Healthcare analytics: 4 success stories

Organizations in all industries are seeking to be more data-driven. That’s especially true in healthcare, where providers are leveraging the enormous amount of data at their disposal with analytics to drive better patient outcomes, streamline operations and cut costs.

Even before the COVID-19 pandemic became a global phenomenon, research firm Acumen Research and Consulting predicted the global healthcare analytics market would grow to $52.2 billion by 2026. Analytics are helping healthcare systems identify and manage workflow bottlenecks, providing operational leaders with predictive insights that can help them better allocate resources, even helping emergency room physicians better identify which patients need urgent care.

Here are four examples of how healthcare organizations are using analytics today.

Kaiser Permanente streamlines operations with analytics

Kaiser Permanente is reducing patient waiting times and the amount of time hospital leaders spend manually preparing data for operational activities using a combination of analytics, machine learning, and AI. The healthcare consortium’s Operations Watch List (OWL), developed as part of its “Insight Driven” program, is a mobile app that provides a comprehensive, near real-time view of key hospital quality, safety, and throughput metrics, including hospital census, bed demand and availability, and patient discharges.

The app draws data from electronic health record (EHR) systems to provide clinical and operational leaders with the insights they need to make decisions.

“The mobile app synthesizes the information to direct hospital leaders’ attention and action on issues that can cause bottlenecks in workflows and longer patient wait times,” says Dick Daniels, executive vice president and CIO at Kaiser Permanente. “The app ensures that the best care delivery and patient experience are delivered in a seamless manner.”

OWL has gone live across all of Kaiser Permanente’s 21 Northern California hospitals, and the plan is to expand it broadly across all its regions and hospitals. Daniels says the pilot sites have reduced patient wait time for admission to the emergency department by an average of 27 minutes per patient. Surveys also show hospital managers have reduced the amount of time they spend manually preparing data for operational activities by an average of 323 minutes per month.

Daniels’ advice: Seek continuous feedback. Daniels’ team used the Scaled Agile Framework (SAFe) methodology to develop the app and for continuous improvement. The approach enabled hospital operations leaders and front-line managers to provide timely guidance and input on their needs and expectations. “By regularly incorporating feedback and often, the development team can continuously refine solutions to deliver the most important, relevant information and functionality to support ease of use and maximize value delivered,” Daniels says.

NorthShore reduces hospitalizations with predictive analytics

NorthShore University HealthSystem’s emergency departments are using data and predictive analytics to help determine which chest pain patients should be admitted for observation and which patients should be sent home. Unnecessary hospitalizations are bad for patients, hospitals and insurers. They lead to longer wait times, a lack of beds for patients that really need them, wasted time of emergency medical staff, and additional costs for everyone. On the other hand, failing to admit patients that really need care can have deadly consequences.

NorthShore’s “Technology-driven Chest Pain Management in the ED” program puts predictive analytics directly into physicians’ and nurses’ workflow to help them better identify which patients with chest pain are at a high risk of a heart attack. It uses the HEART score (History, Electrocardiogram, Age, Risk factors, and initial Troponin) — an assessment tool developed in the Netherlands — and integrates it with the electronic medical record (EMR). Alerts and hard stops require physicians to score patients before they can be discharged or admitted.

“The challenge is hospitals are generally really conservative in terms of ruling out that there’s a serious thing going on, as we should be,” says Chad Konchak, assistant vice president of clinical analytics at NorthShore. “The idea was, could we build tools for physicians and nurses in the emergency room to help them better understand and identify patients at high risk of a heart attack.”

The first version of the new workflow was rolled out in 2017. NorthShore CIO Steve Smith says it has reduced the Chest Pain Observation Days rate by 10 percent without increasing the rate of ED returns, mortality, or morbidity.

Smith’s advice: Focus on the user experience. Getting physicians to adopt tools like this requires making the experience seamless. “Our physicians and nurses use the electronic health record as the key source of information about the patient. It is their ‘cockpit’ for patient care. Integration of any new analytics-driven technology must be in the clinical chart or the value will diminish. If we have to ask our clinicians to stop, leave the system, go to another system, log in, and start filling out a new tool, they just won’t do it,” Smith says.

Data-as-a-service platform helps JHS improve care

Jackson Health System is using its homegrown data-as-a-service platform as a strategic differentiator to improve patient care while cutting costs. Data from various systems and applications at JHS flow through Overwatch, the system’s data integration engine, which then delivers the data to individual systems as needed.

“We had all this information flowing through this engine and we delivered it to these individual systems, but we didn’t take advantage of the fact that we have it all sitting in this engine in transit and in real-time,” says George Rosello, associate director of enterprise application integration at JHS.

Rosello’s idea was to bring together the capabilities of the integration engine with JHS’ data warehouse. An early use case was identifying “high utilizers” of JHS’ emergency department (ED). High utilizers are patients, typically underfunded, who use the ED for primary care, often because they aren’t aware of other options. Overwatch establishes relationships between the data already following through the JHS integration engine, with triggers providing real-time alerts via text and email when ED high utilizers enter one of the JHS EDs. The alerts provide information about the patient, what service line they’re in, where they’re currently located, and what’s currently being done with them. Case managers can then meet with them and help them get into a more appropriate service line.

Rosello’s advice: Don’t lose sight of your goal. “When you have a project, especially projects that take a while, the end goal of the project ends up being finishing the project, but that’s not what it started as,” Rosello says. “Not losing sight of the end goal is a challenge, and something I would advise anyone to keep an eye on. What’s the real success factor of your project?”

Penn Medicine uses real-time data to shorten ICU stays

Even before the COVID-19 pandemic, getting critically ill patients breathing on their own was an essential step toward getting patients safely out of hospital intensive care units (ICUs) and freeing beds for other patients. To streamline that process, non-profit Penn Medicine built a dashboard that leverages its EHR’s real-time data streams to alert respiratory and nursing staff when interventions were needed and when patients might be ready to be weaned from ventilators.

“Many of the critically ill patients we take care of here in the ICU require a breathing machine to survive. That’s a mechanical ventilator,” says Dr. Barry Fuchs, medical director of the Medical Intensive Care Unit and Respiratory Care Department at Penn Medicine. “Although these ventilators save the lives of patients, they’re associated with risks and complications. And the longer that patients remain on a breathing machine, the longer they stay in the ICU.”

Penn Medicine built the ABC application (for Awakening and Breathing Coordination), an electronic dashboard and alert system that gathers sedation and ventilation protocol data in real-time and applies clinical decision support (CDS) rules, based on ICU treatment guidelines and inputs from experts. The ABC application sends alerts to respiratory therapists when a patient’s vital signs meet certain criteria, allowing the therapists to conduct trials to determine whether the patient is ready to breathe on their own.

The application has helped Penn Medicine reduce the time patients spend on a mechanical ventilator by more than 24 hours.

Draugelis’ advice: Bring key stakeholders together. Penn Medicine Chief Data Scientist Michael Draugelis says that successfully implementing the ABC application required bringing together Information Services (IS), the data science department, and clinical experts from the Penn Center for Health Care Innovation.  “This was the first project that really drove the deep collaboration with these three departments,” Draugelis says. “That project, that interaction, has adjusted the way that we work. We’re organizationally shifting in how we manage our projects.”