The 2024 Nudges in Health Care Symposium will take place September 26–27 in Philadelphia. Learn more and register



A screening and navigation platform for hepatocellular carcinoma

Project status



Tessa Cook, MD, PhD

Darco Lalevic, MCIT

Charlie Chambers, MCIT

Innovation leads


Innovation Accelerator Program

Independence Blue Cross


Hepatocellular carcinoma (HCC) is the most common type of liver cancer in adults.

There are approximately 10,000 active patients at risk for HCC at Penn Medicine at any given time. In order to catch this cancer at a treatable stage, such patients should be screened every six months with an abdominal ultrasound. However, as many as 60 percent of patients are diagnosed too late to be cured.

A significant driver of low screening rates is that patients at risk for HCC are challenging to identify. A typical primary care physician with a patient panel of approximately 500 might have only one patient eligible for HCC screening. Identifying that individual is not a simple task, as there are more than 20 risk factors involved.


LiveAware is a digital platform designed to increase imaging-based screening rates, with the pilot use case being patients at risk for HCC. 

LiveAware eliminates the burden on physicians to know who is eligible for screening, streamlines ordering, and supports patients to follow-through. When a patient is identified, a pended screening order is created and pushed to Epic for the physician to sign. All orders are filed as standing orders, which in the case of HCC, means they are automatically placed every six months. After orders are placed, patients are notified through Penn Medicine’s patient portal that they are due for a screening. And for those who have upcoming appointments, same-day screening is offered.


By removing unnecessary burdens and making the right choice the easy choice, LiveAware can reduce the prevalence of late-stage diagnoses for life-threatening conditions, thereby improving patient outcomes and quality of life and reducing expensive downstream care.   

During the first phase of piloting with patients at risk for HCC, 82 percent of orders were signed by physicians – a 22 percent increase from the baseline – and screening rates among at-risk patients increased by 26 percent. At scale, this translates to more than 2,000 at-risk patients being “caught” by LiveAware, who might otherwise have been missed.  

Since the initial pilot, LiveAware has consistently increased the number of screening orders placed over baseline by anywhere from 5 to 35 percent in intervention practices. Unfortunately, the COVID-19 pandemic disrupted the previously observed pattern that showed that most patients completed screenings. The team is currently exploring barriers to screening completion to remedy this issue. 

LiveAware is in use across the Primary Care Service Line for all downtown practices. The team is actively working to continue to scale the platform for patients at risk for liver cancer and working to spread it to other disease areas, such as lung cancer and breast cancer.

In 2022, Independence Blue Cross implemented an adaptation of LiveAware. With this intervention, providers identified more members at risk for liver cancer and increased the hepatoma screening rate by 110 percent.

Innovation Methods

Fake back end

It is essential to validate feasibility and understand user needs before investing in the design and development of a product or service. A fake back end is a temporary, usually unsustainable, structure that presents...

Fake back end

Before developing and delivering an automated system to create pended orders, we manually placed orders to identify what information physicians required to determine whether a patient would benefit from screening.

Fake back end

It is essential to validate feasibility and understand user needs before investing in the design and development of a product or service.

A fake back end is a temporary, usually unsustainable, structure that presents as a real service to users but is not fully developed on the back end.

Fake back ends can help you answer the questions, "What happens if people use this?" and "Does this move the needle?"

As opposed to fake front ends, fake back ends can produce a real outcome for target users on a small scale. For example, suppose you pretend to be the automated back end of a two-way texting service during a pilot. In that case, the user will receive answers from the service, just ones generated by you instead of automation.