Comparing the Performance of Multiple Small-Data Personalized Tacrolimus Dosing Models for Pediatric Liver Transplant: A Retrospective Study

Annu Int Conf IEEE Eng Med Biol Soc. 2023 Jul:2023:1-4. doi: 10.1109/EMBC40787.2023.10341002.

Abstract

Tacrolimus is a potent immunosuppressant used after pediatric liver transplant. However, tacrolimus's narrow therapeutic window, reliance on physicians' experience for the dose titration, and intra- and inter-patient variability result in liver transplant patients falling out of the target tacrolimus trough levels frequently. Existing personalized dosing models based on the area-under-the-concentration over time curves require a higher frequency of blood draws than the current standard of care and may not be practically feasible. We present a small-data artificial intelligence-derived platform, CURATE.AI, that uses data from individual patients obtained once daily to model the dose and response relationship and identify suitable doses dynamically. Retrospective optimization using 6 models of CURATE.AI and data from 16 patients demonstrated good predictive performance and identified a suitable model for further investigations.Clinical Relevance- This study established and compared the predictive performance of 6 personalized tacrolimus dosing models for pediatric liver transplant patients and identified a suitable model with consistently good predictive performance based on data from pediatric liver transplant patients.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Artificial Intelligence
  • Child
  • Humans
  • Immunosuppressive Agents / therapeutic use
  • Liver Transplantation*
  • Retrospective Studies
  • Tacrolimus* / therapeutic use

Substances

  • Tacrolimus
  • Immunosuppressive Agents