Transformer representation learning is necessary for dynamic multi-modal physiological data on small-cohort patients
This work addresses the critical need for objective, early diagnosis of POD in high-risk surgical patients, though it is incremental as it applies existing Transformer architectures to a new clinical dataset.
The authors tackled the problem of underdiagnosed postoperative delirium (POD) in ICU patients by proposing a Transformer-based framework for early prediction using multi-modal physiological data, achieving consistent improvements in sensitivity and Youden index for patient TYPE I.
Postoperative delirium (POD), a severe neuropsychiatric complication affecting nearly 50% of high-risk surgical patients, is defined as an acute disorder of attention and cognition, It remains significantly underdiagnosed in the intensive care units (ICUs) due to subjective monitoring methods. Early and accurate diagnosis of POD is critical and achievable. Here, we propose a POD prediction framework comprising a Transformer representation model followed by traditional machine learning algorithms. Our approaches utilizes multi-modal physiological data, including amplitude-integrated electroencephalography (aEEG), vital signs, electrocardiographic monitor data as well as hemodynamic parameters. We curated the first multi-modal POD dataset encompassing two patient types and evaluated the various Transformer architectures for representation learning. Empirical results indicate a consistent improvements of sensitivity and Youden index in patient TYPE I using Transformer representations, particularly our fusion adaptation of Pathformer. By enabling effective delirium diagnosis from postoperative day 1 to 3, our extensive experimental findings emphasize the potential of multi-modal physiological data and highlight the necessity of representation learning via multi-modal Transformer architecture in clinical diagnosis.