A patient-driven adaptive prediction technique to improve personalized risk estimation for clinical decision support
Open Access
- 4 April 2012
- journal article
- research article
- Published by Oxford University Press (OUP) in Journal of the American Medical Informatics Association
- Vol. 19 (e1) , e137-e144
Abstract
Objective Competing tools are available online to assess the risk of developing certain conditions of interest, such as cardiovascular disease. While predictive models have been developed and validated on data from cohort studies, little attention has been paid to ensure the reliability of such predictions for individuals, which is critical for care decisions. The goal was to develop a patient-driven adaptive prediction technique to improve personalized risk estimation for clinical decision support. Material and methods A data-driven approach was proposed that utilizes individualized confidence intervals (CIs) to select the most ‘appropriate’ model from a pool of candidates to assess the individual patient's clinical condition. The method does not require access to the training dataset. This approach was compared with other strategies: the BEST model (the ideal model, which can only be achieved by access to data or knowledge of which population is most similar to the individual), CROSS model, and RANDOM model selection. Results When evaluated on clinical datasets, the approach significantly outperformed the CROSS model selection strategy in terms of discrimination (pLimitations The CI may not always offer enough information to rank the reliability of predictions, and this evaluation was done using aggregation. If a particular individual is very different from those represented in a training set of existing models, the CI may be somewhat misleading. Conclusion This approach has the potential to offer more reliable predictions than those offered by other heuristics for disease risk estimation of individual patients.Keywords
This publication has 39 references indexed in Scilit:
- Automated discovery of drug treatment patterns for endocrine therapy of breast cancer within an electronic medical recordJournal of the American Medical Informatics Association, 2012
- Calibrating predictive model estimates to support personalized medicineJournal of the American Medical Informatics Association, 2012
- Predicting the outcome of renal transplantationJournal of the American Medical Informatics Association, 2012
- Internet portal use in an academic multiple sclerosis centerJournal of the American Medical Informatics Association, 2012
- Using statistical and machine learning to help institutions detect suspicious access to electronic health recordsJournal of the American Medical Informatics Association, 2011
- The application of naive Bayes model averaging to predict Alzheimer's disease from genome-wide dataJournal of the American Medical Informatics Association, 2011
- Factors influencing alert acceptance: a novel approach for predicting the success of clinical decision supportJournal of the American Medical Informatics Association, 2011
- Personalized estimates of breast cancer risk in clinical practice and public healthStatistics in Medicine, 2011
- The ‘CaP Calculator’: an online decision support tool for clinically localized prostate cancerBJU International, 2010
- Is there an advantage in scoring early embryos on more than one day?Human Reproduction, 2009