Twenty Ordinary Weeks and Three Good Ones: A Measurement Plan and Run Chart Reading for Confirmed Feeding Tube Placement
Student Name
American College of Education
NUR5053: Quality Improvement and Safety
Module 5 Assignment
Instructor Name
November 24, 2026
What the Plan Must Do
The project chartered in Module 4 aims to have every first enteral feeding on the neuroscience step-down unit start only after a radiologist has filed a placement result. Aggregate numbers cannot tell the team whether its changes are working. A before-and-after comparison of two monthly percentages would hide the week-to-week variation that is normal for a unit placing five or six tubes a week, and it would invite the team to celebrate or panic over differences that are only noise. Perla et al. (2011) make the case that data plotted in time order let a team see whether a process has changed with very little statistical machinery, and that such plots are more useful to improvement teams than summary statistics that ignore time. The measurement plan is built around that idea.
Operational Definitions and Data Collection
The project's main process measure counts, as a share of each week's placements, the first feedings that began only once a placement result was on file. The numerator is the number of newly placed nasal small-bore tubes, in the reporting week, whose first feeding time on the pump documentation is later than the time stamp on the radiologist's filed result. The denominator is every newly placed nasal small-bore tube on the unit that week that was used for feeding. Tubes removed before any feeding, tubes placed elsewhere and replacement tubes placed within 24 hours for the same patient are excluded. The week runs Monday 0000 to Sunday 2359. The first feeding time is the pump start, not the time the order was released, because the pump start is when harm could begin.
The data come from two electronic sources: the radiology information system for the result time stamp and the medication administration record for the pump start. The clinical nurse specialist pulls both each Monday for the prior week, and a second reviewer from the quality department independently abstracts every fourth record to check that the definitions produce the same answer. In the first month the two reviewers disagreed on one record out of seven, a patient whose feeding was restarted after a pause, and the definition was amended to specify the first start after placement.
The second process measure, the percentage of high-risk patients receiving guided placement, is reported monthly because the numbers are too small for a weekly chart. The balancing measure is the median hours from the placement order to the first feeding, reported weekly and split by day and night shift. The outcome measure, misplacements discovered after feeding began, is counted and reviewed case by case.
The Baseline Run Chart
The baseline covers 20 weeks, from the week of June 15 to the week of October 26, 2026, recovered from records. Weekly values, in order, were 100, 83, 100, 86, 100, 67, 71, 67, 83, 80, 83, 67, 71, 83, 83, 75, 67, 80, 71 and 83 percent, with between four and seven placements in each week. Plotted in order, the points range from 67% to 100% and fall into no obvious pattern. The median of the 20 points is 81.5%, and it is drawn as the center line and extended forward as the reference against which new points are judged.
The chart was read with the four rules Perla et al. (2011) describe. A shift, meaning a stretch of at least six weeks in a row that all land above the median or all below it, is absent: the longest run is the five weeks above the median at the start of the baseline. A trend, five or more consecutive points going steadily up or down, is absent. The number of runs is nine, which falls within the range expected by chance for 20 points, so the data do not alternate too much or too little. No single point is far enough from the others to count as an astronomical value. The chart was also checked against two rules proposed after a simulation study, the longest run and the number of times the line crosses the median, which kept false signals near 5% in simulated processes while the trend rule proved almost useless for picking up gradual drift (Anhøj & Olesen, 2014). With eight crossings and a longest run of five, the conclusion is the same.
The baseline is a stable process, and a stable process that starts one feeding in five too early will keep doing so until someone redesigns it. That reading matters for leadership. It means the early feedings were not caused by a bad week, a careless nurse or a staffing crisis, each of which would have left a signal, and it means reminders and discipline will not move the center line. Only a change to the system will.
The First Weeks After the Change
The red pump tag described in the Module 4 plan was introduced on night shift in the week of November 2 and extended to all shifts after the first cycle. The three weeks since then reached 100% with six, seven and five placements. All three points sit above the baseline median.
Three points above the median are not a signal. By the shift rule, three more consecutive weeks above 81.5% would be needed before the team could say the process has changed. The small denominators also mean each week's value moves in steps of 14 to 20 percentage points, so one early feeding would drop a week to the low 80s. The team's decision is therefore to continue the tag, to keep plotting, and to begin the second cycle, the radiology priority category, without yet declaring success.
The balancing measure shows the price of the tag. At night, the median time from the placement order to the first feeding rose from 4.1 hours in the baseline to 4.9 hours, an increase of about 48 minutes, slightly more than the 45 minutes the team predicted. During the day it rose by 10 minutes. The increase is the time patients were previously being fed before the tube's position was known, so it is a delay the unit should accept, but it makes the case for the radiology priority, which is meant to bring the night figure back down.
Limits and Next Steps in Measurement
A run chart is the right first tool for a project with a short baseline and small weekly counts, but it is not the only one. Once 20 to 25 points exist after the change, the team will move the process measure to a p-chart, the control chart built for proportions, whose limits widen and narrow with each week's denominator. Mohammed et al. (2008) set out how to choose and build such charts and why unequal subgroup sizes call for that chart type. The data also depend on accurate time stamps; if a nurse documents the pump start late, a feeding can appear to have begun after the result when it did not. The quality reviewer's audit of every fourth record will continue for that reason. Finally, this plan measures whether feeding waits for confirmation, not whether confirmation is correct. A misread film would pass every measure here, which is why each misplacement found after feeding will still be reviewed as an event.
References
Anhøj, J., & Olesen, A. V. (2014). Run charts revisited: A simulation study of run chart rules for detection of non-random variation in health care processes. PLOS ONE, 9(11), Article e113825. https://doi.org/10.1371/journal.pone.0113825
Mohammed, M. A., Worthington, P., & Woodall, W. H. (2008). Plotting basic control charts: Tutorial notes for healthcare practitioners. Quality and Safety in Health Care, 17(2), 137-145. https://doi.org/10.1136/qshc.2004.012047
Perla, R. J., Provost, L. P., & Murray, S. K. (2011). The run chart: A simple analytical tool for learning from variation in healthcare processes. BMJ Quality & Safety, 20(1), 46-51. https://doi.org/10.1136/bmjqs.2009.037895
How this NUR 5053 Module 5 example is structured
NUR 5053 Module 5 commonly builds the measurement plan and reads a run chart for signals of change; your classroom's instructions decide whether you supply your own data or interpret a data set provided in the classroom. This example writes operational definitions and a data collection plan, sets the median from baseline, reads the chart with named rules, reports the balancing measure and states what the chart can and cannot yet say.
NUR5053 Module 5 questions, answered
What does NUR5053 Module 5 usually ask for?
NUR5053 Module 5 commonly asks for a measurement plan, with operational definitions and data sources for each measure, and an interpretation of a run chart. Some sections provide the data set; others expect your project's own baseline. Your classroom's instructions decide which.
How many data points do I need on a run chart?
Enough to apply the rules. The shift rule needs six consecutive points on one side of the median, so a baseline of fewer than about 10 to 12 points can hide or invent a pattern. State how many points you have and what a signal would require.
What if my run chart shows no signal?
Say so and interpret it. A stable baseline tells you the problem is built into the process, which is an important finding. After a change, a lack of signal may mean the change has not worked yet or that you need more weeks of data.
Write yours, or have the desk draft it
This paper is an original model document written by our desk, not a submitted student paper and not an official American College of Education document. Read it for the moves, then write your own to the instructions in your classroom. If you want one built to your exact prompt and rubric, the first custom sample is free and arrives in 24 to 48 hours.