A Study on the Construction of Artificial Intelligence Recognition Model Based on Prospective Multidimensional Renal Transplant Pathology and Clinical Data for Accurate Differentiation of Rejection, Quantitative Lesion Assessment and Prediction of Re-recurrence Risk
Trial Snapshot
- Phase
- Not Applicable
- Status
- Active, not recruiting
- Sponsor
- Enrollment
- 1,000
- Locations
- 1
- Primary Endpoint
- ROC AUC of multi-task AI model for identification of renal allograft lesions
Study Overview
Brief Summary
This prospective research collects leftover kidney biopsy tissue slides and matching routine clinical data from patients who received kidney transplants and underwent standard kidney puncture biopsy at Zhejiang University School of Medicine First Affiliated Hospital starting November 2025. A total of around 1,000 patient samples will be included, covering transplant rejection (including TCMR and ABMR subtypes, acute and chronic rejection), polyomavirus infection and recurrent original kidney disease after transplantation.
All study materials come from residual biopsy specimens generated during regular clinical examinations, with no extra invasive operations, additional medical costs or physical trauma for participants. We will scan pathological slides into digital images and combine them with patients' medical records, lab test results, medication history and follow-up information. After full anonymization and standardized labeling by senior renal pathologists following the Banff standard, we will build an artificial intelligence (AI) multi-task model.
This AI system will serve three core clinical functions: accurately distinguish different types of transplant kidney lesions, quantitatively measure tissue damage caused by rejection, and predict the risk of recurrent rejection after surgery. We will optimize and verify the model's diagnostic accuracy, stability and reliability through dataset segmentation, cross validation and algorithm adjustment.
For patients, this study brings no extra physical or economic burden. If suspicious pathological changes are found during data analysis, relevant clues will be fed back to attending doctors to support individual treatment management. For clinical providers, the finished AI tool can reduce pathologists' reading workload, lower missed diagnosis and misdiagnosis caused by individual experience differences, especially improve detection of subclinical and borderline rejection. It helps clinicians evaluate injury severity and forecast recurrence risk, so as to formulate personalized immunosuppression regimens, reduce rejection relapse and prolong graft survival.
Strict privacy protection measures are implemented throughout the whole research process: all personal identifiable information will be completely removed, and encrypted classified data management is adopted to prevent information leakage. Every participant signs a written informed consent and retains the right to withdraw from the study at any time without affecting their regular medical care. All research procedures have passed ethical review supervision, and all collected data and specimens will be properly stored or destroyed in accordance with standardized medical management rules after the study ends.
The research aims to fill the gap of prospective multi-dimensional AI auxiliary diagnosis research in kidney transplantation, promote standardized, intelligent and precise post-transplant pathological evaluation, and provide new technical support to improve long-term survival outcomes of kidney transplant recipients.
Study Design
- Study Type
- Observational
- Observational Model
- Other
- Time Perspective
- Prospective
Eligibility Criteria
- Ages
- 18 Years to 75 Years (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •Patients who received kidney transplantation and underwent clinically indicated renal allograft biopsy at The First Affiliated Hospital, Zhejiang University School of Medicine starting November
- •Age range from 18 to 75 years old.
- •Complete clinical baseline data, laboratory test records, medication history and pathological information available in electronic medical system.
- •Residual paraffin biopsy slides are available after routine pathological examination.
- •Voluntarily provide written informed consent for the use of residual pathological specimens and clinical data for research.
Exclusion Criteria
- •Poor-quality biopsy specimens including blurred staining, severe tissue damage or insufficient tissue volume which cannot support pathological image analysis.
- •Severe missing core clinical variables that cannot be supplemented via standardized data imputation.
- •Complicated with severe irreversible dysfunction of heart, liver, brain or other vital organs affecting long-term clinical follow-up data collection.
- •Unable to complete routine clinical follow-up, resulting in unavailable outcome data for recurrent rejection labeling.
- •Refuse to participate or withdraw informed consent.
Outcomes
Primary Outcomes
ROC AUC of multi-task AI model for identification of renal allograft lesions
Time Frame: After model training and internal verification（through study completion, an average of 24 months）
Area under receiver operating characteristic curve to evaluate model ability to detect rejection subtypes, polyomavirus nephropathy and recurrent primary renal disease.
Sensitivity and specificity of multi-task AI model for renal allograft lesion diagnosis
Time Frame: After model training and internal verification（through study completion, an average of 24 months）
Sensitivity and specificity of the AI model discriminating TCMR, ABMR, polyomavirus nephropathy and recurrent primary renal disease.
Diagnostic accuracy of multi-task AI model for renal allograft lesions
Time Frame: After model training and internal verification（through study completion, an average of 24 months）
Overall accuracy of the AI model in differentiating post-transplant renal pathological lesions.
Secondary Outcomes
- ICC/Kappa consistency between AI quantitative scoring and pathologists' Banff evaluation(After model training, optimization and internal test set verification（through study completion, an average of 24 months）)
- ROC AUC of AI sub-model for prediction of recurrent renal allograft rejection(After extraction of 12-month routine follow-up data（through study completion, an average of 24 months）)
- Change in inter-pathologist diagnostic Kappa with AI model assistance(After model training and internal verification（through study completion, an average of 24 months）)
Investigators
Chen Dajin
Clinical Professor, Principal Investigator, Kidney Transplantation Center
Zhejiang University