Personalized Modeling for Prediction with Decision-Path Models

Deriving predictive models in medicine typically relies on a population approach where a single model is developed from a dataset of individuals. In this paper we describe and evaluate a personalized approach in which we construct a new type of decision tree model called decision-path model that takes advantage of the particular features of a given person of interest. We introduce three personalized methods that derive personalized decision-path models. We compared the performance of these methods to that of Classification And Regression Tree (CART) that is a population decision tree to predict seven different outcomes in five medical datasets. Two of the three personalized methods performed statistically significantly better on area under the ROC curve (AUC) and Brier skill score compared to CART. The personalized approach of learning decision path models is a new approach for predictive modeling that can perform better than a population approach.

[1]  M. Fine,et al.  Processes and outcomes of care for patients with community-acquired pneumonia: results from the Pneumonia Patient Outcomes Research Team (PORT) cohort study. , 1999, Archives of internal medicine.

[2]  Shyam Visweswaran,et al.  Decision Path Models for Patient-Specific Modeling of Patient Outcomes , 2013, AMIA.

[3]  Winnie S. Liang,et al.  GAB2 Alleles Modify Alzheimer's Risk in APOE ɛ4 Carriers , 2007, Neuron.

[4]  Sreerama K. Murthy,et al.  Automatic Construction of Decision Trees from Data: A Multi-Disciplinary Survey , 1998, Data Mining and Knowledge Discovery.

[5]  John A Kellum,et al.  Understanding the inflammatory cytokine response in pneumonia and sepsis: results of the Genetic and Inflammatory Markers of Sepsis (GenIMS) Study. , 2007, Archives of internal medicine.

[6]  Shyam Visweswaran,et al.  Patient-Specific Models for Predicting the Outcomes of Patients with Community Acquired Pneumonia , 2005, AMIA.

[7]  W. Briggs.  Statistical Methods in the Atmospheric Sciences , 2007 .

[8]  Gregory F Cooper,et al.  A prediction rule to identify low-risk patients with heart failure. , 2005, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[9]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[10]  David G. Stork,et al.  Pattern Classification , 1973 .

[11]  David Maxwell Chickering,et al.  Learning Bayesian Networks: The Combination of Knowledge and Statistical Data , 1994, Machine Learning.

[12]  Carlos A Camargo,et al.  Risk stratification for hospitalization in acute asthma: the CHOP classification tree. , 2010, The American journal of emergency medicine.

[13]  Qing-ke Huang,et al.  Prediction of Severe Acute Pancreatitis Using Classification and Regression Tree Analysis , 2011, Digestive Diseases and Sciences.

[14]  Shyam Visweswaran,et al.  Learning Instance-Specific Predictive Models , 2010, J. Mach. Learn. Res..

[15]  Winnie S. Liang,et al.  GAB2 alleles modify Alzheimer's risk in APOE epsilon4 carriers. , 2007, Neuron.

[16]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[17]  Shyam Visweswaran,et al.  Learning patient-specific predictive models from clinical data , 2010, J. Biomed. Informatics.

[18]  M. Ebell,et al.  The use of classification and regression trees to predict the likelihood of seasonal influenza. , 2012, Family practice.

[19]  Gilles Clermont,et al.  Outlier detection for patient monitoring and alerting , 2013, J. Biomed. Informatics.

[20]  Ron Kohavi,et al.  Lazy Decision Trees , 1996, AAAI/IAAI, Vol. 1.

[21]  Vili Podgorelec,et al.  Decision Trees: An Overview and Their Use in Medicine , 2002, Journal of Medical Systems.

[22]  Usama M. Fayyad,et al.  Multi-Interval Discretization of Continuous-Valued Attributes for Classification Learning , 1993, IJCAI.

[23]  Shyam Visweswaran,et al.  Instance-Specific Bayesian Model Averaging for Classification , 2004, NIPS.