Interpretable Trend Analysis Neural Networks for Longitudinal Data Analysis

Zhenjie Yao, Yixin Chen, Jinwei Wang, Junjuan Li, Shuohua Chen, Shouling Wu, Yanhui Tu, Ming Hui Zhao, Luxia Zhang

Research output: Contribution to journalArticlepeer-review

Abstract

Cohort study is one of the most commonly used study methods in medical and public health researches, which result in longitudinal data. Conventional statistical models and machine learning methods are not capable of modeling the evolution trend of the variables in longitudinal data. In this article, we propose a Trend Analysis Neural Networks (TANN), which models the evolution trend of the variables by adaptive feature learning. TANN was tested on dataset of Kaiuan research. The task was to predict occurrence of cardiovascular events within 2 and 5 years, with three repeated medical examinations during 2008 and 2013. For 2-year prediction, The AUC of the TANN is 0.7378, which is a significant improvement than that of conventional methods, while that of TRNS, RNN, DNN, GBDT, RF, and LR are 0.7222, 0.7034, 0.7054, 0.7136, 0.7160, and 0.7024, respectively. For 5-year prediction, TANN also shows improvement. The experimental results show that the proposed TANN achieves better prediction performance on cardiovascular events prediction than conventional models. Furthermore, by analyzing the weights of TANN, we could find out important trends of the indicators, which are ignored by conventional machine learning models. The trend discovery mechanism interprets the model well. TANN is an appropriate balance between high performance and interpretability.

Original languageEnglish
Article number8
JournalACM Transactions on Computing for Healthcare
Volume5
Issue number2
DOIs
StatePublished - Apr 22 2024

Keywords

  • Additional Key Words and PhrasesNeural networks
  • interpretability
  • longitudinal data
  • trend analysis

Fingerprint

Dive into the research topics of 'Interpretable Trend Analysis Neural Networks for Longitudinal Data Analysis'. Together they form a unique fingerprint.

Cite this