Interrupted Time Series Analysis for Quality Improvement
Interrupted time series (ITS) analysis is one of the strongest quasi-experimental designs available for evaluating quality improvement interventions. It provides more robust evidence than simple before-and-after comparisons by accounting for pre-existing trends and seasonal patterns.
What Is Interrupted Time Series Analysis
ITS analysis uses a series of observations collected at regular intervals before and after an intervention (the "interruption") to assess whether the intervention changed the level or trend of an outcome. By modeling the pre-intervention trend, ITS can distinguish between changes attributable to the intervention and changes that would have occurred regardless. This makes it particularly valuable for evaluating policy changes, system-wide interventions, and quality improvement initiatives where randomized controlled trials are impractical.
Key Design Elements
A well-designed ITS study requires multiple data points before and after the intervention. A minimum of eight observations in each period is generally recommended, though more data points provide greater statistical power. The timing of the intervention must be clearly defined, and there should ideally be a clear boundary between pre-intervention and post-intervention periods. When a control group that did not receive the intervention is available, the study design becomes a controlled ITS, which further strengthens causal inference.
Analyzing ITS Data
ITS analysis typically uses segmented regression to model changes in both the level and slope of the outcome at the point of intervention. The level change indicates an immediate effect of the intervention, while the slope change indicates a gradual effect on the trend over time. Analysts must also assess and address autocorrelation (correlation between adjacent time points) and seasonality, which can bias results if ignored.
Practical Applications in QI
Quality professionals can use ITS to evaluate the impact of initiatives such as new clinical protocols, electronic health record alerts, staffing changes, and educational programs. For example, an ITS analysis could assess whether implementing a surgical safety checklist changed the rate of surgical site infections over time. The method is also useful for evaluating the impact of external events, such as regulatory changes or public reporting initiatives.
Strengths and Limitations
ITS analysis is stronger than pre-post comparisons because it accounts for pre-existing trends. However, it cannot control for events that coincide with the intervention (co-interventions), and it assumes that the pre-intervention trend would have continued without the intervention. Quality professionals should document potential confounders and discuss them when reporting ITS results. Despite these limitations, ITS remains one of the most practical and rigorous methods for evaluating real-world quality improvement interventions.