Apply by 3/31 for career development funding to advance Learning Health System science. Learn more.

PreAct

Clinician putting a swab into a tube

PreAct

Precision medicine activated 

Project status

Implementation
Scale

Collaborators

Ashley Haggerty, MD, MSCE  

Danielle McKenna, MS, LCGC  

Charlie Chambers, MCIT

Susan Domchek, MD  

Kate Nathanson, MD  

Payal Shah, MD 

Lauren Schwartz, MD  

Lainie Martin, MD  

Jacquelyn Powers MS, LCGC 

Derek Mann MS, LCGC

Innovation leads

Funding

Innovation Accelerator Program

Opportunity  

Approximately 1 in 75 individuals with ovaries will develop ovarian cancer in their lifetime. Unfortunately, ovarian cancer typically presents at an advanced stage with a poor prognosis.  

Some newly diagnosed ovarian cancer patients can receive maintenance parp inhibitors after chemotherapy, which have been shown to significantly decrease the risk of disease progression and death. To determine their eligibility for parp inhibitors, patients must complete genetic testing, a multi-step, manual process prone to delays.  

Genetic testing must be completed within four months of diagnosis to ensure optimal treatment. And on the backend, it is time consuming for providers to track which tests have been done and the results. 

When we started this work, only 65 percent of Penn Medicine patients newly diagnosed with ovarian cancer were completing genetic testing within the prescribed timeline. 

Intervention  

Precision Medicine Activated (PreAct) leverages technology to optimize genetic testing for patients and providers. Standardized inclusion criteria are used to automatically identify which patients need testing so that their information can be integrated into an interactive dashboard viewable by the care team. 

When a new patient appears on the dashboard, genetic counselors alert providers so that they can schedule a consultation to discuss parp inhibitors and prescribe genetic testing.  

Once patients get started, test results are automatically pushed to the dashboard. This allows providers to move forward with treatment or subsequent testing quickly and enables genetic counselors to identify if drop-offs happen in real time so that they can intervene before it is too late for patients to complete the testing pathway. 

Finally, PreAct streamlines workflows by embedding into Epic and enabling care team members to communicate via interactive notes directly within the dashboard. 

Impact  

PreAct ensures that care teams have access to the information they need to get the right drug to the right patient at the right time, thereby enabling optimal personalized treatment. It also reduces the cognitive burden on clinicians and decreases the number of staff needed to identify and track patients along the genetic testing pathway. 

The rates for genetic testing among ovarian cancer patients rose from 65 percent to 94 percent after PreAct was introduced. And the average time it took for patients to get an appointment scheduled with a genetic counselor decreased from between 100 and 150 days to only 15 days.   

Based on its success with ovarian cancer patients, the PreAct model is currently being tested in other disease sites, including colon, uterine, and pancreatic cancer. 

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

We hypothesized that if we could ease the cognitive burden on physicians and reduce friction, we could increase the percentage of genetic testing orders placed on time. To test this hypothesis, we manually pre-filled orders and attached them to the patient's visit in the electric health record. Next, we prompted providers to complete the order,...

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.

Fake back end

We hypothesized that if we could ease the cognitive burden on physicians and reduce friction, we could increase the percentage of genetic testing orders placed on time.

To test this hypothesis, we manually pre-filled orders and attached them to the patient's visit in the electric health record. Next, we prompted providers to complete the order, which they could do in only a few clicks.

This simple fake back end pilot resulted in a 20 percent increase in orders placed on time, thereby validating the approach.