Sizeable Data’s Role in Reducing Maternal Mortality

Between 2000 and 2023, global maternal mortality rates declined by 40%, according to UNICEF data. Despite this progress, approximately 197 women still die per 100,000 live births. These deaths disproportionately affect women from low- and middle-income countries and those with lower socioeconomic status.

This statistic underscores the need to ensure that advancements in healthcare truly benefit all women. Maternal deaths are largely preventable, and big data offers a powerful tool to address this challenge.

What Current Maternal Mortality Rates Tell Us

Even as global maternal mortality rates have decreased, progress has stagnated in the past decade. In 2023 alone, an estimated 260,000 women died from preventable causes related to pregnancy and childbirth according to the World Health Organization – roughly one woman every two minutes.

Data from the WHO indicates no improvement in maternal mortality rates among 150 countries between 2016 and 2020 , jeopardizing the Sustainable Development Goal (SDG) target 3.1 to reduce maternal mortality to less than 70 deaths per 100,000 live births by 2030.

This slow progress disproportionately impacts countries in Africa and India, as well as lower socioeconomic communities within other nations, such as Hispanic and Black women in North America. These disparities highlight inequalities in access to quality healthcare, even with medical advancements. Crises like disease outbreaks and conflicts further exacerbate these inequalities by diverting resources from maternal care.

The leading causes of maternal death include postpartum hemorrhage, hypertensive disorders during pregnancy, and infections. Sepsis, embolism, limited access to healthcare facilities, and complications from unsafe abortions also contribute significantly to these rates.

Where Are the Gaps Increasing Maternal Mortality Rates?

• Delays and Inequitable Access to Care: Timely access to emergency obstetric and newborn care can reduce maternal deaths by 15-50%. Millions of women live too far from healthcare centers equipped for safe deliveries, cesarean sections, blood transfusions, and life-saving medications.
• Failures in Quality of Care: Even when women reach facilities, inadequate implementation of protocols for hypertension prevention, hemorrhage management, and sepsis treatment can compromise their safety.
• Under-Resourced Information Systems: While maternal and perinatal death surveillance systems exist in many countries, issues with reporting, compatibility, and research hinder effective action.
• Funding Volatility: Global crises, such as the COVID-19 pandemic, can divert resources from maternal health, reversing progress and worsening statistics.
• Social and Structural Inequalities: Factors like poverty, gender norms, violence, socioeconomic status, transportation barriers, and racism create significant obstacles to accessing care.

What is Big Data? How is Big Data Contributing to Women’s Health?

Big data encompasses the vast amounts of information generated from electronic health records, registries, lab systems, and datasets related to various aspects of women’s health. Analyzing these datasets requires sophisticated methods, such as machine learning and natural language processing, to extract meaningful insights.

In breast cancer care, AI algorithms are being applied to mammograms and pathology slides to improve detection accuracy . Similarly, predictive models are being used to shorten the diagnosis time for Polycystic Ovary Syndrome (PCOS), which currently averages two years .

Machine learning models trained on pregnancy data can predict conditions like pre-eclampsia earlier and more accurately than traditional methods . These models can also identify women at high risk of postpartum hemorrhage, allowing for proactive preparation of blood products and medications .

In What Ways Can Big Data Facilitate Lower Maternal Mortality Rates?

• Risk Prediction and Early Warning: Machine learning models can predict complications like preeclampsia, postpartum hemorrhage, and sepsis, enabling timely interventions.
• Continuity of Care: Predictive models can identify women at risk of being lost to follow-up, allowing for targeted outreach and support.
• Improving Healthcare Access: Geospatial analytics can map travel times to healthcare facilities, informing investments in transportation and local infrastructure.
• Standardizing Emergency Care: Datasets can enable real-time monitoring of vital signs and medication administration at auxiliary health centers, guiding care decisions.
• Maternal Death Surveillance: Big data can digitize case reviews, standardize coding, and automate the synthesis of recommendations for health teams.
• Tackling Inequalities: Linking health data with socioeconomic information can help prioritize interventions for vulnerable populations.

While big data alone cannot solve the maternal mortality crisis, it offers significant potential to reduce rates by predicting risk, ensuring continuity of care, optimizing access, and standardizing emergency responses. The key to success lies in the operational will to implement these changes, prioritizing equity and sustainability.