• Corpus ID: 236171229

On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit

  title={On the Use of Time Series Kernel and Dimensionality Reduction to Identify the Acquisition of Antimicrobial Multidrug Resistance in the Intensive Care Unit},
  author={{\'O}scar Escudero-Arnanz and Joaqu'in Rodr'iguez-'Alvarez and Karl {\O}yvind Mikalsen and Robert Jenssen and Cristina Soguero-Ru{\'i}z},
The acquisition of Antimicrobial Multidrug Resistance (AMR) in patients admitted to the Intensive Care Units (ICU) is a major global concern. This study analyses data in the form of multivariate time series (MTS) from 3476 patients recorded at the ICU of University Hospital of Fuenlabrada (Madrid) from 2004 to 2020. 18% of the patients acquired AMR during their stay in the ICU. The goal of this paper is an early prediction of the development of AMR. Towards that end, we leverage the time-series… 

Figures and Tables from this paper


Data-driven Temporal Prediction of Surgical Site Infection
Using a matched cohort of patients undergoing gastrointestinal surgery, a prediction model for post-operative surgical site infections (SSIs) is built using Gaussian process regression, time warping and imputation methods to manage the sparsity of the data source, and support vector machines for classification.
Predicting colorectal surgical complications using heterogeneous clinical data and kernel methods
A machine-learning statistical model from EHR data can be useful to predict surgical complications and the combination of EHR extracted free text, blood samples values, and patient vital signs, improves the model performance.
Antimicrobial resistance: a global multifaceted phenomenon
This review focuses on antibacterial resistance (ABR), which represents at the moment the major problem, both for the high rates of resistance observed in bacteria that cause common infections and for the complexity of the consequences of ABR.
Experimental comparison of representation methods and distance measures for time series data
An extensive experimental study re-implementing eight different time series representations and nine similarity measures and their variants and testing their effectiveness on 38 time series data sets from a wide variety of application domains gives an overview of these different techniques and presents comparative experimental findings regarding their effectiveness.
Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data
This paper proposes the robust time series cluster kernel (TCK), which leverages the missing data handling properties of Gaussian mixture models augmented with informative prior distributions to ensure robustness to parameters.
Use of a K-nearest neighbors model to predict the development of type 2 diabetes within 2 years in an obese, hypertensive population
A prognostic model was built that accurately identified obese, hypertensive patients at risk for developing type 2 diabetes mellitus within a 2-year period and may help health care providers make more informed decisions.
Unsupervised pattern discovery in electronic health care data using probabilistic clustering models
A probabilistic clustering model designed to mitigate the effects of temporal sparsity inherent in electronic health care records data is developed and results indicate that the model can discover distinct, recognizable physiologic patterns with prognostic significance.
Time series cluster kernels to exploit informative missingness and incomplete label information
This work creates a representation of the missing pattern, which is incorporated into mixed mode mixture models in such a way that the information provided by the missing patterns is effectively exploited, and proposes a semi-supervised kernel, capable of taking advantage of incomplete label information to learn more accurate similarities.
Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission
This work presents two case studies where high-performance generalized additive models with pairwise interactions (GA2Ms) are applied to real healthcare problems yielding intelligible models with state-of-the-art accuracy.
Data-Driven Visual Characterization of Patient Health-Status Using Electronic Health Records and Self-Organizing Maps
The proposed methodology showed to be effective to explore relationships within clinical data and to find patterns related to diabetes and hypertension in a visual way, becoming a promising approach to be applied to any population due to its data-driven philosophy.