Design, construction and evaluation of systems to predict risk in obstetrics

Lovell, D. R., Rosario, B., Niranjan, M., Prager, R. W., Dalton, K. J., Derom, R., & Chalmers, J. (1997) Design, construction and evaluation of systems to predict risk in obstetrics. International Journal of Medical Informatics, 46(3), pp. 159-173.

View at publisher

Abstract

We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy. We present a systematic, practical approach to developing risk prediction systems, suitable for use with large databases of medical information. An important part of this approach is a novel feature selection algorithm which uses the area under the receiver operating characteristic (ROC) curve to measure the expected discriminative power of different sets of predictor variables. We describe this algorithm and use it to select variables to predict risk of a specific adverse pregnancy outcome: failure to progress in labour. Neural network, logistic regression and hierarchical Bayesian risk prediction models are constructed, all of which achieve close to the limit of performance attainable on this prediction task. We show that better prediction performance requires more discriminative clinical information rather than improved modelling techniques. It is also shown that better diagnostic criteria in clinical records would greatly assist the development of systems to predict risk in pregnancy.

Impact and interest:

7 citations in Scopus
Search Google Scholar™
11 citations in Web of Science®

Citation counts are sourced monthly from Scopus and Web of Science® citation databases.

These databases contain citations from different subsets of available publications and different time periods and thus the citation count from each is usually different. Some works are not in either database and no count is displayed. Scopus includes citations from articles published in 1996 onwards, and Web of Science® generally from 1980 onwards.

Citations counts from the Google Scholar™ indexing service can be viewed at the linked Google Scholar™ search.

ID Code: 79858
Item Type: Journal Article
Refereed: Yes
Keywords: Failure to progress, Feature selection, Neural networks, Receiver operating characteristic (ROC), Risk prediction in pregnancy, Algorithms, Health risks, Hospital data processing, Mathematical models, Obstetrics, Regression analysis, Risk assessment, Bayesian risk prediction models, Medical computing, algorithm, article, artificial neural network, bayes theorem, data base, female, human, labor, medical information, prediction, pregnancy, pregnancy disorder, priority journal, receiver operating characteristic, Humans, Logistic Models, Models, Theoretical, Neural Networks (Computer), Obstetric Labor Complications, Pregnancy Complications, Risk, ROC Curve
DOI: 10.1016/S1386-5056(97)00068-3
ISSN: 13865056 (ISSN)
Divisions: Current > Schools > School of Electrical Engineering & Computer Science
Current > QUT Faculties and Divisions > Science & Engineering Faculty
Copyright Owner: Elsevier
Deposited On: 07 Jan 2015 04:01
Last Modified: 07 Jan 2015 04:01

Export: EndNote | Dublin Core | BibTeX

Repository Staff Only: item control page