Modeling Rare Interactions in Time Series Data Through Qualitative Change: Application to Outcome Prediction in Intensive Care Units

TY - CHAP

T1 - Modeling Rare Interactions in Time Series Data Through Qualitative Change: Application to Outcome Prediction in Intensive Care Units

AU - Ibrahim, Zina

AU - Dobson, Richard

AU - Wu, Honghan

PY - 2020/1/14

Y1 - 2020/1/14

N2 - Many areas of research are characterised by the deluge of large-scale highly-dimensional time-series data. However, using the data available for prediction and decision making is hampered by the current lag in our ability to uncover and quantify true interactions that explain the outcomes. We are interested in areas such as intensive care medicine, which are characterised by i) continuous monitoring of multivariate variables and non-uniform sampling of data streams, ii) the outcomes are generally governed by interactions between a small set of rare events, iii) these interactions are not necessarily de- finable by specific values (or value ranges) of a given group of variables, but rather, by the deviations of these values from the normal state recorded over time, iv) the need to explain the predictions made by the model. Here, while numerous data mining models have been formulated for outcome prediction, they are unable to explain their predictions.We present a model for uncovering interactions with the highest likelihood of generating the outcomes seen from highly-dimensional time series data. Interactions among variables are represented by a relational graph structure, which relies on qualitative abstractions to overcome non-uniform sampling and to capture the semantics of the interactions corresponding to the changes and deviations from normality of variables of interest over time. Using the assumption that similar templates of small interactions are responsible for the out- comes (as prevalent in the medical domains), we reformulate the discovery task to retrieve the most-likely templates from the data. Experiments on sepsis prediction using real Intensive Care Unit (ICU) data demonstrates that the discovered interaction templates are se- mantically meaningful within the domain, and using them as features in a prediction task produces a superior performance than when using the raw values of the predictors.

AB - Many areas of research are characterised by the deluge of large-scale highly-dimensional time-series data. However, using the data available for prediction and decision making is hampered by the current lag in our ability to uncover and quantify true interactions that explain the outcomes. We are interested in areas such as intensive care medicine, which are characterised by i) continuous monitoring of multivariate variables and non-uniform sampling of data streams, ii) the outcomes are generally governed by interactions between a small set of rare events, iii) these interactions are not necessarily de- finable by specific values (or value ranges) of a given group of variables, but rather, by the deviations of these values from the normal state recorded over time, iv) the need to explain the predictions made by the model. Here, while numerous data mining models have been formulated for outcome prediction, they are unable to explain their predictions.We present a model for uncovering interactions with the highest likelihood of generating the outcomes seen from highly-dimensional time series data. Interactions among variables are represented by a relational graph structure, which relies on qualitative abstractions to overcome non-uniform sampling and to capture the semantics of the interactions corresponding to the changes and deviations from normality of variables of interest over time. Using the assumption that similar templates of small interactions are responsible for the out- comes (as prevalent in the medical domains), we reformulate the discovery task to retrieve the most-likely templates from the data. Experiments on sepsis prediction using real Intensive Care Unit (ICU) data demonstrates that the discovered interaction templates are se- mantically meaningful within the domain, and using them as features in a prediction task produces a superior performance than when using the raw values of the predictors.

M3 - Conference paper

BT - Proceedings of the European Conference of Artificial Intelligence (ECAI 2020)

ER -