---
title: "Cooperative Joint Attentive Network for Patient Outcome Prediction on Irregular Multi-Rate Multivariate Health Data"
authors:
  - "Qingxiong Tan"
  - "Mang Ye"
  - "Grace Lai-Hung Wong"
  - "PongChi Yuen"
doi: "10.24963/ijcai.2021/219"
url: "https://ijcai.org/proceedings/2021/219"
pdf: "https://ijcai.org/proceedings/2021/0219.pdf"
venue: "Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"
year: 2021
pages: "1586-1592"
track: "Main Track"
keywords:
  - "Data Mining: Mining Spatial, Temporal Data"
---

# Cooperative Joint Attentive Network for Patient Outcome Prediction on Irregular Multi-Rate Multivariate Health Data

Qingxiong Tan, Mang Ye, Grace Lai-Hung Wong, PongChi Yuen

*Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence*, pages 1586-1592. DOI: [10.24963/ijcai.2021/219](https://doi.org/10.24963/ijcai.2021/219)

## Abstract

Due to the dynamic health status of patients and discrepant stability of physiological variables, health data often presents as irregular multi-rate multivariate time series (IMR-MTS) with significantly varying sampling rates. Existing methods mainly study changes of IMR-MTS values in the time domain, without considering their different dominant frequencies and varying data quality. Hence, we propose a novel Cooperative Joint Attentive Network (CJANet) to analyze IMR-MTS in frequency domain, which adaptively handling discrepant dominant frequencies while tackling diverse data qualities caused by irregular sampling. In particular, novel dual-channel joint attention is designed to jointly identify important magnitude and phase signals while detecting their dominant frequencies, automatically enlarging the positive influence of key variables and frequencies. Furthermore, a new cooperative learning module is introduced to enhance information exchange between magnitude and phase channels, effectively integrating global signals to optimize the network. A frequency-aware fusion strategy is finally designed to aggregate the learned features. Extensive experimental results on real-world medical datasets indicate that CJANet significantly outperforms existing methods and provides highly interpretable results.