Maternal health, safe deliveries, pre-partum and post-partum care are crucial not just for the mother but also for the newborn. Through fine grained segmentation of ultrasound scans and echo during pregnancy, a lot of abnormalities can be detected and managed earlier in childbirth and recent trends in multimodal AI and Computer Vision have made such advancements possible. Moreover right doses of medication and food can be recommended by AI customized on the mother’s health over the course of pregancy.
This review discusses how AI can help promote maternal and neonatal health when resources are low to counter morbidity or diseases acuired from hospital settings. AI can help in monitoring maternal health, predicting risks of preterm deliveries and miscarriages, gestational diabetes and anemia, congenital cardiac disease, PPD and anxiety etc. as well as pain, jaundice, sepsis and malnutrition in neonates.
https://www.frontiersin.org/journals/public-health/articles/10.3389/fpubh.2022.880034/full
In this paper, the authors developed a method to perform fetal organ classification from ultrasound images, using a DenseNet model. The model was able to classify the brain, abdomen, femur, and thorax, as well as the maternal cervical parts with promising accuracy, and this can help obtain early medical intervention if necessary.
https://www.nature.com/articles/s41598-023-44689-0
Several pregnancy related diseases and complications that can be predicted using AI have been discussed in this review. Diseases such as Gestational Diabetes, Preeclempsia and complications such as Perinatal Death, Stillbirth, Neonatal Death, Preterm Birth, Spontaneous Abortion etc. can be identified and specific procedures such as C-section and an appropriate time for performing them can be suggested.
https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2023.1130139/full
Public health issues in maternal health are a major concern worldwide, particularly in marginalized and underserved communities. These Public health issues are influenced by a variety of social, economic, and structural factors. Improving access, reducing bias, enhancing social support, and expanding mental health services and community programs will play a key role in addressing them.
In this article, Public health issues in maternal morbidity and mortality were reported with increasing incidence. Public health issues in maternal care and outcomes even worsened during the COVID-19 Pandemic.
This paper outlines racial and ethnic Public health issues in maternal mortality and severe maternal morbidity, introduce a framework that describes the complex web of factors, describes the impact of suicide and substance use disorder on the maternal mortality crisis and discusses how similar quality of care levers that have been identified as crucial in reducing Public health issues can address the under-recognized issue of maternal mental health and self-harm.
https://link.springer.com/article/10.1007/s00737-021-01161-0
Despite advancements in healthcare, significant Public health issues persist in maternal health outcomes, particularly in marginalized populations such as Black, Indigenous, and rural women as described in this article. Key drivers include socioeconomic barriers, implicit bias, and racial discrimination within healthcare systems. Additionally, geographic Public health issues wherein rural populations often lack sufficient healthcare infrastructure further contribute to unequal maternal health outcomes.
AI has the potential to significantly improve maternal health outcomes by addressing Public health issues, enhancing diagnostics, and improving access to care. Collaboration between technologists, healthcare providers, and policymakers is essential to realize the full potential of AI in improving maternal health.
This analysis examines the application of AI chatbots and NLP to enhance maternal-infant healthcare by facilitating personalization and self-management through data acquisition on health parameters, such as weight gain, blood pressure, incontinence, mental health, nutrition and physical activity. As the application is refined and expanded, it could significantly improve maternal and infant health outcomes, and increase the accessibility of personalized care.
This article discusses an automated method to detect hypertension in pregnant and postpartum women, that aims to eradicate implicit and explicit racial biases and inequitable treatment. Hypertension was found to increase complications in pregnancy especially among Black non-hispanic women and how automation and AI can help prevent this.
This study utilised natural language processing to develop a maternal health education chatbot using a feedforward deep neural network in the native languages of some of the marginalised communities. If deployed into wearable sensors it can monitor and provide pregnant women with the much needed resources and education to manage their health and well-being.