Categorization of phenotype trajectories utilizing transformers on clinical time-series

Abstract

Patients being admitted to a hospital will most often be associated with a certain clinical development during their stay. However, there is always a risk of patients being subject to the wrong diagnosis or to a certain treatment not pertaining to the desired effect, potentially leading to adverse events. Thus, there is a need to develop an anomaly detection system for deviations from expected clinical progress. As a first step towards this goal we have considered methods for categorization of typical developments, coined phenotype trajectories. We analyzed 16 months of vital sign recordings obtained from the Nordland Hospital Trust (NHT), where we employed an self-supervised framework based on the STraTS transformer architecture to represent the time series data in a latent space. These representations were then subjected to various clustering techniques to explore potential phenotype trajectories. While our preliminary results from this ongoing research are promising, they underscore the importance of enhancing the dataset with additional demographic information from patients. This additional data will be crucial for a more comprehensive evaluation of the method’s performance. Our data preprocessing and model implementation are available at <a href=https://github.com/helgeingvart/phenotypeTrajectories>https://github.com/helgeingvart/phenotypeTrajectories</a>.