Frontiers in Cardiovascular Medicine (May 2022)

Long Short-Term Memory Network for Development and Simulation of Warfarin Dosing Model Based on Time Series Anticoagulant Data

  • Yun Kuang,
  • Yaxin Liu,
  • Qi Pei,
  • Xiaoyi Ning,
  • Yi Zou,
  • Liming Liu,
  • Long Song,
  • Chengxian Guo,
  • Yuanyuan Sun,
  • Kunhong Deng,
  • Chan Zou,
  • Dongsheng Cao,
  • Dongsheng Cao,
  • Yimin Cui,
  • Yimin Cui,
  • Chengkun Wu,
  • Guoping Yang,
  • Guoping Yang,
  • Guoping Yang,
  • Guoping Yang

DOI
https://doi.org/10.3389/fcvm.2022.881111
Journal volume & issue
Vol. 9

Abstract

Read online

BackgroundWarfarin is an effective treatment for thromboembolic disease but has a narrow therapeutic index, and dosage can differ tremendously among individuals. The study aimed to develop an individualized international normalized ratio (INR) model based on time series anticoagulant data and simulate individualized warfarin dosing.MethodsWe used a long short-term memory (LSTM) network to develop an individualized INR model based on data from 4,578 follow-up visits, including clinical and genetic factors from 624 patients whom we enrolled in our previous randomized controlled trial. The data of 158 patients who underwent valvular surgery and were included in a prospective registry study were used for external validation in the real world.ResultsThe prediction accuracy of LSTM_INR was 70.0%, which was much higher than that of MAPB_INR (maximum posterior Bayesian, 53.9%). Temporal variables were significant for LSTM_INR performance (51.7 vs. 70.0%, P < 0.05). Genetic factors played an important role in predicting INR at the onset of therapy, while after 15 days of treatment, we found that it might unnecessary to detect genotypes for warfarin dosing. Using LSTM_INR, we successfully simulated individualized warfarin dosing and developed an application (AI-WAR) for individualized warfarin therapy.ConclusionThe results indicate that temporal variables are necessary to be considered in warfarin therapy, except for clinical factors and genetic factors. LSTM network may have great potential for long-term drug individualized therapy.Trial RegistrationNCT02211326; www.chictr.org.cn:ChiCTR2100052089.

Keywords