A Comparison of Dimensionality Reduction Techniques for Unstructured Clinical Text

Abstract

Much of clinical data is free text, which is challenging to use together with machine learning, visualization tools, and clinical decision rules. In this paper, we compare supervised and unsupervised dimensionality reduction techniques, including the recently proposed sLDA and MedLDA algorithms, on clinical texts. We evaluate each dimensionality reduction method by using them as features for two important prediction problems that arise in emergency departments: predicting whether a patient has an infection, which can progress to sepsis, and predicting the likelihood of a patient being admitted to the Intensive Care Unit (used for risk stratification). We find that, on this data, existing supervised dimensionality reduction techniques perform better than unsupervise techniques only for very low dimensional representations.

Publication
ICML 2012 Workshop on Clinical Data Analysis
Yoni Halpern
Yoni Halpern
PhD student

Google Research

David Sontag
David Sontag
Associate Professor of EECS

My research focuses on advancing machine learning and artificial intelligence, and using these to transform health care.

Related