Prognosis of Clinical Outcomes with Temporal Patterns and Experiences with One Class Feature Selection

Abstract

Accurate prognosis of outcome events, such as clinical procedures or disease diagnosis, is central in medicine. The emergence of longitudinal clinical data, like the Electronic Health Records (EHR), represents an opportunity to develop automated methods for predicting patient outcomes. However, these data are highly dimensional and very sparse, complicating the application of predictive modeling techniques. Further, their temporal nature is not fully exploited by current methods, and temporal abstraction was recently used which results in symbolic time intervals representation. We present Maitreya, a framework for the prediction of outcome events that leverages these symbolic time intervals. Using Maitreya, learn predictive models based on the temporal patterns in the clinical records that are prognostic markers and use these markers to train predictive models for eight clinical procedures. In order to decrease the number of patterns that are used as features, we propose the use of three one class feature selection methods. We evaluate the performance of Maitreya under several parameter settings, including the one-class feature selection, and compare our results to that of atemporal approaches. In general, we found that the use of temporal patterns outperformed the atemporal methods, when representing the number of pattern occurrences.

Figure 1

An example of a Time Intervals Related Pattern (TIRP), containing a sequence of four lexicographically ordered symbolic time intervals and all of their pair-wise temporal relations shown on the right half matrix.

Figure 2

Maitreya, a framework for outcomes prediction. A cohort set of patients having the outcome is constructed, and a corresponding control group of patients who don’t have the outcome. One fold is used to discover frequent TIRPs using KarmaLego. SingleKarma-Lego detects the TIRPs that were selected by the One Class Feature Selection at the other two folds of the cohort and controls are used to detect these TIRPs. Then a matrix is constructed on which 10 folds cross validation classification is performed. Finally, once a new patient arrives his TIRPs are detected using SIngleKarmaLego and given to the induced classifier classifier.