AI: a transformative force in maternal healthcare

Timely medical intervention is a critical factor in ensuring the wellbeing of both mother and baby during pregnancy, childbirth and the postnatal period. Unfortunately, women continue to struggle with maternal deaths due to inadequate medical care, lack of early interventions and various health complications.

While the maternal death rate is the highest in countries with low per-capita income, with the most occurring in sub-Saharan Africa, as well as densely populated low-income communities in South and Southeast Asia, countries such as the United Kingdom and the United States have seen a staggering rise in maternal death. In the UK, the figure has increased to a level that has not been seen in almost 20 years. Similarly, the US has seen an alarming rise in maternal death across all ethnic groups. It remains the only nation with a high per-capita income with a worrying incidence of maternal death despite its substantial spending on healthcare.

Shifting the health landscape

Artificial intelligence (AI) and robotics have enormous potential in healthcare and are quickly shifting the landscape – emerging as a transformative force. They offer a new dimension to the way healthcare professionals approach disease diagnosis, treatment and monitoring. AI is being used in healthcare to help diagnose patients, for drug discovery and development, to improve physician-patient communication, to transcribe voluminous medical documents, and to analyse genomics and genetics. Labs are conducting research work faster than ever before, work that otherwise would have taken decades without the assistance of AI. AI-driven research in life sciences has included applications looking to address broad-based areas, such as diabetes, cancer, chronic kidney disease and maternal health.

In addition to increasing the knowledge of access to postnatal and neonatal care, AI can predict the risk of adverse events in antenatal and postnatal women and their neonatal care. It can be trained to identify those at risk of adverse events, by using patients’ health information such as nutrition status, age, existing health conditions and lifestyle factors. 

AI can further be used to improve access to women located in rural areas with a lack of trained professionals – AI-enabled ultrasound can assist front-line workers with image interpretation for a comprehensive set of obstetrics measurements, increasing quality access to early foetal ultrasound scans. The use of AI assistants and chatbots can also improve pregnant mothers’ experience by helping them find available physicians, schedule appointments and even answer some patient questions.

AI algorithms

Many healthcare professionals I have spoken to emphasised that pre-existing conditions such as high blood pressure that leads to preeclampsia, iron deficiency, cardiovascular disease, age-related issues for those over 35, various other existing health conditions, and failure in the progress of labour that might lead to Caesarean (C-section), could all cause maternal deaths. Training AI models to detect these diseases early on and accurately for women could prove to be beneficial. AI algorithms can leverage advanced algorithms, machine learning (ML) techniques, and predictive models to enhance decision-making, optimise healthcare delivery, and ultimately improve patient outcomes in foeto-maternal health.

For example, foetal heart monitoring (FHR) has long been important for those identified as having high-risk pregnancies. FHR offers critical insights into the foetal condition, helping healthcare professionals assess the safety of the foetus. AI-driven algorithms can analyse complex FHR patterns, detecting subtle anomalies that may not be readily noticeable with traditional monitoring methods.

Similarly, an AI algorithm-based clinical decision support system was developed to prevent ectopic pregnancy – which is one of the major causes of mortality and morbidity. To avoid complications, early diagnosis and the choice of initial treatment for such patients is decisive.

Moreover, to improve access to services in rural areas, Restless Multiarmed Bandit (RMAB) is a framework used in AI to optimise resource allocation in dynamic environments. This method is particularly useful where resources are limited, and decisions need to be made sequentially under uncertainty.

A practical application of RMAB is seen in the healthcare sector, specifically in improving maternal and child health outcomes. For example, the SAHELI project in India employs RMAB to prioritise outreach to beneficiaries by community health workers, ensuring the most effective use of limited resources to improve maternal and child health outcomes.

To address racial gaps and inequality in maternal healthcare, Safe Babies Safe Mom (SBSM), a project in Washington, DC, has been designed to leverage AI to mitigate the impacts of systemic racism in maternal care and address disparities among different communities. By employing advanced techniques in artificial intelligence and machine learning, SBSM aims to develop a maternal and infant health safety surveillance system for hospitals. This system is intended to proactively identify risks that could lead to adverse outcomes for birthing individuals and their babies.

AI concerns

Significant concerns, however, remain surrounding biases, lack of transparency and privacy in the use of AI in healthcare.

While we have yet to see any legislation to regulate the use of AI in the US, the EU has taken a significant step forward with the approval of its EU Artificial Intelligence Act (EU AI Act). The act encourages responsible innovation within the AI space – including healthcare AI applications but establishes strict prohibitions on certain AI practices classified as high-risk. This legislation is expected to have a substantial impact on the global AI landscape, extending far beyond the EU’s borders. The first of its kind, the legislation creates a comprehensive framework for AI regulation.

As for preventing biases, particularly in maternal health care – AI algorithms should be regularly monitored and audited, while healthcare professionals should work with developers to tailor algorithms to specific populations. It is also essential to include sex and gender diversity both in research practices and in the workplace – particularly in the field of STEM, to bring in perspectives otherwise not available in a field mostly dominated by men.

It is important to remember that AI is not a replacement for human connection but rather complements the expertise of healthcare professionals and enhances the experience of patients. Not all aspects of maternal care will equally benefit from the use of AI. More should be invested in the training of healthcare professionals. While machine learning algorithms can analyse large datasets and assist clinicians in assessments, they cannot replicate the authenticity or empathy that human professionals offer.

Afifa Waheed trained as a barrister, is co-founder of an NGO, a former UN adviser, and is currently a lawyer in New York City with expertise in healthcare, intellectual property law and litigation.