Building and Interpreting Risk Models from Imbalanced Clinical Data
Authors:
- Aaron N RichterARAaron N Richter
- Taghi M KhoshgoftaarTKTaghi M Khoshgoftaar
- 1 November 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 143-150
Abstract
As more clinical data becomes available for research, it is important to be able to build effective models and understand the predictions made from them. In this paper, we present a case study modeling melanoma risk using structured clinical records. Advanced modeling techniques are required as the data set is large, sparse, and imbalanced. We explore the use of logistic regression, decision tree, and random forest classifiers with various feature selection and random undersampling techniques. For clinical models to be used in practice, both providers and patients should have insight into why a certain prediction is made. Therefore, interpretability must be a key factor when choosing a model for a clinical prediction task, and we explore the level of interpretation given by the models compared to their predictive performance.Keywords
This publication has 25 references indexed in Scilit:
- A survey of open source tools for machine learning with big data in the Hadoop ecosystemJournal of Big Data, 2015
- Risk Prediction Models for Melanoma: A Systematic ReviewCancer Epidemiology, Biomarkers & Prevention, 2014
- A review of data mining using big data in health informaticsJournal of Big Data, 2014
- Where Are We on the Diffusion Curve? Trends and Drivers of Primary Care Physicians' Use of Health Information TechnologyHealth Services Research, 2013
- Individualized Risk Prediction Model for Lung Cancer in Korean MenPLOS ONE, 2013
- Identifying individuals at high risk of melanoma: a simple toolEuropean Journal Of Cancer Prevention, 2010
- Experimental perspectives on learning from imbalanced data2007
- Improved prediction of recurrence after curative resection of colon carcinoma using tree‐based risk stratificationCancer, 2004
- Focus on melanomaCancer Cell, 2002
- LOGISTIC REGRESSION MODELING OF SOFTWARE QUALITYInternational Journal of Reliability, Quality and Safety Engineering, 1999