scholarly journals National Health Service (NHS) trust boards adopt statistical process control reporting: the impact of the Making Data Count Training Programme

BMJ Leader ◽  
2021 ◽  
pp. leader-2020-000357
Author(s):  
Samantha Riley ◽  
Anna Burhouse ◽  
Thomas Nicholas
Keyword(s):  
Process Control ◽  
Statistical Process Control ◽  
Training Session ◽  
Board Members ◽  
Statistical Process ◽  
Behavioural Changes ◽  
Performance Reports ◽  
Board Training ◽  
The Impact ◽  
Over Time

BackgroundRed, amber, green (RAG) reports persist as the tool most commonly used by NHS trust boards to understand performance and gain assurance, despite statistical process control (SPC) being a more reliable way of presenting data over time. The aim of this study is to report board members’ feedback on an educational intervention focusing on the use of SPC in NHS trust performance reports, review the presence of SPC charts in performance reports and explore board members’ experience of behavioural changes in their board or fellow board members following the intervention.MethodsA 90-minute board training session in the use of SPC—Making Data Count—was delivered to 61 NHS trust boards between November 2017 and July 2019. This paper describes the approach taken with boards to enable them to understand the limitations of RAG reports and the benefits of using SPC and analyses the extent to which the Making Data Count training has led to boards adopting SPC. The paper provides quantitative analysis of the increase in SPC use across the 61 participating boards, summaries from the board evaluation forms and qualitative reflections of seven senior leaders from four boards who consented to participate in post-training interviews with an independent evaluator.ResultsDuring the period covered by this study, 583 participants of board training provided feedback. 99% of respondents agreed that the training session was a good use of their time. 97% of respondents agreed that participating in the event would enhance their ability to make good decisions. A review of the presence of SPC charts in the board papers of the 61 trusts prior to the board training revealed that 72% contained 0–5 SPC charts. A review of the same trusts’ papers 6–12 months after the training revealed a significant increase in the presence of SPC with 85% of reports containing a minimum of six charts.ConclusionThe Making Data Count education intervention has increased the use of SPC in board reports and has had some self-reported impact on individual and collective behavioural changes by board members, including reducing the amount of time wasted by boards discussing insignificant changes in data and providing a clearer focus on those issues requiring board attention. Further research is required to see if this immediate impact is sustained over time and to identify the key enablers and barriers to organisational adoption of SPC by boards in the NHS.

scholarly journals The Impact of Statistics in Industry and the Role of Statisticians

2016 ◽  
Vol 30 (1) ◽  
pp. 7-20
Author(s):  
Ronald J.M.M. Does ◽  
Albert Trip
Keyword(s):  
Process Control ◽  
Statistical Process Control ◽  
Six Sigma ◽  
Practical Experience ◽  
Successful Implementation ◽  
Statistical Process ◽  
Quality Program ◽  
Quality Programs ◽  
The Impact

The use of statistics in quality management has a long history. Pioneers in this field, such as Walter A. Shewhart and W. Edwards Deming, refer to themselves as industrial statisticians. Statistical thinking in industry means that all work is regarded as a series of interconnected processes, that all processes show variation, and that a reduction in variation is the key for continuous improvement. In literature we find several quantitative quality programs to achieve this. We may mention Statistical Process Control (SPC)and the Six Sigma quality program, among others. We have implemented Statistical Process Control and Six Sigma in several industries. In this paper we briefly describe the philosophies of both programs and the steps needed for a successful implementation. Based on practical experience with both programs we describe the role that a statistician can play in industry. We shall also give an overview of research initiated by the projects we have carried out.

scholarly journals Quality Assurance System Using Statistical Process Control: An Implementation for Image Cytometry

2004 ◽  
Vol 26 (3) ◽  
pp. 101-117
Author(s):  
David Chiu ◽  
Martial Guillaud ◽  
Dennis Cox ◽  
Michele Follen ◽  
Calum MacAulay
Keyword(s):  
Quality Assurance ◽  
Process Control ◽  
Statistical Process Control ◽  
Control Charts ◽  
Room Temperature ◽  
Image Cytometry ◽  
Cervical Neoplasia ◽  
Cancer Center ◽  
Statistical Process ◽  
Over Time

