# An Unsupervised Multivariate Time Series Kernel Approach for Identifying Patients with Surgical Site Infection from Blood Samples

## TL;DR

This paper introduces an unsupervised kernel-based method for detecting surgical site infections from multivariate blood sample time series, effectively handling missing data without requiring labeled training data.

## Contribution

It presents a novel unsupervised framework using multivariate time series kernels that directly manage missing data, eliminating the need for data imputation.

## Key findings

- Outperforms baseline methods that rely on imputation
- Performs comparably to supervised classifiers
- Effective in identifying infections from blood sample sequences

## Abstract

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.