Prediction using patient comparison vs. modeling: A case study for mortality prediction

M. Hoogendoorn, Ali El Hassouni, Kwongyen Mok, Marzyeh Ghassemi, Peter Szolovits

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Information in Electronic Medical Records (EMRs) can be used to generate accurate predictions for the occurrence of a variety of health states, which can contribute to more pro-active interventions. The very nature of EMRs does make the application of off-the-shelf machine learning techniques difficult. In this paper, we study two approaches to making predictions that have hardly been compared in the past: (1) extracting high-level (temporal) features from EMRs and building a predictive model, and (2) defining a patient similarity metric and predicting based on the outcome observed for similar patients. We analyze and compare both approaches on the MIMIC-II ICU dataset to predict patient mortality and find that the patient similarity approach does not scale well and results in a less accurate model (AUC of 0.68) compared to the modeling approach (0.84). We also show that mortality can be predicted within a median of 72 hours.

Original languageEnglish
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers, Inc.
Pages2464-2467
Number of pages4
Volume2016-October
ISBN (Electronic)9781457702204
DOIs
Publication statusPublished - 13 Oct 2016
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: 16 Aug 201620 Aug 2016

Conference

Conference38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period16/08/1620/08/16

Fingerprint Dive into the research topics of 'Prediction using patient comparison vs. modeling: A case study for mortality prediction'. Together they form a unique fingerprint.

Cite this