Outlier-based detection of unusual patient-management actions: An ICU study.

Medical errors remain a significant problem in healthcare. This paper investigates a data-driven outlier-based monitoring and alerting framework that uses data in the Electronic Medical Records (EMRs) repositories of past patient cases to identify any unusual clinical actions in the EMR of a current patient. Our conjecture is that these unusual clinical actions correspond to medical errors often enough to justify their detection and alerting.

An Efficient Pattern Mining Approach for Event Detection in Multivariate Temporal Data.

This work proposes a pattern mining approach to learn event detection models from complex multivariate temporal data, such as electronic health records. We present Recent Temporal Pattern mining, a novel approach for efficiently finding predictive patterns for event detection problems. This approach first converts the time series data into time-interval sequences of temporal abstractions.

A Generalized Mixture Framework for Multi-label Classification.

We develop a novel probabilistic ensemble framework for multi-label classification that is based on the architecture. In this framework, we combine multi-label classification models in the that decompose the class posterior distribution (, …, |) using a product of posterior distributions over components of the output space. Our approach captures different input-output and output-output relations that tend to change across data.

A Temporal Pattern Mining Approach for Classifying Electronic Health Record Data.

We study the problem of learning classification models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to define a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classification features.

An Optimization-based Framework to Learn Conditional Random Fields for Multi-label Classification.

This paper studies multi-label classification problem in which data instances are associated with multiple, possibly high-dimensional, label vectors. This problem is especially challenging when labels are dependent and one cannot decompose the problem into a set of independent classification problems. To address the problem and properly represent label dependencies we propose and study a pairwise conditional random Field (CRF) model.

A Mixtures-of-Trees Framework for Multi-Label Classification.

We propose a new probabilistic approach for multi-label classification that aims to represent the class posterior distribution (|). Our approach uses a mixture of tree-structured Bayesian networks, which can leverage the computational advantages of conditional tree-structured models and the abilities of mixtures to compensate for tree-structured restrictions. We develop algorithms for learning the model from data and for performing multi-label predictions using the learned model.

Outlier detection for patient monitoring and alerting.

We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management decisions using past patient cases stored in electronic health records (EHRs). Our hypothesis is that a patient-management decision that is unusual with respect to past patient care may be due to an error and that it is worthwhile to generate an alert if such a decision is encountered. We evaluate this hypothesis using data obtained from EHRs of 4486 post-cardiac surgical patients and a subset of 222 alerts generated from the data.

A Pattern Mining Approach for Classifying Multivariate Temporal Data.

We study the problem of learning classification models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to define a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classification features.

A Bayesian Scoring Technique for Mining Predictive and Non-Spurious Rules.

Rule mining is an important class of data mining methods for discovering interesting patterns in data. The success of a rule mining method heavily depends on the evaluation function that is used to assess the quality of the rules. In this work, we propose a new rule evaluation score - the Predictive and Non-Spurious Rules (PNSR) score.

Mining Recent Temporal Patterns for Event Detection in Multivariate Time Series Data.

Improving the performance of classifiers using pattern mining techniques has been an active topic of data mining research. In this work we introduce the recent temporal pattern mining framework for finding predictive patterns for monitoring and event detection problems in complex multivariate time series data. This framework first converts time series into time-interval sequences of temporal abstractions.

Conditional outlier detection for clinical alerting.

We develop and evaluate a data-driven approach for detecting unusual (anomalous) patient-management actions using past patient cases stored in an electronic health record (EHR) system. Our hypothesis is that patient-management actions that are unusual with respect to past patients may be due to a potential error and that it is worthwhile to raise an alert if such a condition is encountered. We evaluate this hypothesis using data obtained from the electronic health records of 4,486 post-cardiac surgical patients.

Mining Clinical Data using Minimal Predictive Rules.

Modern hospitals and health-care institutes collect huge amounts of clinical data. Those who deal with such data know that there is a widening gap between data collection and data comprehension. Thus, it is very important to develop data mining techniques capable of automatically extracting useful knowledge to support clinical decision-making in various diagnostic and patient-management tasks.

A temporal abstraction framework for classifying clinical temporal data.

The increasing availability of complex temporal clinical records collected today has prompted the development of new methods that extend classical machine learning and data mining approaches to time series data. In this work, we develop a new framework for classifying the patient's time-series data based on temporal abstractions. The proposed STF-Mine algorithm automatically mines discriminative temporal abstraction patterns from the data and uses them to learn a classification model.