Expanding Impact: How Safe Babies Safe Moms Data is Powering Research Across Health Systems

By: Aditi Bhardwaj is a Data Scientist working with the Health Care Financing Initiative and the Massive Data Institute, McCourt School of Public Policy, Georgetown University.

The Safe Babies Safe Moms (SBSM) initiative is a rich, real-world maternal health program grounded in collaboration between MedStar Health, community-based organizations, and researchers. At its core, SBSM has collected a robust dataset capturing clinical, social, and operational data across a maternal care journey—from prenatal care to delivery and beyond. Our team at Health Care Financing Initiative (HCFI) has worked closely with these data over the last 5 years to assess the program’s return on investment and broader societal impact.

Last year, our research team presented at the MedStar Health and Georgetown University Research Symposium. We demonstrated the significant economic value of SBSM. Using detailed cost data, risk stratification models, and longitudinal tracking of maternal outcomes, our analysis showed that in 2022 alone, the program’s $2.3 million cost was outweighed by substantial health and financial gains—resulting from a 5-year societal net present value of $5.2 million. The reduction in preterm births emerged as the program’s standout outcome, producing measurable savings for the healthcare system and improving the long-term well-being of families.

SBSM Dataset: A Shared Resource for Innovation

Importantly, our work is just one example of how SBSM data is enabling deeper understanding of maternal health interventions. The dataset—securely managed and de-identified for research use—is now supporting multiple analytical efforts across institutions and disciplines. This collaborative use of data reflects the growing emphasis on shared learning and system-wide evaluation in maternal health.

One notable example is the recent case study published by NEJM Catalyst. The research team at MedStar Health Research Institute conducted an independent evaluation of SBSM as part of a broader inquiry into value-based maternal health interventions. The case study not only echoed several of our core findings—particularly on the cost-saving potential of preterm birth prevention—but also cited our 2024 research brief as a foundational input.

This external validation speaks to the strength of both the SBSM model and the data infrastructure that supports it. By enabling rigorous, multi-angle analysis, HCFI can help researchers and policymakers alike identify the mechanisms that truly improve maternal and infant outcomes—while also maintaining financial sustainability.

Looking Forward: A Model for Evidence-Based Policy

As conversations around maternal health reform and value-based care continue to gain momentum, programs like SBSM are increasingly cited by researchers and health system leaders as examples of what’s possible when clinical innovation is supported by strong data infrastructure. Still, sustaining and scaling this kind of work is not straightforward. Practical challenges—especially around Medicaid and private insurance reimbursement—remain front and center (Hall & Greenberg, 2016).

What many in the field agree on is that a shared, well-structured data foundation is essential for advancing research for improving outcomes for mothers and babies. Continued research from diverse perspectives—clinical practice and health economics—will be key to identifying what’s needed to make perinatal value-based care models both effective and sustainable over the long term.

I am proud to be part of this collaborative journey and am grateful to our colleagues across the SBSM ecosystem who continue to expand the understanding of what makes maternal health programs successful.

Acknowledgments

This work was made possible by the dedicated efforts of the Health Care Financing Initiative (HCFI) team. Special thanks to:

• Carol Davis, Ph.D., MBA, Assistant Research Professor & HCFI Associate Director
• Vika (Jin) Li, Master of Science in Data Science for Public Policy, McCourt School of Public Policy, 2025
• Yuhan Ma, Master of Science in Data Science for Public Policy, McCourt School of Public Policy, 2025
• Yetong Xu, Master of Science in Data Science for Public Policy, McCourt School of Public Policy, 2024
• Rehman Liaqat, Master of Public Policy, McCourt School of Public Policy, 2024

To explore our research further, visit the HCFI website.