THEA: Take Home Electronic Assessment
Project status
Collaborators
Anna Graseck, MD, MSCI
Chris Klock, MBA
Abbie Lund, MA
Katy Mahraj, MSI
Penn Medicine Women’s Health Center for Clinical Innovation
Innovation leads
Funding
Richard and Carolyn Sloane OB/GYN Innovation Award
Penn Medicine Women’s Health Leadership Council
Opportunity
Hypertensive disorders of pregnancy, such as preeclampsia, complicate up to 8 percent of pregnancies in the United States. These can lead to serious negative health effects and are potentially fatal.
Frequent blood pressure (BP) monitoring during pregnancy can help clinical teams detect hypertensive disorders and address them early. However, requiring an office visit to take BP readings can place a burden on patients who need to organize transportation and set aside time for travel. Office visits also require clinician time and effort that, in the case of patients who have normal BP readings and no symptoms, could be directed at more critical tasks.
Intervention
Take Home Electronic Assessment (THEA) is a text message–based program for monitoring prenatal BP. Patients enrolled in THEA receive a BP cuff and weekly reminders to measure their BP and text back their readings. The results are imported immediately into the electronic health record, and abnormal BPs are flagged for clinician review.
THEA also supplies prenatal educational content via text message, including instructions for using the home BP cuff and information addressing common health concerns during pregnancy. Content is tailored according to gestational age, ensuring patients receive information when it is most relevant. Patients can also send questions, and often THEA can reply with an auto-generated response based on keywords detected within the message.
The THEA program takes inspiration from Heart Safe Motherhood, a remote monitoring intervention we developed to monitor postpartum patients already diagnosed with hypertensive disorders of pregnancy.
Impact
With THEA readings and telemedicine visits incorporated into the prenatal visit schedule, obstetrics practices reduced the mean number of in-person visits from 10.5 to 6.9 during the one-year study window, summing to more than 5,700 in-person visits and 1,400 hours of clinical time.
THEA’s acceptance rate was 82 percent, with 44 percent of BP requests receiving a response. Because of the automated monitoring and elevation, staff were able to focus on patients with high readings – about 6 percent of BPs received – and triage these individuals to more intensive outpatient monitoring, laboratory testing, or delivery as merited. During the one-year study, 40 (out of 4,399) enrolled patients were diagnosed with a hypertensive disorder, nine of those being preeclampsia.
THEA has been available to all obstetrics patients at the Penn OB-GYN Associates (POGA) clinic and Dickens Center for Women’s Health since December 2021. In 2024, the program expanded to maternal-fetal medicine practices at Hospital of the University of Pennsylvania. In early 2025, Pennsylvania Hospital adopted the educational messaging component of THEA.
Way to Health Specs
Learn more about the platformInnovation Methods
Quantitative data review
Quantitative data review
We used A/B testing to determine the best date/time to send educational content to participants to maximize engagement with educational links.
Fake back end
Fake back end
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 used a fake back end to assess the feasibility of using natural language processing to classify patient requests for handling and automated response.