Predicting Dosage of Immunosuppressant Drugs After Kidney Transplantation Using Machine Learning

TL;DR

This paper develops a machine learning model, specifically a random forest, to accurately predict personalized immunosuppressant drug dosages for kidney transplant patients, addressing the challenge of dosage variance.

Contribution

The study introduces a novel application of random forest algorithms for personalized drug dosage prediction in kidney transplant patients.

Findings

High accuracy in dosage predictions

Effective handling of patient-specific variability

Potential to improve post-transplant medication management

Abstract

While kidney transplants are seen as the best treatment option for patients with end-stage renal disease and kidney failure, the organ's health depends on the dosage of immunosuppressant drugs post-transplantation. Due to the dosage variance based on each patient's unique physiology, nephrologists face numerous difficulties when determining the precise dosage needed for each patient. Therefore, in this research we aim to devise a machine learning algorithm to forecast the dosage of immunosuppressant drugs needed for different patients after kidney transplantation. Utilizing a random forest algorithm, the devised model is able to achieve accurate measurements for patient drug dosages.