Improving screening for depression in prenatal and postpartum care


According to The American Congress of Obstetricians and Gynecologists, up to 23 percent of women struggle with depression symptoms during pregnancy.

Depression symptoms can increase a woman's risk behaviors during pregnancy, such as poor nutrition and substance and alcohol use, leading to premature birth, low birth weight, and development problems. 

At the start of this project, providers struggled to ensure consistent depression screening for prenatal and postpartum patients at the Helen O. Dickens Center for Women.


TIPS-Connect is a tablet-based depression screening model for use in prenatal and postpartum care. The intervention, co-designed with patients and providers, implements privacy-centric, evidence-based screening in the clinic setting. 

Patients presenting for new OB visits, 28-week prenatal visits, and initial postpartum visits are required to complete the screening as part of the check-in process. Results are uploaded immediately to the electronic health record (EHR) for provider reference, and decision support is offered based on raw patient scores.


At the initial pilot site, TIPS-Connect increased the standardized screening rate for prenatal depression from approximately 0 to 70 percent. Lessons learned from this project informed an enterprise-wide redesign of depression screening at Penn Medicine. 

TIPS-Connect is now a standard part of care at the Helen O. Dickens Center for Women. 

Phase 3: How we work

Ian Bennett, MD, PhD
Janet Rocchio RN, MBA 
Regina Howard
Rebecca Henderson
Marian Moseley, MSS, MLSP
Jabina Coleman, MSW, CLC
C. Neill Epperson, MD
Liisa Hantsoo, PhD
Becky Marlow, RN, BSN, MBA
The SPIRIT Group

Innovation leads

Katy Mahraj, MSI 
Matt Van Der Tuyn, MA
Roy Rosin, MBA


Innovation Accelerator Program

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 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 developed a prototype application on iPad to conduct PHQ-2 and PHQ-9 screenings for all eligible patients at three points during their prenatal and postpartum journey.

The practice provided the iPad to patients at check-in to complete screening before they saw the provider. The data flowed into a secure database monitored by social workers at the practice, who would work with the patient and their provider based on survey results to facilitate follow-up evaluation, care, and referrals as required.

Based on this pilot's success, the workflow was translated into a scalable, sustainable process in Epic using the Welcome module to provide screening on tablets and best practice alerts to enable real-time clinical decision support.


Pilot phase

There were two arms in the pilot phase of this project. In addition to testing in-person screening on tablets, we conducted a fake back end pilot to evaluate patient engagement with remote monitoring of mood during pregnancy. During this pilot, 33 percent of patients screening positive for depression risk in pregnancy agreed to text-based monitoring. Eighty percent of mood scores requested were received, and 50 percent of participants sought out text-based conversations with the practice about their mood. Based on these early results, we completed a clinical trial focused on remote monitoring of depression in the prenatal period. In a study with 64 pregnant women, most of whom were covered under Medicaid, we found that patients who had access to the clinic via a smartphone app were significantly more likely to open up about mental health concerns and spend more time in conversation with their clinician when symptoms increased. Also, those with access experienced fewer symptoms of depression and anxiety. Due to financial considerations, the smartphone app was not adopted at scale.

Katy Mahraj, MSI