Model-Informed Precision Dosing on Cyclosporine Therapy in Hematopoietic Stem Cell Transplant Recipients

NCT07695571 | Not Yet Recruiting DMC

• 1 other identifier: HPM CYCLOSPORINE BMT
• Study Type: observational
• Target: 300
• Locations: 0 countries
• Sites: N/A

Brief Summary

The purpose of this study is to develop a new tool that helps doctors choose the right cyclosporine dose for patients undergoing bone marrow transplantation. The tool is designed to predict the best dose using sparse sampling, making it practical for everyday clinical care. It combines information about population pharmacokinetics of cyclosporine with advanced artificial intelligence techniques, including machine learning and deep learning. This tool aims to improve treatment, personalize dosing for each patient, and reduce the risk of graft-versus-host disease.

Conditions

Bone Marrow Transplantation; AML

Keywords

Clinical Pharmacokinetics; Machine learning

Outcome Measures

Primary Outcomes (1)

• Predictive accuracy of individualized cyclosporine dosing models.

  Comparison of the predictive performance of the hybrid Population Pharmacokinetic-Machine Learning (PopPK-ML) model, deep learning model, and conventional Bayesian forecasting for predicting individualized cyclosporine doses using therapeutic drug monitoring (TDM) data. Performance will be assessed using root mean square error (RMSE), mean absolute error (MAE), mean prediction error (MPE), coefficient of determination (R²), and target dose prediction accuracy.

  up to 6 months

Study Arms (1)

Patients receiving cyclosporine to prevent graft-versus-host disease after HSCT.

Participants undergoing allogeneic hematopoietic stem cell transplantation who received cyclosporine for graft-versus-host disease (GVHD) prophylaxis. Cyclosporine was administered according to institutional practice, and blood concentration measurements obtained during routine therapeutic drug monitoring were used to develop and evaluate a model-informed precision dosing algorithm.

Eligibility Criteria

• Age: 2 Years - 65 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of pediatric and adult patients aged 2-65 years who underwent first allogeneic hematopoietic stem cell transplantation (HSCT) and received cyclosporine for graft-versus-host disease (GVHD) prophylaxis. Participants will be identified retrospectively from electronic medical records and therapeutic drug monitoring (TDM) databases. Eligible patients must have complete demographic, clinical, laboratory, dosing, and cyclosporine TDM data. Patients with inaccurate dose administration or blood sampling times, missing essential covariates, or insufficient pharmacokinetic or TDM data will be excluded.

You may qualify if:

• CsA therapy indicated alone or in combination for GVHD prophylaxis.
• Aged 2-65 years.
• Clinically stable after first HSCT.

You may not qualify if:

• Inaccurate sampling or dose administration times.
• Patients with missing key covariates.
• Patients lacking sufficient pharmacokinetic or TDM data

Sponsors & Collaborators

• Yasmin medhat munir Mohamed: lead

Related Publications (5)

• Yang Y, Zhu Y, Xia L, Chai Y, Quan D, Xue Q, Wang Z. Population pharmacokinetics of cyclosporine A in hematopoietic stem cell transplant recipients: A systematic review. Eur J Pharm Sci. 2025 Jan 1;204:106882. doi: 10.1016/j.ejps.2024.106882. Epub 2024 Aug 29.

  PMID: 39214318 BACKGROUND

• Destere A, Marquet P, Labriffe M, Drici MD, Woillard JB. A Hybrid Algorithm Combining Population Pharmacokinetic and Machine Learning for Isavuconazole Exposure Prediction. Pharm Res. 2023 Apr;40(4):951-959. doi: 10.1007/s11095-023-03507-y. Epub 2023 Mar 29.

  PMID: 36991227 BACKGROUND

• Irie K, Minar P, Reifenberg J, Boyle BM, Noe JD, Hyams JS, Mizuno T. Hybrid Population Pharmacokinetic-Machine Learning Modeling to Predict Infliximab Pharmacokinetics in Pediatric and Young Adult Patients with Crohn's Disease. Clin Pharmacokinet. 2025 Nov;64(11):1669-1679. doi: 10.1007/s40262-025-01564-7. Epub 2025 Aug 30.

  PMID: 40885855 BACKGROUND

• Chen K, Wang C, Wei Y, Ma S, Huang W, Dong Y, Wang Y. Machine learning and population pharmacokinetics: a hybrid approach for optimizing vancomycin therapy in sepsis patients. Microbiol Spectr. 2025 May 6;13(5):e0049925. doi: 10.1128/spectrum.00499-25. Epub 2025 Mar 31.

  PMID: 40162774 BACKGROUND

• van Os W, O'Jeanson A, Troisi C, Liu C, Brooks JT, Hughes JH, Tong DMH, Keizer RJ. Machine Learning-Based Model Selection and Averaging Outperform Single-Model Approaches for a Priori Vancomycin Precision Dosing. CPT Pharmacometrics Syst Pharmacol. 2025 Oct;14(10):1650-1660. doi: 10.1002/psp4.70084. Epub 2025 Jul 30.

  PMID: 40734640 BACKGROUND

Central Study Contacts

Yasmin Mohammed, demonstrater assitant

CONTACT

+201093201956; Yasmin.Mohammed@pharm.capu.edu.eg

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: demonstrater assistant

Study Record Dates

• First Submitted: July 2, 2026
• First Posted: July 10, 2026
• Study Start: August 1, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): June 1, 2027
• Last Updated: July 10, 2026

Record last verified: 2026-07