Korean J Transplant.  2020 Dec;34(Supple 1):S147. 10.4285/ATW2020.PO-1191.

Machine-learning models to predict tacrolimus dosage in liver transplant recipients

• Lee JM
• Yoon SB
• Lee HC
• Jung CW
• Hong SK
• Cho JH
• Yi NJ
• Lee KW

• KMID: 2509337
• DOI: http://doi.org/10.4285/ATW2020.PO-1191

Abstract

Background
Tacrolimus is the most widely used immunosuppressive agents to prevent rejection after solid organ transplantation. However, the use of tacrolimus should be cautious due to its narrow therapeutic index and variability of individual bio availabilities. Machine learning techniques could be good modality to decide optimal dosage of tacrolimus, compared with traditional statistical models, have many advantages including high power and accuracy, we have implemented a new approach to find the optimal dose of tacrolimus by machine learning technique. 
Methods
We retrospectively reviewed the postoperative tacrolimus levels of patients who underwent liver transplantation at the Seoul National University Hospital from March 2016 to March 2018. We implemented an artificial intelligence model predicting future tacrolimus levels by tacrolimus concentrations in the previous two days, sex, height, and daily changing body weight. We investigated hyperparameters (the number of layers in the network and the number of nodes in each layer) using a grid search and found the model with the lowest validation error.
Results
A machine learning model was derived using data from the 187 patients. As a result of testing the model with 18 patients, the predicted value of the model had an error of 1.5 ug/L from the actual measured tacrolimus level. Simulating the model in the random case with a calculated tacrolimus dose to ensure the next drug concentration to be within the therapeutic range, more than 95% of the final predicted tacrolimus level comes in the therapeutic window.
Conclusions
This is the first study to use machine learning models to predict optimal dosage after liver transplantation. The machine-learning model is useful to decide the optimal dose of tacrolimus immediate postoperative period after liver transplantation.