DRG grouping by machine learning: from expert-oriented to data-based method

Background Diagnosis-related groups (DRGs) are a payment system that could effectively solve the problem of excessive increases in healthcare costs which are applied as a principal measure in the healthcare reform in China. However, expert-oriented DRG grouping is a black box with the drawbacks of upcoding and high cost. Methods This study proposes a method of data-based grouping, designed and updated by machine learning algorithms, which could be trained by real cases, or even simulated cases. It inherits the decision-making rules from the expert-oriented grouping and improves performance by incorporating continuous updates at low cost. Five typical classification algorithms were assessed and some suggestions were made for algorithm choice. The kappa coefficients were reported to evaluate the performance of grouping. Results Based on tenfold cross-validation, experiments showed that data-based grouping had a similar classification performance to the expert-oriented grouping when choosing suitable algorithms. The groupings trained by simulated cases had less accuracy when they were tested by the real cases rather than simulated cases, but the kappa coefficients of the best model were still higher than 0.6. When the grouping was tested in a new DRGs system, the average kappa coefficients were significantly improved from 0.1534 to 0.6435 by the update; and with enough computation resources, the update process could be completed in a very short time. Conclusions As a new potential option, the data-based grouping meets the requirements of the DRGs system and has the advantages of high transparency and low cost in the design and update process.

[1]  Classification and Regression Trees , 2000 .

[2]  Mehmed Kantardzic,et al.  Data-Mining Concepts , 2011 .

[3]  Jessica C. Teets,et al.  The state of the field for governance and policy innovation in China , 2020, Journal of Chinese Governance.

[4]  S. Hölzer,et al.  Introducing Diagnosis-Related Groups in Kazakhstan: Evolution, achievements, and challenges. , 2016, Health policy.

[5]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[6]  Kevin Quinn.  After the Revolution: DRGs at Age 30 , 2014, Annals of Internal Medicine.

[7]  Chengwu Shen,et al.  Diagnosis-related group (DRG)-based case-mix funding system, a promising alternative for fee for service payment in China. , 2018, Bioscience trends.

[8]  Publisher's Note , 2018, Anaesthesia.

[9]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[10]  R. Bal,et al.  Performance regulation in a networked healthcare system: From cosmetic to institutionalized compliance , 2020, Public Administration.

[11]  Sean P Roddy,et al.  Inpatient coding and the diagnosis-related group. , 2017, Journal of vascular surgery.

[12]  P. Barros,et al.  Upcoding in a National Health Service: the evidence from Portugal , 2016, Health economics.

[13]  Tianqi Chen,et al.  XGBoost: A Scalable Tree Boosting System , 2016, KDD.

[14]  Jay Pan,et al.  10 years of health-care reform in China: progress and gaps in Universal Health Coverage , 2019, The Lancet.

[15]  K. Zou,et al.  The effects of diagnosis-related groups payment on hospital healthcare in China: a systematic review , 2020, BMC Health Services Research.

[16]  Norbert Goldfield,et al.  The Evolution of Diagnosis‐Related Groups (DRGs): From Its Beginnings in Case‐Mix and Resource Use Theory, to Its Implementation for Payment and Now for Its Current Utilization for Quality Within and Outside the Hospital , 2010, Quality management in health care.

[17]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[18]  R. Busse,et al.  Appendectomy and diagnosis-related groups (DRGs): patient classification and hospital reimbursement in 11 European countries , 2011, Langenbeck's Archives of Surgery.

[19]  Ron Artstein.  Inter-Coder Agreement for Computational Linguistics , 2008 .

[20]  Iris Wallenburg,et al.  Opening the black box of diagnosis-related groups (DRGs): unpacking the technical remuneration structure of the Dutch DRG system. , 2018, Health economics, policy, and law.

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

[22]  Karl P. Pfeiffer,et al.  Regression tree construction by bootstrap: Model search for DRG-systems applied to Austrian health-data , 2010, BMC Medical Informatics Decis. Mak..

[23]  Paul J M Steinbusch,et al.  The risk of upcoding in casemix systems: a comparative study. , 2007, Health policy.

[24]  D. Ruppert.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[25]  F. Wittenbecher,et al.  Hospital payment systems based on diagnosis-related groups: experiences in low- and middle-income countries. , 2013, Bulletin of the World Health Organization.

[26]  Da Huo,et al.  A machine learning model to classify aortic dissection patients in the early diagnosis phase , 2019, Scientific Reports.

[27]  Rema Padman,et al.  Machine Learning Approaches for Early DRG Classification and Resource Allocation , 2015, INFORMS J. Comput..

[28]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[29]  Robert B. Fetter,et al.  Diagnosis Related Groups: Understanding Hospital Performance , 1991 .

[30]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[31]  R. Busse,et al.  Editorial: Hospital case payment systems in Europe , 2006 .