Automatic Identification of Surgery Indicators

This study investigates the possibility of using data mining techniques to find indicators that can help to estimate future patient demand. By extracting certain information from medical records, we believe that the need for surgery can be predicted. We hypothesize that the generated models may provide new knowledge about, and a basis for, how to structure patient information when referring patients from the general practitioner to hospital care. We conduct an experiment in which we compare ten supervised learning algorithms on a data set of 80 hip arthrosis patients. The data set has been generated by manually extracting information from unstructured patient records. The empirical results are promising, indicating that it is possible, as early as during the referral stage, to accurately predict the need for surgery.

[1]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[2]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[3]  Thomas T. H. Wan,et al.  Healthcare Informatics Research: From Data to Evidence-Based Management , 2006, Journal of Medical Systems.

[4]  Ulf Johansson,et al.  Obtaining Accurate and Comprehensible Data Mining Models: An Evolutionary Approach , 2007 .

[5]  Mary K Obenshain.  Application of Data Mining Techniques to Healthcare Data , 2004, Infection Control & Hospital Epidemiology.

[6]  Marie Persson,et al.  Identification of Surgery Indicators by Mining Hospital Data: A Preliminary Study , 2009, 2009 20th International Workshop on Database and Expert Systems Application.

[7]  John T. Blake,et al.  A comprehensive simulation for wait time reduction and capacity planning applied in general surgery , 2007, Health care management science.

[8]  Rob J. Kusters,et al.  Towards Decision Support for Waiting Lists: An Operations Management View , 2001, Health care management science.

[9]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[10]  Erik Demeulemeester,et al.  Operating room planning and scheduling: A literature review , 2010, Eur. J. Oper. Res..

[11]  James P. Egan,et al.  Signal detection theory and ROC analysis , 1975 .

[12]  Marie Jeanette Persson,et al.  Analysing management policies for operating room planning using simulation , 2010, Health care management science.

[13]  M Tavakoli,et al.  Referral rates and waiting lists: some empirical evidence. , 1998, Health economics.

[14]  Balaji Rajagopalan,et al.  Data Mining to Support Simulation Modeling of Patient Flow in Hospitals , 2002, Journal of Medical Systems.

[15]  Marion S. Rauner,et al.  OR applied to health services: Planning for the future with scarce resources , 2003, Eur. J. Oper. Res..

[16]  Yoav Freund,et al.  Experiments with a New Boosting Algorithm , 1996, ICML.

[17]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Data Mining Researchers , 2003 .

[18]  Tom Fawcett,et al.  Analysis and Visualization of Classifier Performance: Comparison under Imprecise Class and Cost Distributions , 1997, KDD.

[19]  Ron Kohavi,et al.  The Case against Accuracy Estimation for Comparing Induction Algorithms , 1998, ICML.

[20]  Samuel Ingraham Davies.  Machine learning at the operating room of the future : a comparison of machine learning techniques applied to operating room scheduling , 2004 .

[21]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[22]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[23]  Sheldon Howard Jacobson,et al.  Application of discrete-event simulation in health care clinics: A survey , 1999, J. Oper. Res. Soc..

[24]  J. Kellgren,et al.  Radiological Assessment of Osteo-Arthrosis , 1957, Annals of the rheumatic diseases.

[25]  M. Stone.  Cross‐Validatory Choice and Assessment of Statistical Predictions , 1976 .

[26]  Paul Davidsson,et al.  Evaluating learning algorithms and classifiers , 2007, Int. J. Intell. Inf. Database Syst..

[27]  Isabel M. Ramos,et al.  Applying Data Mining to Software Development Projects: A Case Study , 2004, ICEIS.

[28]  Brian R. Gaines,et al.  Induction of ripple-down rules applied to modeling large databases , 1995, Journal of Intelligent Information Systems.

[29]  David W. Aha,et al.  Instance-Based Learning Algorithms , 1991, Machine Learning.

[30]  Ronen Feldman,et al.  Book Reviews: The Text Mining Handbook: Advanced Approaches to Analyzing Unstructured Data by Ronen Feldman and James Sanger , 2008, CL.

[31]  Y A Ozcan,et al.  Towards a science of the management of health care , 1998, Health care management science.