Learn how run charts help teams spot trends, shifts, and sustained runs in hospital-acquired infection data. Reading points in time order separates meaningful process changes from random variation, guiding timely review and escalation to infection control—because a single data point rarely tells the whole story.

Multiple Choice

How do you identify a trend in a run chart of hospital-acquired infections?

When monitoring hospital-acquired infections over time, the goal is to tell whether observed changes reflect real shifts in the process or just random variation. A run chart helps by plotting infection data in chronological order and highlighting patterns that aren’t random. The best approach is to look for nonrandom patterns such as a trend (a streak of points that consistently rise or fall) or a shift (a sustained change in the level, where many consecutive points sit above or below the previous center). Also pay attention to sustained runs where several points stay on one side of the center line. Using simple statistical rules to judge when these patterns are unlikely due to chance lets you determine if investigation or action is warranted, and you escalate to infection control when such patterns appear. Focusing only on the most recent data point misses the bigger picture and can overlook a developing trend. Counting infections per year removes the temporal sequence needed to see patterns. Ignoring shifts and assuming randomness would cause you to miss meaningful changes in the infection rate.

Hospital-acquired infections don’t usually announce themselves with a sudden, obvious spike. More often, the first clue is a pattern: infection counts rise week after week, or the rate stays higher than usual for a stretch of time. A run chart helps teams spot these changes by placing infection data in time order, so the story behind the numbers is easier to see.

That timing matters. A yearly total may show how many infections occurred, but it can hide when they happened and whether the rate was changing. A run chart keeps the sequence intact. It helps hospital teams distinguish a genuine shift in the infection process from the ordinary ups and downs that occur in any system.

What a run chart shows

A run chart is a simple line graph. The horizontal axis shows time—days, weeks, or months—while the vertical axis shows a measure, such as infection cases or an infection rate. Each data point represents one time period, and lines connect the points.

Many charts include a center line, often the median of the data. This gives the team a reference for what’s typical during the period being reviewed. The median is less affected by unusually high or low values than the mean, which can make it useful when infection data include a few sharp spikes.

The chart’s strength lies in showing the order of events. Imagine two hospital units that each report 12 infections in a year. One unit has roughly one infection each month. The other has a quiet first half of the year, followed by a cluster of cases. The annual totals match, but the patterns—and the questions they raise—are very different.

Read the pattern, not just the latest point

A single data point can catch the eye, especially if it’s higher than the points around it. But one unusual value doesn’t, by itself, show that the underlying process has changed. It may reflect random variation, a short-lived event, or a data issue that needs checking.

Instead, look across the whole sequence for signs that points are behaving in a nonrandom way. Three common patterns are trends, shifts, and runs.

  • A trend is a sequence of points that keeps rising or keeps falling. Many run-chart methods flag five or more consecutive points moving in the same direction, although local guidelines may use different rules.

  • A shift occurs when several points in a row fall above or below the center line. A common rule identifies six or more consecutive points on one side as a possible shift.

  • A run is a group of consecutive points on the same side of the median. In everyday language, it’s a sustained stretch above or below the chart’s center.

These rules help teams judge whether a pattern is unlikely to be due to chance alone. They’re signals to look more closely, not proof of what caused the change. A rising trend, for example, might reflect a real increase in infections—or a change in how cases are detected and recorded.

Why time order changes the picture

Counting infections by year is useful for some purposes, but it strips away the sequence needed to spot a developing pattern. It’s like knowing the final score of a game without knowing whether one team led the whole time or surged in the last few minutes.

Focusing only on the newest point has the opposite problem: it gives too much weight to one moment. A recent low count may feel reassuring, yet earlier points might show a steady rise. A high count may feel alarming, but it could be one isolated event within an otherwise stable series.

The run chart offers a more balanced view. It puts the latest value in context, while keeping earlier changes visible. That context is especially important for infections, where a delay between exposure, symptoms, testing, and reporting can blur the timeline.

Make sure the data can be trusted

Before interpreting a pattern, teams should check how the data were collected. Are the same case definitions being used throughout the period? Did a new screening process begin? Were reporting rules changed? If the way cases are found shifts, the chart may show a change in detection rather than a change in the underlying infection rate.

Counts also need context. A unit with more patients, longer stays, or more procedures may report more infections simply because it has more opportunities for infections to occur. When possible, teams should use a rate with an appropriate denominator, such as infections per 1,000 patient-days or per 100 procedures. The measure should match the question being asked.

For example, comparing raw infection counts between two months can mislead if the number of patient-days changed sharply. A rate can offer a fairer comparison, though it still depends on consistent definitions and reliable records. Numbers are only as useful as the system that produced them.

From signal to follow-up

When a run chart shows a sustained trend or shift, the next step is to review the signal with the people responsible for infection prevention and unit care. That may include infection-control staff, nurse leaders, clinicians, and data analysts. They can check the cases, confirm the data, and look for changes in the care process.

Useful questions include: Did staffing, patient mix, equipment, or workflow change? Were there changes in hand hygiene access, cleaning routines, device use, or supply availability? Did a cluster appear in one location or among patients with a shared exposure? These questions turn a line on a chart into a focused investigation.

A signal doesn’t automatically call for a sweeping intervention. It calls for a proportionate response. A possible increase may warrant prompt review, while a confirmed cluster could require urgent escalation under the hospital’s infection-control procedures. The goal is neither to dismiss every fluctuation nor to treat every bump as an emergency. It’s to notice meaningful patterns early and respond with the right level of attention.

A chart is a guide, not a verdict

Run-chart rules make pattern recognition more consistent, but they don’t explain why a pattern occurred. A shift above the center line tells the team that the data may have changed; it doesn’t identify the source. Likewise, a chart with no clear signal doesn’t guarantee that every part of the system is safe.

Teams should also avoid changing the center line casually. If they redraw it every time new data arrive, a real change can become harder to see. When a sustained shift is confirmed and understood, a new center line may be appropriate to describe the updated process. The reason for that change should be documented so future readers can follow the chart’s history.

Clear labels matter, too. Include the time period, measure, denominator, center line, and any important process changes. A short note that a screening policy changed in March, for instance, can prevent a later reviewer from mistaking a reporting shift for a sudden rise in infections.

Seeing change before it becomes a headline

A run chart turns a stream of infection data into a picture that teams can discuss and act on. The key is to look for nonrandom patterns—especially sustained upward or downward trends and runs of points on one side of the center line—rather than reacting to the newest value alone.

Used with sound data and clear escalation pathways, the chart becomes an early-warning tool. It won’t tell a hospital everything, but it can show when the pattern deserves a closer look. And in infection prevention, that earlier look can make a real difference.