A risk adjusted self-starting Bernoulli CUSUM control chart with dynamic probability control limits

Document Type : Research Article

Authors

1 Associate Professor, Department of Industrial Engineering, Amirkabir University of Technology

2 Ph.D. Student, Department of Industrial Engineering, Amirkabir University of Technology

Abstract

Usually, in monitoring schemes the nominal value of the process parameter is assumed known. However, this assumption is violated owing to costly sampling and lack of data particularly in healthcare systems. On the other hand, applying a fixed control limit for the risk-adjusted Bernoulli chart causes to a variable in-control average run length performance for patient populations with dissimilar risk score distributions in monitoring clinical and surgical performance. To solve these problems, a self-starting scheme is proposed based on a parametric bootstrap method and dynamic probability control limits for the risk-adjusted Bernoulli cumulative sum control charts. The advantage of the proposed control charts lies in the use of probability control limits when any assumptions about the patients’ risk distributions and process parameter. Simulation studies show that both proposed schemes have good performance under various shifts.

Keywords


[1] Chou, S. C.; “Statistical Process Control for Health Care,” International Journal for Quality in Health Care, Vol. 14, No. 5, pp. 427-428, 2002.
[2] Tennant, R.; Mohammed, M. A.; Coleman, J. J. and Martin, U.; “Monitoring Patients Using Control Charts: A Systematic Review,” International Journal for Quality in Health Care, Vol. 19, No. 4, pp. 187- 194, 2007.
[3] Woodall, W. H.; Adams, B. M.; Benneyan, J. C.; “The Use of Control Charts in Healthcare,” Statistical Methods in Healthcare, Wiley, in Faltin, F.; Kenett, R.; Ruggeri, F. Eds., pp. 251-267, 2011.
[4] Lim, T. O.; “Statistical Process Control Tools for Monitoring Clinical Performance,” International Journal for Quality in Health Care, Vol. 15, No. 1, pp. 3-4, 2003.
[5] Coory, M.; Duckett, S. and Sketcher-Baker, K.; “Using Control Charts to Monitor Quality of Hospital Care with Administrative Data,” International Journal for Quality in Health Care, Vol. 20, No. 1, pp. 31-39, 2008.
[6] Joner, M. D.; Woodall, W. H.; Reynolds, M. R.; “Detecting a Rate Increase Using a Bernoulli Scan Statistic,” Statistics in Medicine, Vol. 27, No. 14, pp. 2555-2575, 2008.
[7] De-Leval, M. R., François, K.; Bull, C.; Brawn, W. B. and Spiegelhalter, D.; “Analysis of a Cluster of Surgical Failures,” The Journal of Thoracic and Cardiovascular Surgery, Vol. 107, No. 3, pp. 914- 924, 1994.
[8] Steiner, S. H.; Cook, R. and Farewell, V.; “Monitoring Paired Binary Surgical Outcomes Using Cumulative Sum Charts,” Statistics in Medicine, Vol. 18, No. 1, pp. 69-86, 1999.
[9] Shu, L.; Jiang, W.; Tsui, K. L.; “A Comparison of Weighted CUSUM Procedures that Account for Monotone Changes in Population Size,” Statistics in Medicine, Vol. 30, No. 7, pp. 725-741, 2011.
[10] Sun, R. J.; Kalbfleisch, J. D.; Schaubel, D. E.; “A Weighted Cumulative Sum (WCUSUM) to Monitor Medical Outcomes with Dependent Censoring,” Statistics in Medicine, Vol. 33, No. 18, pp. 3114- 3129, 2014.
[11] Lim, T. O.; Soraya, A.; Ding, L. M. and Morad, Z.; “Assessing Doctors’ Competence: Application of CUSUM Technique in Monitoring Doctors’ Performance,” International Journal for Quality in Health Care, Vol. 14, No. 3, pp. 251-258, 2002.
[12] Steiner, S. H.; Cook, R. J.; Farewell, V. T. and Treasure, T.; “Monitoring Surgical Performance Using Risk-Adjusted Cumulative Sum Charts,” Biostatistics, Vol. 1, No. 4, pp. 441-452, 2000.
[13] Jones, M. A.; Steiner, S. H.; “Assessing the Effect of Estimation Error on Risk-Adjusted CUSUM Chart Performance,” International Journal for Quality in Health Care, Vol. 24, No. 2, pp. 176-181, 2012.
