The constant development of healthcare systems calls for understanding process variation. It is detrimental to eradicate extraneous process variation using all possible avenues, while uplifting adequately defined metric closer to their target values. Common instances of vital healthcare variables involve waiting times, lab turnaround times, medication errors, response times of emergency services, patient satisfaction scores among others. Effective study and monitoring of such variables could be a genesis to considerable quality improvements. Within the statistical quality control, process control charts are essential tools for providing insights on process variables as well as finding out quality variables or quality improvements. A control chart is simply a statistical instrument that can be used to differentiate between process variations emanating from common causes as well as those variations emanating from special reasons. The statistics plotted could be rates, averages, proportions or any other qualities of interest. Each process surely has some variation.

In some cases variation be due to reasons not present normally in the process, while some is merely due to abundant ever-present process differences. Control charts have three horizontal lines namely the upper control limit, the center line and the lower control limit. Center line always denotes the mean value of the characteristic quality being studied. In case points lie within the upper control limit or within the lower control limit, then the process considered to be under control. Nevertheless, points plotted and appear outside the control limits are considered as proof implying that the process out of control simply calling for corrective or preventive actions to locate and eliminate the causes. The limits are arrived at using process data and outline the natural variation range within which the points plotted always fall approximately. Control charts are therefore critical to monitor if processes are getting worse as well as testing and validating improvement ideas.

Healthcare improvement requires significant changes in care service delivery processes. The turnaround time highlights the most critical aspect for laboratory testing. Research has shown that poor performance in the laboratory with regard to long turnaround times has a huge impact on patient care. To date, most turnaround time studies concentrated on outpatient testing, inpatient testing particularly during emergencies and outfits. Most processes within the healthcare industry infringe normality conventions namely cutting tool wear processes, chemical processes within fast-tracked life test. According to Valenstein and Emancipator, turnaround data distribution is abnormal. The skewed nature of turnaround data distribution might lead to specimens with unreasonably long turnaround times. Therefore, if traditional control charts that are founded on normality assumptions are applied to monitor an abnormal process, probabilities of error within control charts increases with respect to process skewness. This project brings in control charts into laboratory operations to monitor its turnaround time.