Aims: Optical technologies have shown some promise for improving the care of cervical neoplasia. We are currently evaluating fluorescence and reflectance spectroscopy and quantitative cyto‐histopathology for cervical neoplasia screening and diagnosis. Here we describe the establishment and application of a quality assurance (QA) system for detecting system malfunctions and assessing the comparability of four image cytometers used in a multicenter clinical trial. Methods: Our QA system involves three levels of evaluation based on the periodicity and complexity of the measurements. We implemented our QA system at three image cytometers at the British Columbia Cancer Agency and one at M.D. Anderson Cancer Center. The measurements or tasks were performed daily, monthly, and semi‐annually. The current and voltage of the lamp, the calibration image characteristics, and the room temperature were checked daily. Long‐term stability over time, short‐term variability over time, and spatial response field uniformity were evaluated monthly. Camera linearity was measured semi‐annually. Control charts based on statistical process control techniques were used to detect when the system did not perform optimally. Results: Daily measurements have shown good consistency in room temperature, lamp and calibration behaviour. Monthly measurements have shown small coefficients of variation between and within the four devices. There have been greater differences between sessions than within sessions. Comparability among the four systems is reasonably good. Semi‐annual measurements have shown stable camera linearity. QA events were detected using the QA system. Multiple examples of event detection leading to correction of system malfunction are described in this report. Conclusions: QA programs are critical for ensuring data integrity and therefore for the conduct of multicenter clinical trials.

scholarly journals Statistical process control part 2: using statistical process control to measure process improvement in patient flow

2009 ◽  
Vol 33 (3) ◽  
pp. 412 ◽  
Author(s):  
Tamara G Chetter
Keyword(s):  
Health Care ◽  
Quality Improvement ◽  
Process Control ◽  
Statistical Process Control ◽  
Process Improvement ◽  
Patient Flow ◽  
Care Process ◽  
Statistical Process ◽  
The Impact ◽  
Control Part

THE FIRST ARTICLE in this series, ?Statistical process control part 1: a primer for using statistical process control in health care process improvement? 1 (in this issue of the Journal), introduced the basic concepts of statistical process control (SPC) and its main tool, the control chart. While this set of techniques was originally developed in the manufacturing sector, there is growing realisation in recent years that SPC (and also other quality improvement techniques, such as Six Sigma and lean thinking) can be successfully applied to health care quality improvement.2 The reason for this is that SPC is a potent and powerful, yet simple tool for tracking, and detecting any variation in, process performance over time; which creates the opportunity for health professionals to promptly respond to any improvement or deterioration in the process. Perhaps the most valuable feature of SPC techniques however, is the ability to place a change in the outcome of a process in close temporal proximity to the redesign and improvement of the process. This means SPC can reliably evaluate the effectiveness of quality improvement initiatives implemented at the front line of health service delivery, despite the complexities of the hospital system and the challenges this often poses for health services research (for example, the inability to use robust research designs). The purpose of this companion article is to therefore demonstrate the practical application of SPC in a health care organisation. Specifically, the technique of control charting was used to track the impact of patient flow process improvement interventions in a public hospital, in the hope that this will exemplify to health care professionals the value and simplicity in applying SPC as part of their daily work.

scholarly journals Stability of diagnostic rate in a cohort of 38,813 colorectal polyp specimens and implications for histomorphology and statistical process control

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Michael Bonert ◽  
Asghar Naqvi ◽  
Mozibur Rahman ◽  
John K. Marshall ◽  
Ted Xenodemetropoulos ◽  
...  
Keyword(s):  
Process Control ◽  
Statistical Process Control ◽  
Colorectal Polyp ◽  
Colorectal Polyps ◽  
Anatomical Location ◽  
Free Text ◽  
Tubular Adenoma ◽  
Serrated Adenoma ◽  
Statistical Process ◽  
Over Time

AbstractThis work sought to quantify pathologists’ diagnostic bias over time in their evaluation of colorectal polyps to assess how this may impact the utility of statistical process control (SPC). All colorectal polyp specimens(CRPS) for 2011–2017 in a region were categorized using a validated free text string matching algorithm. Pathologist diagnostic rates (PDRs) for high grade dysplasia (HGD), tubular adenoma (TA_ad), villous morphology (TVA + VA), sessile serrated adenoma (SSA) and hyperplastic polyp (HP), were assessed (1) for each pathologist in yearly intervals with control charts (CCs), and (2) with a generalized linear model (GLM). The study included 64,115 CRPS. Fifteen pathologists each interpreted > 150 CRPS/year in all years and together diagnosed 38,813. The number of pathologists (of 15) with zero or one (p < 0.05) outlier in seven years, compared to their overall PDR, was 13, 9, 9, 5 and 9 for HGD, TVA + VA, TA_ad, HP and SSA respectively. The GLM confirmed, for the subset where pathologists/endoscopists saw > 600 CRPS each(total 52,760 CRPS), that pathologist, endoscopist, anatomical location and year were all strongly correlated (all p < 0.0001) with the diagnosis. The moderate PDR stability over time supports the hypothesis that diagnostic rates are amendable to calibration via SPC and outcome data.

Sign in / Sign up

Export Citation Format

Share Document