Robust prediction of patient mortality from 48 hour intensive care unit data

Luigi Yuri Di Marco, Marjan Bojarnejad, Susan T. King, Wenfeng Duan, Costanzo Di Maria, Dingchang Zheng, Alan Murray, Philip Langley

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

1 Citation (Scopus)


The aim of this study was to develop a new algorithm to predict individual patient mortality with improved accuracy with respect to established methods from data collected over the first 48 hours of admission to the Intensive Care Unit. A binary classifier was developed to participate in Event 1 of the PhysioNet/Computing in Cardiology Challenge 2012. The algorithm development was undertaken using only posterior knowledge from the training dataset (Set-A), containing 41 demographic and clinical variables from 4000 ICU patients. For each variable a feature was defined as the average (across all available measurements of the given variable) likelihood of being part of the 'survivors' group. To select features with highest discrimination ability ('survivors' vs. 'non-survivors'), a forward sequential selection criterion with logistic cost function was adopted and repeated for cross-validation on N (=10) 'leave Mout' (M=50%) random partitions of Set-A. Features that were selected in more than one partition were considered (#Feat = 32). A logistic regression model was used for classification. The score was defined as the lowest between sensitivity and positive predictive value in classification. The proposed method scored 54.9% on Set-A and 44.0% on the test set (Set-B), outperforming the established method SAPS-I (29.6% on Set-A, 31.7% on Set-B).

Original languageEnglish
Title of host publicationComputing in Cardiology 2012, CinC 2012
Number of pages4
ISBN (Electronic) 9781467320771
ISBN (Print)9781467320740
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event39th Computing in Cardiology Conference, CinC 2012 - Krakow, Poland
Duration: 9 Sept 201212 Sept 2012

Publication series

NameComputing in Cardiology
ISSN (Print)2325-8861
ISSN (Electronic)2325-887X


Conference39th Computing in Cardiology Conference, CinC 2012

ASJC Scopus subject areas

  • Computer Science(all)
  • Cardiology and Cardiovascular Medicine


Dive into the research topics of 'Robust prediction of patient mortality from 48 hour intensive care unit data'. Together they form a unique fingerprint.

Cite this