. Patients without metastatic castration-resistant prostate cancer at the last follow-up will be censored. Model performance will be evaluated in the validation cohort.
Time frame: Up to 60 months after initiation of androgen deprivation therapy plus androgen receptor signaling inhibitors.
Plan to share: No — Individual participant data will not be publicly shared because this study involves multicenter clinical data, pathology whole-slide images, and follow-up information from patients with metastatic hormone-sensitive prostate cancer. Although data will be de-identified, the combination of clinical variables and pathology images may still carry potential privacy and re-identification risks. Data sharing is also subject to the ethical approvals, institutional policies, and data use agreements of each participating center. Reasonable requests for access to aggregated or de-identified data may be considered by the principal investigator, subject to approval by the relevant ethics committees and participating institutions.
No publications or documents are linked to this record.
Ran from Jan 2019 to primary completion in Mar 2026, 86 months.
Of 1,098 non-industry interventional studies with no phase under Prostatic Neoplasms, half reached primary completion within 43 months of starting (the median), counting those still running; a quarter within 22 and three quarters within 86. This study's 86 months is above that.
Counting every sponsor, half of 1,155 studies reached it within 43 months; a quarter within 22 and three quarters within 84.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is active, not recruiting, as verified in May 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Xiangya Hospital of Central South University →