CSAI: Conditional Self-Attention Imputation for Healthcare Time-series

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Qian, Linglong, Raj, Joseph Arul, Ellis, Hugh Logan, Zhang, Ao, Zhang, Yuezhou, Wang, Tao, Dobson, Richard JB, Ibrahim, Zina
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915710181048320
author Qian, Linglong
Raj, Joseph Arul
Ellis, Hugh Logan
Zhang, Ao
Zhang, Yuezhou
Wang, Tao
Dobson, Richard JB
Ibrahim, Zina
author_facet Qian, Linglong
Raj, Joseph Arul
Ellis, Hugh Logan
Zhang, Ao
Zhang, Yuezhou
Wang, Tao
Dobson, Richard JB
Ibrahim, Zina
contents We introduce the Conditional Self-Attention Imputation (CSAI) model, a novel recurrent neural network architecture designed to address the challenges of complex missing data patterns in multivariate time series derived from hospital electronic health records (EHRs). CSAI extends state-of-the-art neural network-based imputation by introducing key modifications specific to EHR data: a) attention-based hidden state initialisation to capture both long- and short-range temporal dependencies prevalent in EHRs, b) domain-informed temporal decay to mimic clinical data recording patterns, and c) a non-uniform masking strategy that models non-random missingness by calibrating weights according to both temporal and cross-sectional data characteristics. Comprehensive evaluation across four EHR benchmark datasets demonstrates CSAI's effectiveness compared to state-of-the-art architectures in data restoration and downstream tasks. CSAI is integrated into PyPOTS, an open-source Python toolbox designed for machine learning tasks on partially observed time series. This work significantly advances the state of neural network imputation applied to EHRs by more closely aligning algorithmic imputation with clinical realities.
format Preprint
id arxiv_https___arxiv_org_abs_2312_16713
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle CSAI: Conditional Self-Attention Imputation for Healthcare Time-series
Qian, Linglong
Raj, Joseph Arul
Ellis, Hugh Logan
Zhang, Ao
Zhang, Yuezhou
Wang, Tao
Dobson, Richard JB
Ibrahim, Zina
Machine Learning
Artificial Intelligence
We introduce the Conditional Self-Attention Imputation (CSAI) model, a novel recurrent neural network architecture designed to address the challenges of complex missing data patterns in multivariate time series derived from hospital electronic health records (EHRs). CSAI extends state-of-the-art neural network-based imputation by introducing key modifications specific to EHR data: a) attention-based hidden state initialisation to capture both long- and short-range temporal dependencies prevalent in EHRs, b) domain-informed temporal decay to mimic clinical data recording patterns, and c) a non-uniform masking strategy that models non-random missingness by calibrating weights according to both temporal and cross-sectional data characteristics. Comprehensive evaluation across four EHR benchmark datasets demonstrates CSAI's effectiveness compared to state-of-the-art architectures in data restoration and downstream tasks. CSAI is integrated into PyPOTS, an open-source Python toolbox designed for machine learning tasks on partially observed time series. This work significantly advances the state of neural network imputation applied to EHRs by more closely aligning algorithmic imputation with clinical realities.
title CSAI: Conditional Self-Attention Imputation for Healthcare Time-series
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2312.16713