[14] Rossi, G.; Del-Sarto, S. and Marchi, M.; “A New Risk-Adjusted Bernoulli Cumulative Sum Chart for Monitoring Binary Health Data,” Statistical Methods in Medical Research, 2014.
[15] Taseli, J. C. and Benneyan, A.; “Cumulative Sum Charts for Heterogeneous Dichotomous Events,” Industrial Engineering Research Conference Proceedings, pp. 1754-1759, 2008.
[16] Gombay, E.; Hussein, A. and Steiner, S. H.; “Monitoring Binary Outcomes Using Risk-Adjusted Charts: a Comparative Study,” Statistics in Medicine, Vol. 30, No. 23, pp. 2815-2826, 2008.
[17] Zeng, L.; “Risk-Adjusted Performance Monitoring in Healthcare Quality Control,” Quality and Reliability Management and Its Applications, Springer, London, pp. 27-45, 2016.
[18] Tang, X.; Gan, F. F. and Zhang, L.; “Risk- Adjusted Cumulative Sum Charting Procedure Based on Multiresponses,” Journal of the American Statistical Association, Vol. 110, No. 509, pp. 16-26, 2016.
[19] Cook, D. A.; Coory, M. and Webster, R. A.; “Exponentially Weighted Moving Average Charts to Compare Observed and Expected Values for Monitoring Risk-Adjusted Hospital Indicators,” BMJ Quality and Safety, Vol. 20, No. 6, pp. 469–474, 2011.
[20] Fang, Y. Y.; Khoo, M. B.; Teh, S. Y. and Xie, M.; “Monitoring of Time between Events with a Generalized Group Runs Control Chart,” Quality and Reliability Engineering International, 2015.
[21] Pan, X. and Jarrett, J. E.; “The Multivariate EWMA Model and Health Care Monitoring,” International Journal of Economics and Management Sciences, 2014.
[22] Zhang, X. and Woodall, W. H.; “Dynamic Probability Control Limits for Risk-Adjusted Bernoulli CUSUM Charts,” Statistics in Medicine, Vol. 34, No. 25, pp. 3336-3348, 2014.
[23] Shen, X.; Tsung, F.; Zou, C. and Jiang, W.; “Monitoring Poisson Count Data with Probability Control Limits When Sample Sizes are Time- Varying,” Naval Research Logistics, Vol. 60, No. 8, pp. 625-636, 2011.
[24] Paynabar, K.; Jin, J. and Yeh, A.; “Phase I Risk Adjusted Control Charts for Monitoring Surgical Performance with Considering Categorical Covariates,” Journal of Quality Technology, Vol. 44, No. 1, pp. 39-53, 2012.
[25] Asadayyoobi, N. and Niaki, S. T. A.; “Monitoring Patient Survival Times in Surgical Systems Using a Risk-Adjusted AFT Regression,” Quality Technology and Quantitative Management Chart, 2015 [Accepted].
[26] Mohammadian, F.; Niaki, S. T. A. and Amiri, A.; “Phase I Risk-Adjusted Geometric Control Charts to Monitor Health Care Systems,” Quality and Reliability Engineering International, 2014.
[27] Hawkins, D. M.; “Self-Starting CUSUM Charts for Location and Scale,” The Statistican, Vol. 36, No. 1, pp. 299-315, 1987.
[28] Hawkins, D. M. and Maboudou-Tchao, E. M.; “Self-Starting Multivariate Exponentially Weighted Moving Average Control Charting,” Technometrics, Vol. 49, No. 1, pp. 199-209, 2007.
[29] Shen, X.; Tsui, K. L.; Woodall, W. H. and Zou, C.; “Self-Starting Monitoring Scheme for Poisson Count Data with Varying Population Sizes,” Technometrics, 2015 [Accepted].
[30] Szarka, J. L. and Woodall, W. H.; “A Review and Perspective on Surveillance of Bernoulli Processes,” Quality and Reliability Engineering International, Vol. 27, No. 6, pp. 735-752, 2007.
[31] Parsonnet, V.; Dean, D. and Berstein, A. D.; “A Method of Uniform Stratification of Risk for Evaluating the Results of Surgery in Acquired Adult Heart Disease,” Circulation, Vol. 79, No. 6, pp. 3-12, 1989.
[32] Tian, W. M.; Sun, H. Y.; Zhang, X. and Woodall, W. H.; “The Impact of Varying Patient Populations on the in Control Performance of the Risk-Adjusted CUSUM Chart,” International Journal for Quality in Health Care, Vol. 27, No. 1, pp. 31-36, 2015.