Apply by Jan. 31 for Penn PORTAL career development funding to advance Learning Health System science. Learn more.

Together Care

Together Care

Post-operative and therapeutic care for high-risk patients in gynecologic oncology

Project status

Implementation
Scale

Collaborators

Nawar Latif, MD, MPH, MSCE

Leslie Andriani, MD

Lisa Mills, MS

Nick Bailey

Innovation leads

Funding

Innovation Accelerator Program

Opportunity

Penn Medicine's gynecologic oncology division serves a medically and socially high-risk population conducting an average of 162 surgeries and 435 chemotherapy visits per month. From 2017 to 2019, gynecologic oncology patients accounted for more than 700 emergency department (ED) visits, with patients from high community need index zip codes representing 45 percent of visits. Between 8 to 11 percent of patients in this population experience an unplanned readmission or ED visit after surgery – resulting in approximately $4.5 million in costs per year.

Intervention

Together Care is a personalized pathway that integrates digital support and home care services for gynecologic oncology patients undergoing surgical procedures or chemotherapy. Using the Way to Health platform, Together Care provides text message–based perioperative education, chemotherapy and postoperative symptom management recommendations, and streamlined patient triage support. Additionally, patients with highly complex surgeries or medical comorbidities are given early referrals to home health to better facilitate home-based, comprehensive care.

Together Care for surgery patients was evaluated over the course of four pilots between August 2021 and December 2023. In the fourth iteration, the team implemented a fully automated version of the texting program, with conversations monitored by staff to ensure accuracy and timely responses.

Impact

Across the four pilots, Together Care showed signs of promise in target areas. Few patients had a post-discharge ED visit (15 of 274) or surgery-related readmission (5 of 274). Participants reported high satisfaction, and no care disparities based on race and zip code were identified. At Penn Medicine's Dickens Clinic for Women's Health, a high-volume resident-training obstetrics and gynecology clinic, ED visits were 29 percent at baseline but 9 percent during Together Care's pilot 4, and the hospitalization rate was 3.2 percent at baseline but 0.7 percent during the pilot.

In May 2023, beginning with the fourth pilot, the program scaled to full clinical practice and is now the standard of care within the Department of Obstetrics and Gynecology. 

Way to Health Specs

Learn more about the platform
Activity monitoring
Arms and randomization
Criteria-based rules
Dashboard view
Device integration
eConsent
EHR integration
Email
Enrollment
Gamification
Incentives
IVR
Multiple languages
Patient portal messaging
Patient-reported outcomes capture
Photo messaging
Remote patient monitoring
Schedule-based rules
Survey administration
Two-way texting
Vitals monitoring

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 first conducted text message-based patient evaluations with a fake back end. We took the telephone script typically used for evaluations, created an algorithm for text messaging based on that script, and had a care team member send and reply to text messages according to the algorithm. This allowed us to evaluate the texting program and refine...

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 first conducted text message-based patient evaluations with a fake back end. We took the telephone script typically used for evaluations, created an algorithm for text messaging based on that script, and had a care team member send and reply to text messages according to the algorithm. This allowed us to evaluate the texting program and refine the algorithm in response to patient and provider feedback before setting up the automated texting service.