An Analytical Framework for TJR Readmission Prediction and Cost-Effective Intervention

This paper introduces an analytical framework for assessing the cost-effectiveness of intervention strategies to reduce total joint replacement (TJR) readmissions. In such a framework, a machine learning-based readmission risk prediction model is developed to predict an individual TJR patient's risk of hospital readmission within 90 days post-discharge. Specifically, through data sampling and boosting techniques, we overcome the class imbalance problem by iteratively building an ensemble of models. Then, utilizing the results of the predictive model, and by taking into account the imbalanced misclassification costs between readmitted and nonreadmitted patients, a cost analysis framework is introduced to support decision making in selecting cost-effective intervention policies. Finally, using this framework, a case study at a community hospital is presented to demonstrate the applicability of the analysis.

[1]  Steven M. Kurtz,et al.  SYMPOSIUM: ABJS CARL T. BRIGHTON WORKSHOP ON HEALTH POLICY ISSUES IN ORTHOPAEDIC SURGERY Future Young Patient Demand for Primary and Revision Joint Replacement , 2009 .

[2]  Glenn Fung,et al.  Predicting Readmission Risk with Institution Specific Prediction Models , 2013, ICHI.

[3]  Shigeru Katagiri,et al.  Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification , 2017, IEEE Transactions on Knowledge and Data Engineering.

[4]  Thomas P Vail,et al.  What Are the Rates and Causes of Hospital Readmission After Total Knee Arthroplasty? , 2014, Clinical orthopaedics and related research.

[5]  Javad Parvizi,et al.  Unplanned readmission after total joint arthroplasty: rates, reasons, and risk factors. , 2013, The Journal of bone and joint surgery. American volume.

[6]  C. Ko,et al.  Factors predicting complication rates following total knee replacement. , 2006, The Journal of bone and joint surgery. American volume.

[7]  Robert Chen,et al.  Patient Stratification Using Electronic Health Records from a Chronic Disease Management Program. , 2016, IEEE journal of biomedical and health informatics.

[8]  Johannes Gehrke,et al.  Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission , 2015, KDD.

[9]  Gary M. Weiss,et al.  Cost-Sensitive Learning vs. Sampling: Which is Best for Handling Unbalanced Classes with Unequal Error Costs? , 2007, DMIN.

[10]  Amanda H. Salanitro,et al.  Risk prediction models for hospital readmission: a systematic review. , 2011, JAMA.

[11]  Doina Precup,et al.  Assessing the Predictability of Hospital Readmission Using Machine Learning , 2013, IAAI.

[12]  Chi-Hyuck Jun,et al.  Instance categorization by support vector machines to adjust weights in AdaBoost for imbalanced data classification , 2017, Inf. Sci..

[13]  Robert C. Holte,et al.  Cost curves: An improved method for visualizing classifier performance , 2006, Machine Learning.

[14]  Robert C. Holte,et al.  Explicitly representing expected cost: an alternative to ROC representation , 2000, KDD '00.

[15]  Joshua D. Harris,et al.  Causes and Rates of Unplanned Readmissions After Elective Primary Total Joint Arthroplasty: A Systematic Review and Meta-Analysis. , 2015, American journal of orthopedics.

[16]  Joseph Futoma,et al.  A comparison of models for predicting early hospital readmissions , 2015, J. Biomed. Informatics.

[17]  Francisco Herrera,et al.  A Review on Ensembles for the Class Imbalance Problem: Bagging-, Boosting-, and Hybrid-Based Approaches , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[18]  Yuan Feng,et al.  Modeling and analysis of postoperative intervention process for total joint replacement patients using simulations , 2017, 2017 13th IEEE Conference on Automation Science and Engineering (CASE).

[19]  Maureen A. Smith,et al.  Bouncing Back: Patterns and Predictors of Complicated Transitions 30 Days After Hospitalization for Acute Ischemic Stroke , 2007, Journal of the American Geriatrics Society.

[20]  Taghi M. Khoshgoftaar,et al.  Comparing Boosting and Bagging Techniques With Noisy and Imbalanced Data , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[21]  Jinsung Yoon,et al.  Discovery and Clinical Decision Support for Personalized Healthcare , 2017, IEEE Journal of Biomedical and Health Informatics.

[22]  Amit G Singal,et al.  A Primer on Predictive Models , 2014, Clinical and Translational Gastroenterology.

[23]  Hoangmai H Pham,et al.  Care patterns in Medicare and their implications for pay for performance. , 2007, The New England journal of medicine.

[24]  David A. Cieslak,et al.  Learning Decision Trees for Unbalanced Data , 2008, ECML/PKDD.

[25]  Zhi-Hua Zhou,et al.  The Influence of Class Imbalance on Cost-Sensitive Learning: An Empirical Study , 2006, Sixth International Conference on Data Mining (ICDM'06).

[26]  Lior Rokach,et al.  Ensemble-based classifiers , 2010, Artificial Intelligence Review.

[27]  B. Starfield,et al.  Prevalence, expenditures, and complications of multiple chronic conditions in the elderly. , 2002, Archives of internal medicine.

[28]  N. Cook.  Use and Misuse of the Receiver Operating Characteristic Curve in Risk Prediction , 2007, Circulation.

[29]  Taghi M. Khoshgoftaar,et al.  RUSBoost: A Hybrid Approach to Alleviating Class Imbalance , 2010, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[30]  John J Callaghan,et al.  Incidence of and risk factors for 30-day readmission following elective primary total joint arthroplasty: analysis from the ACS-NSQIP. , 2013, The Journal of arthroplasty.

[31]  Foster J. Provost,et al.  Learning When Training Data are Costly: The Effect of Class Distribution on Tree Induction , 2003, J. Artif. Intell. Res..