Towards actionable risk stratification: A bilinear approach
| Autor: | Robert Sorrentino, Xiang Wang, Fei Wang, Jianying Hu |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Male
medicine.medical_specialty Multivariate analysis Health Informatics Context (language use) computer.software_genre Risk Assessment Clinical decision support system Decision Support Techniques Cohort Studies Risk Factors Odds Ratio Electronic Health Records Humans Medicine Intensive care medicine Heart Failure Principal Component Analysis Framingham Risk Score business.industry Odds ratio Computer Science Applications ROC Curve Case-Control Studies Multivariate Analysis Cohort Female Programming Languages Data mining business Risk assessment computer Algorithms Medical Informatics Software Cohort study |
| Zdroj: | Journal of Biomedical Informatics. 53:147-155 |
| ISSN: | 1532-0464 |
| DOI: | 10.1016/j.jbi.2014.10.004 |
| Popis: | Display Omitted Bilinear risk prediction model for EHR data.Low-dimensional embedding of patients in a learned risk space.Identification of meaningful clinical contexts.Significant improvement in accuracy over existing risk prediction model. Risk stratification is instrumental to modern clinical decision support systems. Comprehensive risk stratification should be able to provide the clinicians with not only the accurate assessment of a patient's risk but also the clinical context to be acted upon. However, existing risk stratification techniques mainly focus on predicting the risk score for individual patients; at the cohort level, they offer little insight beyond a flat score-based segmentation. This essentially reduces a patient to a score and thus removes him/her from his/her clinical context. To address this limitation, in this paper we propose a bilinear model for risk stratification that simultaneously captures the three key aspects of risk stratification: (1) it predicts the risk of each individual patient; (2) it stratifies the patient cohort based on not only the risk score but also the clinical characteristics; and (3) it embeds all patients into clinical contexts with clear interpretation. We apply our model to a cohort of 4977 patients, 1127 among which were diagnosed with Congestive Heart Failure (CHF). We demonstrate that our model cannot only accurately predict the onset risk of CHF but also provide rich and actionable clinical insights into the patient cohort. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect