4 keys to data-driven hospital quality improvement

From required Centers for Medicare & Medicaid Services (CMS) and Centers for Disease Control and Prevention reporting to Agency for Healthcare Research and Quality (AHRQ) indicators, hospitals now track and report large volumes of data on a daily basis. But how can hospitals use these data to drive improvement initiatives, predict performance for value-based purchasing and improve patient outcomes? For many healthcare IT professionals, these are critical questions that play a big role in shaping the effectiveness (or ineffectiveness) of their hospital’s quality improvement program.

The data-driven healthcare movement is premised on the idea that better data will lead to better patient outcomes. By looking at patterns in adverse events, for example, hospitals can determine where they need to focus quality improvement efforts and track the results of those efforts over time. However, many hospitals find it difficult to cut through the clutter and find actionable, meaningful information among the data points.

Missed opportunities for improvement

While nearly all hospitals use data in some form to make quality decisions, evidence suggests that the industry has a long way to go to fully realize the potential of data-driven improvement. It’s easy to generate data. Pulling it in a timely fashion and in a format that is usable for decision makers has proven to be a challenge for many hospital systems.

For example, hospitals can now leverage AHRQ quality data to evaluate their performance and benchmark against their peers. However, organizing the data and producing models of the results is slow; it can take up to seven quarters to get the comparative data back for benchmarking purposes. With this much of a time lag, it is very difficult to link specific policies and procedures to outcomes in order to recommend changes.

At the same time, the sheer volume of data produced is daunting. Sophisticated analytics are needed in order to draw connections between data points and understand the story they are trying to tell. Unless hospitals are able to extract meaning from the data, they will not be able to use it to guide appropriate quality-improvement decisions.

The stakes for hospitals that fail to meet quality standards are getting higher. Increasingly, payers are moving to value-based purchasing and reimbursement models in which hospitals are paid for outcomes achieved, not services rendered. CMS is already moving in this direction, and private insurers are starting to follow suit with their own value-based purchasing programs.

Four critical characteristics of effective QI data

In order to impact hospital performance and patient outcomes, data must be easy to find, use and understand. There are four critical factors that hospital, health network and state association leaders should be looking for when it comes to leveraging analytics for quality improvement. These factors include:

  • Actionable insights: It’s not enough to count adverse events. Hospitals need analytics tools that allow them to identify the factors that contribute to adverse events and analyze risk factors. For example, by examining pre-existing patient characteristics and the procedures performed, analytics can help to identify which adverse events were potentially preventable and the risk factors that are correlated to different outcomes. These types of insights, along with models that employ both predictive analytics and risk adjustment, can help hospital leaders make proactive decisions to improve patient outcomes and financial returns.
  • Time-to-Value: In order to turn data into valuable insight, it must be available as close to real time as possible. When there is too much time lag between data collection and analysis, it is harder to link actions to outcomes. Policies and procedures may have already changed, and people who were involved in providing care may be gone. Additionally, without real-time insights it becomes impossible to monitor whether or not improvement activities are producing the anticipated results. Addressing this “blind spot” is one of the biggest obstacles for quality improvement leaders.
  • Accessibility and flexibility: How organizations access and view data is often as important as the information itself. Hospital leaders need to be able to access data when, where and how they need it. For instance, cloud-based capabilities are an excellent way to provide fast, easy access to higher-level insights and clinical performance analysis. However, security and privacy concerns dictate that more sensitive, patient-specific data is delivered through secure channels in accordance with HIPAA compliance standards. It is imperative for those across the spectrum of care--from hospital executives to practitioners to those involved in monitoring quality--to have the flexibility to securely access and view performance insights, both broad and patient-specific, as they look for ways to improve quality care.
  • Benchmarking and collaboration: Evaluating performance is an important part of making quality improvement plans. Hospitals need tools that help them compare to meaningful benchmarks and monitor their progress towards their goals. Hospital leaders also benefit from comparing their hospital’s performance with others in their system, state and nationwide. These comparisons allow hospitals to identify potential areas for quality improvement and set meaningful, appropriate goals. For hospital networks and state associations, these comparisons are a catalyst for increased dialogue and sharing of best practices among members.

Capturing quality data and turning it into action is not an easy task, but with the right approach, resources and leadership, hospitals can use analytics to make a real difference in the quality of care provided to patients. New analytics tools can help to turn the data deluge into understandable, and actionable, insights--helping providers enhance the patient experience while reducing costs and improving care.