CHL Performance Improvement and Data Analytics 5 — Questions and Answers
Question 1: A dashboard shows that ED door-to-physician time improved from 45 minutes to 28 minutes after a process change. To confirm this is a sustained improvement rather than regression, a leader should:
- Send a congratulatory email and close the project
- Continue plotting the metric on a control chart for at least 12–18 data points post-change (Correct answer)
- Switch to measuring a different metric
- Reduce staffing since throughput improved
Correct answer: Continue plotting the metric on a control chart for at least 12–18 data points post-change
Sustained improvement requires ongoing monitoring with a control chart to detect regression before it becomes entrenched.
Question 2: Which type of benchmark comparison is MOST useful for setting a realistic performance improvement target for a community hospital?
- Internal historical benchmark from five years ago
- Academic medical center 90th-percentile benchmark
- Peer-group benchmark from similar community hospitals (Correct answer)
- National average across all hospital types
Correct answer: Peer-group benchmark from similar community hospitals
Peer-group benchmarks from similar organizations account for case mix and resource differences, making targets realistic and actionable.
Question 3: In predictive analytics, overfitting a model means:
- The model performs well on training data but poorly on new, unseen data (Correct answer)
- The model uses too few variables to make accurate predictions
- The data set is too large to process in real time
- The model's predictions are rounded to the nearest whole number
Correct answer: The model performs well on training data but poorly on new, unseen data
Overfitting occurs when a model learns noise in training data rather than true patterns, causing poor generalization to new data.
Question 4: A healthcare leader wants to understand whether longer nursing shift lengths are associated with higher patient fall rates. The MOST appropriate analytic method is:
- Pareto chart of fall causes
- Correlation analysis between shift length and fall rate across units (Correct answer)
- Fishbone diagram of fall contributing factors
- Time-series chart of daily fall counts
Correct answer: Correlation analysis between shift length and fall rate across units
Correlation analysis quantifies the strength and direction of the relationship between two continuous variables across multiple observations.
Question 5: When using the Model for Improvement, what is the purpose of a 'small test of change' (PDSA cycle)?
- To pilot the change in the entire organization before full rollout
- To learn rapidly whether a change leads to improvement with minimal risk (Correct answer)
- To satisfy Joint Commission requirements before implementation
- To collect baseline data prior to selecting an intervention
Correct answer: To learn rapidly whether a change leads to improvement with minimal risk
Small PDSA cycles test changes in a limited context to generate learning quickly while reducing the risk of widespread harm if the change fails.
Question 6: Which measure type captures the end result experienced by the patient, such as functional status at discharge?
- Process measure
- Balancing measure
- Outcome measure (Correct answer)
- Structure measure
Correct answer: Outcome measure
Outcome measures reflect the actual results of care experienced by patients, such as clinical status, function, or quality of life.
Question 7: A performance improvement team discovers that 80% of medication errors originate from 3 of the 20 identified root causes. This finding reflects:
- Common cause variation across all categories
- The Pareto principle, suggesting focused effort on those 3 causes (Correct answer)
- A need to redesign all 20 contributing factors simultaneously
- Measurement error requiring a new data collection tool
Correct answer: The Pareto principle, suggesting focused effort on those 3 causes
The Pareto principle (80/20 rule) indicates that a minority of causes drive the majority of defects, guiding teams to prioritize high-impact interventions.
CHL Performance Improvement and Data Analytics 5
A dashboard shows that ED door-to-physician time improved from 45 minutes to 28 minutes after a process change.
To confirm this is a sustained improvement rather than regression, a leader should: