Prostatic Neoplasms, Castration-Resistant
Conditions
Keywords
artificial intelligence, time to castration-resistant, prostate cancer, whole slide image
Brief 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.
Detailed description
Hormone therapy is an important treatment method for prostate cancer and can effectively extend the survival of patients. However, almost all patients will progress to castration-resistant prostate cancer at different times. Current Hormone therapy options include androgen deprivation therapy(ADT), anti-androgen receptor(AR), and chemotherapy, with combination therapy being more effective in the early stages but associated with greater side effects. Therefore, predicting the time to castration-resistant progression and using this information to apply personalized treatment plans can ensure efficacy while reducing drug side effects. Therefore, we have developed an artificial intelligence predictive model for predicting the time to castration resistance of prostate cancer, which is expected to accurately predict the progression time for different patients and assist doctors in making personalized and precise treatment plans based on individual progression risks. This study is a predictive test with no intervention measures, planning to collect pathological slides of prostate biopsy from the enrolled patients and digitise them into whole-slide images (WSIs). The AI model will analyse the WSIs and generate slide-level predictive results (within 12 months, between 12 to 24months or over 24 months). The routine therapy and examination will be performed as usual. These two processes will not interfere with each other. Then we will follow-up the patients for 24 months, to record the time to castration-resistant progression, then we will compare the results with predictive model.
Interventions
OTHERArtificial 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.
Sponsors
Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
MALE
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
1. Patients are diagnosed with intermediate- to high-risk prostate cancer; undergo prostate biopsy 2. Patients only received endocrine therapy for prostate cancer; 3. Patients with complete clinical and pathological information. 4. Patients agree to participate in this diagnostic test.
Exclusion criteria
1. Patients with other tumors and undergo systemic therapy . 2. The patient refused to participate in this diagnostic test.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| 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. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| sensitivity | For each enrolled patient, the predictive results of AI model will be obtained in not long after prostate biopsy, and the sensitivity of the AI model will be evaluated through study completion, an average of 3 year. | The output of the predictive model is divided into a binary variable using a 12-month threshold: TTCR \<12 months is considered a positive outcome, and TTCR ≥12 months is considered a negative outcome. Accordingly, patients with TTCR \<12 months are positive patients, and those with TTCR ≥12 months are negative patients. The number of correctly predicted positive slides (TTCR\<12 months), to be divided by the number of positive slides in total |
| specificity | For each enrolled patient, the predictive results of AI model will be obtained in not long after prostate biopsy, and the specificity of the AI model will be evaluated through study completion, an average of 3 year. | The output of the predictive model is divided into a binary variable using a 12-month threshold: TTCR \<12 months is considered a positive outcome, and TTCR ≥12 months is considered a negative outcome. Accordingly, patients with TTCR \<12 months are positive patients, and those with TTCR ≥12 months are negative patients. The number of correctly predicted negative slides (TTCR≥12 months), to be divided by the number of negative slides in total |
Countries
China
Contacts
CONTACTTianxin Lin, Ph.D
CONTACTShaoxu Wu, MD
STUDY_DIRECTORShaoxu Wu, Ph.D
Department of Urology of Sun Yat-sen Memorial Hospital of Sun Yat-sen University
Outcome results
None listed