EMIT: A New Approach for Irregular Time Series in Healthcare AI
Excited to share our paper “EMIT: Event-Based Masked Auto Encoding for Irregular Time Series” published at ICDM 2024. Together with A/Prof. Sen WANG, Dr Ruihong Qiu, A/Prof. Adam Irwin and Prof. Shazia Sadiq, we explore how irregular time series (like vital signs and lab results recorded at uneven intervals) challenge existing AI models and how our proposed framework, EMIT, improves clinical decision support through better representation learning. Special thanks to CIRES, Queensland Health and The University of Queensland for supporting this research.
Read full paper at https://arxiv.org/pdf/2409.16554
Our Approach
We introduce EMIT, a pretraining framework based on transformer architecture, tailored for irregular clinical time series data. EMIT learns by:
- Finding important points in irregular time series
- Pretraining by masking and predicting those points
- Use the pretrained model for any downstream task (e.g., outcome prediction)
Key Findings
Improved Representation Learning: EMIT captures important variations without losing timing information, outperforming generic pretext approaches for irregular time series.
Data Efficiency: On benchmark healthcare datasets (MIMIC-III & PhysioNet Challenge 2012), EMIT achieved strong results using only 50% of labeled data, reducing reliance on costly annotations.
Task Relevance: By designing pretext tasks specific to irregular time series, EMIT delivers more reliable clinical predictions compared to standard forecasting approaches.
How can we design AI that adapts to the messy, irregular reality of clinical data while still delivering trustworthy predictions?
Professor Susan Williams from the Universität Koblenz Germany, is visiting our Swinburne University of Technology node from the 4th to 9th February 2024. Sue is a Professor of Enterprise Information Management and will be collaborating and working with CIRES Chief Investigator Dr Paul Scifleet, and CIRES PhD Researchers Lufan Zhang and Pa Pa Khin.
As an interdisciplinary researcher with expertise in the areas of social and organisational informatics, Sue’s work focuses on information ecologies and the design of the digital workplace. With an academic background in computer and information science, her research examines complex socio-technical change (STC) and human-centred technology design. Her long-term research programme investigates the challenges associated with understanding how new information infrastructures are shaping work and work practices, and the design of digital workspaces and workplaces to support distributed collaborative work.
CIRES Chief Investigator Dr Paul Scifleet is looking forward to the collaboration. “Professor William’s is one of the world’s leading researchers in Enterprise Information Management and the challenges businesses face today in managing the ever-increasing amount of vital information shared in workplace collaboration technologies. We are excited to be working with Professor Williams to improve the information resilience of Australian businesses facing the same concerns.”