A Risk-Adjusted CUSUM Chart for Monitoring Surgical Performance with Ordinal Outcomes and Random Effects

Document Type : Research Article

Authors

1 Department of Industrial Engineering, University of Gonabad, Gonabad, Iran

2 Department of Industrial Engineering, University of Gonabad, Gonabad, Iran.

3 Department of Industrial Engineering, Islamic Azad University- North Tehran Branch, Tehran, Iran.

Abstract

Monitoring healthcare processes poses unique challenges due to the substantial variability in patient risk profiles, which can significantly influence surgical outcomes. Traditional control charts often neglect these individual differences, leading to potentially biased and misleading performance assessments. To overcome these limitations, risk-adjusted control charts have been developed to incorporate patient-specific covariates for more equitable monitoring. This study extends previous approaches by proposing a risk-adjusted cumulative sum (RA-CUSUM) control chart that accommodates ordinal surgical outcomes and incorporates random effects to model unobserved heterogeneity among healthcare providers. The proposed RA-CUSUM chart employs dynamic probability control limits (DPCLs) to maintain a constant conditional false alarm rate, enabling consistent performance across heterogeneous patient populations. Through extensive simulation studies, we demonstrate its efficacy in detecting shifts in surgical performance stability, particularly in response to changes in location and scale. A real-world case study using cardiac surgery data demonstrates the practical applicability of the method. This work provides a more refined and fair framework for evaluating surgical quality and lays the groundwork for integrating adaptive techniques in future healthcare monitoring systems. In addition to healthcare monitoring, the method can be extended to other domains where ordinal outcomes and case heterogeneity are relevant, such as education and finance. This adaptability makes it a valuable decision-support tool for quality improvement programs and real-time risk management.

Keywords

Main Subjects

References

  1. Agresti, A. (2010). Analysis of ordinal categorical data: Wiley.
  2. Aminnayeri, M., & Sogandi, F. (2016). A risk-adjusted self-starting Bernoulli CUSUM control chart with dynamic probability control limits. AUT Journal of Modeling and Simulation, 48(2), 103-110.
  3. Aytaçoğlu,​B.,​Driscoll,​A.​R.,​&​Woodall,​W.​H.​(2023).​ Design of adaptive EWMA control charts using the conditional false alarm rate. Quality and Reliability Engineering International, 39(6), 2206-2214.
  4. Bersimis, S., & Sachlas, A. (2022). Surveilling public health through statistical process monitoring: a literature review and a unified framework. Communications in Statistics: Case Studies, Data Analysis and Applications, 8(3), 515-543.
  5. Christensen, R. H. B. (2015). Analysis of ordinal data with cumulative link models—estimation with the R-package ordinal. R-package version, 28, 406.
  6. Grigg, O. A. (2019). The STRAND Chart: A survival time control chart. Statistics in Medicine, 38(9), 16511661.
  7. Khosravi, R., Owlia, M. S., Fallahnezhad, M. S., & Amiri, A. (2018). Phase I risk-adjusted control charts for surgical data with ordinal outcomes. Communications in Statistics-Theory and Methods, 47(18), 4422-4432.
  8. Lai, X., Li, X., Liu, L., Tsung, F., Lai, P. B., Wang, J., . . . Liu, J. (2021). A risk-adjusted approach to monitoring surgery for survival outcomes based on a weighted score test. Computers & Industrial Engineering, 160, 107568.
  9. Li, L., Liu, Y., Shang, Y., & Liu, Z. (2023). A new phase II risk-adjusted CUSUM chart for monitoring surgical performance. Computers & Industrial Engineering, 186, 109738.
  10. Paynabar, K., Jin, J., & Yeh, A. B. (2012). Phase I risk-adjusted control charts for monitoring surgical performance by considering categorical covariates. Journal of Quality Technology, 44(1), 39-53.
  11. Sego, L. H., Reynolds Jr, M. R., & Woodall, W. H. Appendix A. Derivation of the Score Statistic (2009). Risk-adjusted monitoring of survival times. Statistics in Medicine, 28(9), 1386-1401.
  12. Steiner, S. H., Cook, R. J., Farewell, V. T., & Treasure, T. (2000). Monitoring surgical performance using riskadjusted cumulative sum charts. Biostatistics, 1(4), 441452.
  13. Tang, X., Gan, F. F., & Zhang, L. (2015). Riskadjusted cumulative sum charting procedure based on multiresponses. Journal of the American Statistical Association, 110(509), 16-26.
  14. Zhang, X., Loda, J. B., & Woodall, W. H. (2017). Dynamic probability control limits for risk-adjusted CUSUM charts based on multiresponses. Statistics in medicine, 36(16), 2547-2558.
  15. Zhang, X., & Woodall, W. H. (2015). Dynamic probability control limits for risk-adjusted Bernoulli CUSUM charts. Statistics in Medicine, 34(25), 33363348.
AUT Journal of Modeling and Simulation
Volume 57, Issue 1
June 2025
Pages 17-28

Files

Share

How to cite

Statistics