Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
The goal of this prospective diagnostic test (correlation) study is to develop and investigate the performance of artificial intelligence in predicting peritoneum transporter status and dialysis efficiency in adult patients undergoing peritoneal dialysis (PD).
The main questions it aims to answer are:
Can artificial intelligence predict peritoneal transporter status based on simple clinical and biochemical measurements? Can artificial intelligence predict dialysis adequacy (Kt/V) using these features?
Researchers will compare the performance of the AI model with the gold standard Peritoneal Equilibration Test (PET) and Kt/V to evaluate its accuracy and reliability.
Participants will:
Provide peritoneal dialysate and spot urine samples for biochemical analysis. Undergo routine dialysis adequacy and peritoneal equilibration testing (PET). Have clinical and laboratory data collected for AI model training and validation.
The study will recruit approximately 350 peritoneal dialysis patients, with 280 participants in the training/validation arm and 70 participants in the test arm. The study duration is 12 months following enrollment.
The DETECT-PD (Dialysis Efficiency and Transporter Evaluation Computational Tool in Peritoneal Dialysis) study is a double-blind, prospective diagnostic test (correlation) study designed to evaluate the feasibility and effectiveness of artificial intelligence (AI) in predicting peritoneal transporter status and dialysis efficiency in patients undergoing peritoneal dialysis (PD). The study aims to develop a computational model that leverages clinical, biochemical, and peritoneal transport data to provide a non-invasive and efficient assessment tool, ultimately improving dialysis management and patient outcomes.
Patient recruitment and data collection will be conducted during routine dialysis adequacy and peritoneal transporter status assessments. The following clinical and biochemical parameters will be collected:
Demographics & Medical History Peritoneal Dialysis Data Biochemical Data
The AI model will be developed using Python 3.11 and PyTorch 2.41 for deep learning and predictive analytics.
The key methodological steps include:
Data Preprocessing: Handling missing values, feature scaling, and one-hot encoding for categorical variables.
Feature Selection: Identifying the most predictive clinical and biochemical markers.
Model Training: Using deep learning regression models to predict PET and Kt/V outcomes.
Performance Evaluation: Evaluating model accuracy using:
Mean Absolute Error (MAE) Mean Squared Error (MSE) R² score (coefficient of determination) Bland-Altman plots and correlation coefficients for agreement with measured values.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Training/Validation | Participants in training/validation arm will receive the same standard investigations and care as part of their routine PD management, including clinical evaluations, biochemical testing, and measurements of peritoneal transporter status via the Peritoneal Equilibrium Test (PET) and dialysis adequacy (Kt/V). |
| |
| Test | Participants in training/validation arm will receive the same standard investigations and care as part of their routine PD management, including clinical evaluations, biochemical testing, and measurements of peritoneal transporter status via the Peritoneal Equilibrium Test (PET) and dialysis adequacy (Kt/V). |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| data collection | Other | An additional collection of peritoneal dialysate and spot urine samples will be collected. Participants randomized to the training/validation arm will have their data used for model development, including the training and validation phases. |
| Measure | Description | Time Frame |
