Online profile monitoring for surgical outcomes using a weighted score test

ABSTRACT In the past decade, risk-adjusted control charts have been widely used to monitor surgical outcomes. However, most existing approaches focus on monitoring shifts in location parameters and may not be able to detect a scale change that is also likely to occur in surgical data. In this article, we derive a weighted score test statistic to construct an exponentially weighted moving average chart and propose a new charting method to simultaneously monitor location and scale parameters. This new chart may be applied to monitoring surgical performance. Simulation results indicate that the proposed method is more efficient than existing methods, such as the risk-adjusted cumulative sum chart, in detecting the heterogeneity of surgical outcomes. A data set from the Surgical Outcome Monitoring and Improvement Program in Hong Kong is used to illustrate the applicability of the proposed chart.

[1]  Landon H. Sego,et al.  Risk‐adjusted monitoring of survival times , 2009, Statistics in medicine.

[2]  Mark Jones,et al.  Risk‐adjusted survival time monitoring with an updating exponentially weighted moving average (EWMA) control chart , 2009, Statistics in medicine.

[3]  S. Steiner EWMA Control Charts with Time-Varying Control Limits and Fast Initial Response , 1999 .

[4]  Daniel B. Hall,et al.  Order‐restricted score tests for homogeneity in generalised linear and nonlinear mixed models , 2001 .

[5]  Daniel Commenges,et al.  Generalized Score Test of Homogeneity Based on Correlated Random Effects Models , 1997 .

[6]  A. Bernstein,et al.  A method of uniform stratification of risk for evaluating the results of surgery in acquired adult heart disease. , 1989, Circulation.

[7]  Elisabeth J. Umble,et al.  Cumulative Sum Charts and Charting for Quality Improvement , 2001, Technometrics.

[8]  David J. Spiegelhalter,et al.  A Simple Risk-Adjusted Exponentially Weighted Moving Average , 2007 .

[9]  T. Treasure,et al.  Monitoring cardiac surgical performance: a commentary. , 2004, The Journal of thoracic and cardiovascular surgery.

[10]  S. Steiner,et al.  Monitoring surgical performance using risk-adjusted cumulative sum charts. , 2000, Biostatistics.

[11]  V T Farewell,et al.  A risk‐adjusted Sets method for monitoring adverse medical outcomes , 2004, Statistics in medicine.

[12]  C. Hogan Independent review. , 2002, GMHC treatment issues : the Gay Men's Health Crisis newsletter of experimental AIDS therapies.

[13]  D. Commenges,et al.  Tests of Homogeneity for Generalized Linear Models , 1995 .

[14]  Heping Zhang,et al.  Generalized score test of homogeneity for mixed effects models , 2006 .

[15]  Stefan H. Steiner,et al.  The Monitoring and Improvement of Surgical-Outcome Quality , 2015 .

[16]  Richard J Cook,et al.  Monitoring the evolutionary process of quality: risk-adjusted charting to track outcomes in intensive care. , 2003, Critical care medicine.

[17]  Seyed Taghi Akhavan Niaki,et al.  Monitoring patient survival times in surgical systems using a risk-adjusted AFT regression chart , 2017 .

[18]  Stefan H. Steiner,et al.  An Overview of Phase I Analysis for Process Improvement and Monitoring , 2014 .

[19]  Samer A M Nashef,et al.  EuroSCORE II. , 2012, European journal of cardio-thoracic surgery : official journal of the European Association for Cardio-thoracic Surgery.

[20]  R J Cook,et al.  Risk-Adjusted Monitoring of Binary Surgical Outcomes , 2001, Medical decision making : an international journal of the Society for Medical Decision Making.

[21]  Chris Sherlaw-Johnson,et al.  Monitoring the results of cardiac surgery by variable life-adjusted display , 1997, The Lancet.

[22]  M. Coory,et al.  Exponentially weighted moving average charts to compare observed and expected values for monitoring risk-adjusted hospital indicators , 2011, Quality and Safety in Health Care.

[23]  Arthur B. Yeh,et al.  Phase I Risk-Adjusted Control Charts for Monitoring Surgical Performance by Considering Categorical Covariates , 2012 .

[24]  Fah Fatt Gan,et al.  Risk-adjusted number-between failures charting procedures for monitoring a patient care process for acute myocardial infarctions , 2010, Health care management science.

[25]  Jan Terje Kvaløy,et al.  Risk-adjusted monitoring of time to event , 2010 .

[26]  Xihong Lin Variance component testing in generalised linear models with random effects , 1997 .

[27]  K. Liang A locally most powerful test for homogeneity with many strata , 1987 .

[28]  Pinaki Biswas,et al.  A risk‐adjusted CUSUM in continuous time based on the Cox model , 2008, Statistics in medicine.

[29]  Tom Treasure,et al.  Risk-adjusted sequential probability ratio tests: applications to Bristol, Shipman and adult cardiac surgery. , 2003, International journal for quality in health care : journal of the International Society for Quality in Health Care.

[30]  Stefan H. Steiner,et al.  Risk-Adjusted Monitoring of Outcomes in Health Care , 2014 .