An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples
This work addresses the challenge of infection detection in healthcare without requiring labeled data, which is often scarce, though it is incremental as it applies existing kernel methods to a specific domain.
The paper tackled the problem of detecting surgical site infections in colorectal cancer surgery patients using unsupervised analysis of multivariate blood test time series with missing data, achieving performance comparable to supervised methods and superior to imputation-based baselines.
A large fraction of the electronic health records consists of clinical measurements collected over time, such as blood tests, which provide important information about the health status of a patient. These sequences of clinical measurements are naturally represented as time series, characterized by multiple variables and the presence of missing data, which complicate analysis. In this work, we propose a surgical site infection detection framework for patients undergoing colorectal cancer surgery that is completely unsupervised, hence alleviating the problem of getting access to labelled training data. The framework is based on powerful kernels for multivariate time series that account for missing data when computing similarities. Our approach show superior performance compared to baselines that have to resort to imputation techniques and performs comparable to a supervised classification baseline.