|---|---|---|
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual 2-hour and 4-hour dialysate-to-plasma creatinine ratio (D/P Cr) Performance Metrics: Mean Absolute Error (MAE) Unit of Measure: Absolute error | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual dialysate-to-baseline dialysate glucose concentration ratio (D/D0 Glu) Performance Metrics: Mean Absolute Error (MAE) Unit of Measure: Absolute error | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual 2-hour and 4-hour dialysate-to-plasma creatinine ratio (D/P Cr) Performance Metrics: Mean Squared Error (MSE) Unit of Measure: Squared Error | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual dialysate-to-baseline dialysate glucose concentration ratio (D/D0 Glu) Performance Metrics: Mean Squared Error (MSE) Unit of Measure: Squared Error | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual 2-hour and 4-hour dialysate-to-plasma creatinine ratio (D/P Cr) Performance Metrics: Coefficient of Determination (R²) Unit of Measure: R² value (range: 0 to 1, higher values indicate better model performance) |
| Measure | Description | Time Frame |
|---|---|---|
| Dialysis Adequacy (Kt/V) parameters | Predictive Accuracy of AI Model for Dialysis Adequacy (Kt/V) Outcome: AI-predicted vs. actual total weekly Kt/V Performance Metrics: Mean Absolute Error (MAE) Unit of Measure: Absolute error | Measured at baseline during study enrollment |
| Dialysis Adequacy (Kt/V) parameters |
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
End-stage renal failure patients requiring peritoneal dialysis as renal replacement therapy
Not provided
Not provided
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Tuen Mun Hospital | Tuenmen | Hong Kong |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 32188600 | Background | Riley RD, Ensor J, Snell KIE, Harrell FE Jr, Martin GP, Reitsma JB, Moons KGM, Collins G, van Smeden M. Calculating the sample size required for developing a clinical prediction model. BMJ. 2020 Mar 18;368:m441. doi: 10.1136/bmj.m441. No abstract available. | |
| 12046043 | Background | Szeto CC, Wong TY, Chow KM, Leung CB, Li PK. Dialysis adequacy and transport test for characterization of peritoneal transport type in Chinese peritoneal dialysis patients receiving three daily exchanges. Am J Kidney Dis. 2002 Jun;39(6):1287-99. doi: 10.1053/ajkd.2002.33405. |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot_SAP | Yes | Yes | No | Study Protocol and Statistical Analysis Plan | Jan 8, 2025 |
Not provided
Not provided
Not provided
Not provided
|
| data report | Other | An additional collection of peritoneal dialysate and spot urine samples will be collected. Participants randomized to the test arm will have their data isolated and reserved exclusively for evaluating the performance of the final AI model |
|
|
| Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual dialysate-to-baseline dialysate glucose concentration ratio (D/D0 Glu) Performance Metrics: Coefficient of Determination (R²) Unit of Measure: R² value (range: 0 to 1, higher values indicate better model performance) | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual 2-hour and 4-hour dialysate-to-plasma creatinine ratio (D/P Cr) Performance Metrics: Intraclass Correlation Coefficient (ICC) Unit of Measure: ICC value (range: 0 to 1, higher values indicate better agreement) | Measured at baseline during study enrollment |
| Peritoneal Equilibration Test (PET) Parameters | Predictive Accuracy of AI Model for Peritoneal Equilibration Test (PET) Parameters Outcome: AI-predicted vs. actual dialysate-to-baseline dialysate glucose concentration ratio (D/D0 Glu) Performance Metrics: Intraclass Correlation Coefficient (ICC) Unit of Measure: ICC value (range: 0 to 1, higher values indicate better agreement) | Measured at baseline during study enrollment |
