Long short-term memory algorithm for personalized tacrolimus dosing: A simple and effective time series forecasting approach post-lung transplantation.
{"title":"Long short-term memory algorithm for personalized tacrolimus dosing: A simple and effective time series forecasting approach post-lung transplantation.","authors":"Haruki Choshi, Kentaroh Miyoshi, Maki Tanioka, Hayato Arai, Shin Tanaka, Kazuhiko Shien, Ken Suzawa, Mikio Okazaki, Seiichiro Sugimoto, Shinichi Toyooka","doi":"10.1016/j.healun.2024.10.026","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Management of tacrolimus trough levels (TTLs) influences morbidity and mortality after lung transplantation. Several studies have explored pharmacokinetic and artificial intelligence models to monitor tacrolimus levels. However, many models depend on a wide range of variables, some of which, like genetic polymorphisms, are not commonly tested for in regular clinical practice. This study aimed to verify the efficacy of a novel approach simply utilizing time series data of tacrolimus dosing, with the objective of accurately predicting trough levels in a variety of clinical settings.</p><p><strong>Methods: </strong>Data encompassing 36 clinical variables for each patient were gathered, and a multivariate long short-term memory algorithm was applied to forecast subsequent TTLs based on the selected clinical variables. The tool was developed using a dataset of 87,112 data points from 117 patients, and its efficacy was confirmed using 6 additional cases.</p><p><strong>Results: </strong>Shapley additive explanations revealed a significant correlation between trough levels and prior dose-concentration data. By using simple trend learning of dose, administration route, and previous trough levels of tacrolimus, we could predict values within 30% of the actual values for 88.5% of time points, which facilitated the creation of a tool for simulating TTLs in response to dosage adjustments. The tool exhibited the potential for rectifying clinical misjudgments in a simulation cohort.</p><p><strong>Conclusions: </strong>Utilizing our time series forecasting tool, precise prediction of trough levels is attainable independently of other clinical variables through the analysis of historical tacrolimus dose-concentration trends alone.</p>","PeriodicalId":15900,"journal":{"name":"Journal of Heart and Lung Transplantation","volume":" ","pages":""},"PeriodicalIF":6.4000,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Heart and Lung Transplantation","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.healun.2024.10.026","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
Abstract
Background: Management of tacrolimus trough levels (TTLs) influences morbidity and mortality after lung transplantation. Several studies have explored pharmacokinetic and artificial intelligence models to monitor tacrolimus levels. However, many models depend on a wide range of variables, some of which, like genetic polymorphisms, are not commonly tested for in regular clinical practice. This study aimed to verify the efficacy of a novel approach simply utilizing time series data of tacrolimus dosing, with the objective of accurately predicting trough levels in a variety of clinical settings.
Methods: Data encompassing 36 clinical variables for each patient were gathered, and a multivariate long short-term memory algorithm was applied to forecast subsequent TTLs based on the selected clinical variables. The tool was developed using a dataset of 87,112 data points from 117 patients, and its efficacy was confirmed using 6 additional cases.
Results: Shapley additive explanations revealed a significant correlation between trough levels and prior dose-concentration data. By using simple trend learning of dose, administration route, and previous trough levels of tacrolimus, we could predict values within 30% of the actual values for 88.5% of time points, which facilitated the creation of a tool for simulating TTLs in response to dosage adjustments. The tool exhibited the potential for rectifying clinical misjudgments in a simulation cohort.
Conclusions: Utilizing our time series forecasting tool, precise prediction of trough levels is attainable independently of other clinical variables through the analysis of historical tacrolimus dose-concentration trends alone.
期刊介绍:
The Journal of Heart and Lung Transplantation, the official publication of the International Society for Heart and Lung Transplantation, brings readers essential scholarly and timely information in the field of cardio-pulmonary transplantation, mechanical and biological support of the failing heart, advanced lung disease (including pulmonary vascular disease) and cell replacement therapy. Importantly, the journal also serves as a medium of communication of pre-clinical sciences in all these rapidly expanding areas.