Predictive Accuracy of AI Model for Dialysis Adequacy (Kt/V) Outcome: AI-predicted vs. actual total weekly Kt/V Performance Metrics: Mean Squared Error (MSE) Unit of Measure: Squared Error |
| Measured at baseline during study enrollment |
| Dialysis Adequacy (Kt/V) parameters | Predictive Accuracy of AI Model for Dialysis Adequacy (Kt/V) Outcome: AI-predicted vs. actual total weekly Kt/V Performance Metrics: Coefficient of Determination (R²) Unit of Measure: R² value (range: 0 to 1, higher values indicate better model performance) | Measured at baseline during study enrollment |
| Dialysis Adequacy (Kt/V) parameters | Predictive Accuracy of AI Model for Dialysis Adequacy (Kt/V) Outcome: AI-predicted vs. actual total weekly Kt/V Performance Metrics: Intraclass Correlation Coefficient (ICC) Unit of Measure: ICC value (range: 0 to 1, higher values indicate better agreement) | Measured at baseline during study enrollment |
| Discriminative Ability of AI Model | Outcome: Classification of peritoneal transporter type (low, low-average, high-average, high) based on PET Performance Metrics: Area Under the Receiver Operating Characteristic Curve (AUC-ROC) Unit of Measure: AUC-ROC value (range: 0 to 1, higher values indicate better discriminative ability) | Measured at baseline during study enrollment |
| Discriminative Ability of AI Model | Outcome: Classification of peritoneal transporter type (low, low-average, high-average, high) based on PET Performance Metrics: Area Under the Precision-Recall Curve (AUC-PR) Unit of Measure: AUC-PR value (range: 0 to 1, higher values indicate better model performance) | Measured at baseline during study enrollment |
| Discriminative Ability of AI Model | Outcome: Classification of peritoneal transporter type (low, low-average, high-average, high) based on PET Performance Metrics: Sensitivity Unit of Measure: Sensitivity (%) | Measured at baseline during study enrollment |
| Discriminative Ability of AI Model | Outcome: Classification of peritoneal transporter type (low, low-average, high-average, high) based on PET Performance Metrics: F1-score Unit of Measure: F1-score (range: 0 to 1, higher values indicate better balance between precision and recall) | Measured at baseline during study enrollment |
| Calibration Performance of AI Model | Outcome: Model-predicted vs. actual transporter status and dialysis adequacy (Kt/V) Performance Metrics: Calibration Slope Unit of Measure: Calibration slope (ideal value = 1) | Measured at baseline during study enrollment |
| Calibration Performance of AI Model | Outcome: Model-predicted vs. actual transporter status and dialysis adequacy (Kt/V) Performance Metrics: Calibration-in-the-large (Mean Calibration Error) Unit of Measure: Mean error (lower values indicate better calibration) | Measured at baseline during study enrollment |
| Calibration Performance of AI Model | Outcome: Model-predicted vs. actual transporter status and dialysis adequacy (Kt/V) Performance Metrics: Calibration Slope Calibration-in-the-large (Mean Calibration Error) Brier Score | Measured at baseline during study enrollment |
| Calibration Performance of AI Model | Outcome: Model-predicted vs. actual transporter status and dialysis adequacy (Kt/V) Performance Metrics: Brier Score Unit of Measure: Brier Score (range: 0 to 1, lower values indicate better calibration) | Measured at baseline during study enrollment |
| 26551272 | Background | SPRINT Research Group; Wright JT Jr, Williamson JD, Whelton PK, Snyder JK, Sink KM, Rocco MV, Reboussin DM, Rahman M, Oparil S, Lewis CE, Kimmel PL, Johnson KC, Goff DC Jr, Fine LJ, Cutler JA, Cushman WC, Cheung AK, Ambrosius WT. A Randomized Trial of Intensive versus Standard Blood-Pressure Control. N Engl J Med. 2015 Nov 26;373(22):2103-16. doi: 10.1056/NEJMoa1511939. Epub 2015 Nov 9. |
| 16755101 | Background | Chen CA, Lin SH, Hsu YJ, Li YC, Wang YF, Chiu JS. Neural network modeling to stratify peritoneal membrane transporter in predialytic patients. Intern Med. 2006;45(9):663-4. doi: 10.2169/internalmedicine.45.1419. Epub 2006 Jun 1. No abstract available. |
| 36350033 | Background | Gu J, Bai E, Ge C, Winograd J, Shah AD. Peritoneal equilibration testing: Your questions answered. Perit Dial Int. 2023 Sep;43(5):361-373. doi: 10.1177/08968608221133629. Epub 2022 Nov 9. |
| 33563110 | Background | Morelle J, Stachowska-Pietka J, Oberg C, Gadola L, La Milia V, Yu Z, Lambie M, Mehrotra R, de Arteaga J, Davies S. ISPD recommendations for the evaluation of peritoneal membrane dysfunction in adults: Classification, measurement, interpretation and rationale for intervention. Perit Dial Int. 2021 Jul;41(4):352-372. doi: 10.1177/0896860820982218. Epub 2021 Feb 10. |
| 21427259 | Background | Blake PG, Bargman JM, Brimble KS, Davison SN, Hirsch D, McCormick BB, Suri RS, Taylor P, Zalunardo N, Tonelli M; Canadian Society of Nephrology Work Group on Adequacy of Peritoneal Dialysis. Clinical Practice Guidelines and Recommendations on Peritoneal Dialysis Adequacy 2011. Perit Dial Int. 2011 Mar-Apr;31(2):218-39. doi: 10.3747/pdi.2011.00026. No abstract available. |
| 22697882 | Background | Chen JB, Lam KK, Su YJ, Lee WC, Cheng BC, Kuo CC, Wu CH, Lin E, Wang YC, Chen TC, Liao SC. Relationship between Kt/V urea-based dialysis adequacy and nutritional status and their effect on the components of the quality of life in incident peritoneal dialysis patients. BMC Nephrol. 2012 Jun 14;13:39. doi: 10.1186/1471-2369-13-39. |
| 38490516 | Background | Lin YL, Lee YC, Lee CC, Wu MH. Role of Peritoneal Equilibration Test in Assessing Folate Transport During Peritoneal Dialysis. J Ren Nutr. 2024 Sep;34(5):463-468. doi: 10.1053/j.jrn.2024.02.003. Epub 2024 Mar 13. |
| 19776045 | Background | Cnossen TT, Smit W, Konings CJ, Kooman JP, Leunissen KM, Krediet RT. Quantification of free water transport during the peritoneal equilibration test. Perit Dial Int. 2009 Sep-Oct;29(5):523-7. |
| 2663040 | Background | Twardowski ZJ. Clinical value of standardized equilibration tests in CAPD patients. Blood Purif. 1989;7(2-3):95-108. doi: 10.1159/000169582. |
| 36114414 | Background | Bello AK, Okpechi IG, Osman MA, Cho Y, Cullis B, Htay H, Jha V, Makusidi MA, McCulloch M, Shah N, Wainstein M, Johnson DW. Epidemiology of peritoneal dialysis outcomes. Nat Rev Nephrol. 2022 Dec;18(12):779-793. doi: 10.1038/s41581-022-00623-7. Epub 2022 Sep 16. |
| Feb 13, 2025 |
| Prot_SAP_000.pdf |
| ICF | No | No | Yes | Informed Consent Form | Jan 8, 2025 | Feb 13, 2025 | ICF_001.pdf |
| ID | Term |
|---|---|
| D007676 | Kidney Failure, Chronic |
| D004194 | Disease |
| ID | Term |
|---|---|
| D051436 | Renal Insufficiency, Chronic |
| D051437 | Renal Insufficiency |
| D007674 | Kidney Diseases |
| D014570 | Urologic Diseases |
| D052776 | Female Urogenital Diseases |
| D005261 | Female Urogenital Diseases and Pregnancy Complications |
| D000091642 | Urogenital Diseases |
| D052801 | Male Urogenital Diseases |
| D002908 | Chronic Disease |
| D020969 | Disease Attributes |
| D010335 | Pathologic Processes |
| D013568 | Pathological Conditions, Signs and Symptoms |
Not provided
Not provided
| ID | Term |
|---|---|
| D003625 | Data Collection |
| D012107 | Research Design |
| ID | Term |
|---|---|
| D004812 | Epidemiologic Methods |
| D008919 | Investigative Techniques |
| D017531 | Health Care Evaluation Mechanisms |
| D011787 | Quality of Health Care |
| D017530 | Health Care Quality, Access, and Evaluation |
| D011634 | Public Health |
| D004778 | Environment and Public Health |
| D008722 | Methods |
Not provided
Not provided