Kennedy O’Hanley
DATA 150 Spring 2020
Problem Statement:
I am investigating the use of data science to improve the health of women and children, specifically maternal and newborn health. Right now, many women do not have access to safe health care facilities, and are in danger of losing their life or their baby’s life, but there is new technology that could help to minimize and eliminate these dangers that women in third world countries face. The harms I am seeking to address are using new data science to better equip women in under-developed countries for childbirth and pregnancy. There are many women losing their lives and their babies in these areas due to insufficient resources and a lack of funding and facilities. Specifically in Ethiopia, 80% of newborn deaths are caused by treatable cases. The neonatal mortality rate accounts for 41% of under-five-years old deaths. These statistics are staggeringly high. Along with infants, mothers are also at risk. Women have a one in fifty-two chance of dying from childbirth each year. The lives of so many people are risked simply by getting pregnant and giving birth. This is happening because Ethiopia, and many other third world countries don’t have the resources or facilities to properly care for women during this stage of life. There is about one midwife per 1,500 births, making it impossible for each woman to get the care and treatment she and her baby need. There is also a need for improvements in vaccination for children under five in other parts of the world as well. Many children aren’t getting the care or medicine they need. These problems could hugely benefit by having more access to resources and healthcare and emergency facilities. By using GIS techniques to collect and layer pregnancies with healthcare resources and facilities, the longevity of these women would rise. There are many women’s lives at risk, simply because of poor funding and an inadequate allocation of funding. Data Science could increase the quality of life for many people, and give women and children especially the freedoms they deserve.
Annotations:
Tatem, A. J., Campbell, J., Guerra-Arias, M., Bernis, L. D., Moran, A., & Matthews, Z. (2014). Mapping for maternal and newborn health: the distributions of women of childbearing age, pregnancies and births. International Journal of Health Geographics, 13(1), 2. doi: 10.1186/1476-072x-13-2
The article questions if there is a way to improve the data and estimations for the distribution of women who are of child-bearing age. By improving the estimations of these women, we can plan for women to be in safer conditions regarding their health as they give birth, and for the health of their newly-born babies. The authors discuss the Millennium Development Goals, which were eight goals set by 189 countries, aimed at improving the lives of the poorest around the world. The fourth of these goals was to lower child mortality and the fifth goal targeted maternal health. Maternal health was not improving as quickly as leaders had hoped. Even when looking at some of the countries who had progressed well as a whole, there were still subgroups of women who had inadequate resources and facilities. Some regions had even worsened and had poorer resources than what they started with. This article states three specific areas in which estimations could be improved to help narrow in on those who really need help: greater estimations of the population, especially women of child-bearing age; better projections about how many pregnancies will last short-term and long-term; and the need to link the information from these pregnancies to the health care facilities nearest to the women who need them.
Specifically in Ethiopia, it is common to have a skilled birth attendant (SBA), but there is a need for these SBA’s to provide access to the poorest women as well. There are huge wealth differences in Ethiopia, and usually poor women do not have access to an SBA or to a health facility near them. Despite not being able to have access to a SBA, there are midwives and health care workers distributed somewhat evenly throughout poorer areas. However, these health care workers are at about a 1:1,500 ratio with pregnancies, meaning there is one healthcare worker per 1,500 pregnant women. United Nations leaders have begun to do Midwife assessments, and are trying to figure out the best way to improve the field and training of Midwives, and allocate resources and funding to the correct areas.
The need for adequate and sufficient resources for maternal and neonatal health very closely relates to Amartya Sen’s definition of human development. Women should be entitled to a safe and healthy birthing process, both for the mother and child. This is a basic right that every woman should have access to, which takes Sen’s “friendly” approach to human development. Maternal and newborn health is currently one of the areas of human development that needs the most improvement, and the authors do a good job of discussing clear and concise methods to achieve this. Specifically, the focus of this article is on improving the population estimation of pregnant women and women of child-bearing age. Doing so would help narrow in on specific regions that need more healthcare workers or healthcare facilities. The authors suggest using a GIS based approach, collecting populations of women of reproductive age, then the number of pregnancies and live births, and then on top is the locations of health care centers specifically designed to aid pregnant women. If this approach is used consistently around the world it could be incredibly helpful. This article uses several different geospatial datasets to create visuals that demonstrate how using this technology could enhance our understanding of the women who need more help in every area. Specifically relating to Ethiopia, they collected data on the emergency maternal and newborn health care facilities with GPS locations, and then converted that into GIS shapefile format. Next it was translated to a Mollweide projection, which is used to most efficiently calculate distances. This eventually evolved into a visual map that shows the amount of pregnancies in Ethiopia, and how close they are in relation to these emergency care facilities. This article drives home how much lives of young mothers, or soon-to-be mothers, and the health of their newborn babies could improve through the use of data science.
Ebener, S., Guerra-Arias, M., Campbell, J., Tatem, A. J., Moran, A. C., Johnson, F. A., … Matthews, Z. (2015). The geography of maternal and newborn health: the state of the art. International Journal of Health Geographics, 14(1). doi: 10.1186/s12942-015-0012-x
This article focuses on ways that data science can be used to map where pregnant women and women of child-bearing age reside. While there is some existing data, the data could be significantly improved by updating the methods of sharing this data to the newer and more developed technology we have to date. The authors discuss how this can happen, and how we can improve our estimates for these women. It mentions the Millennium Development Goals, and how goal number five was to cut down on maternal mortality by 75%. It also references goal number four, for reduced newborn and infant mortality by two-thirds. According to the article, goal four and five were the most off track of the eight goals implemented in 2000. There weren’t enough resources and people being put into helping maternal and newborn health. Commission on Information and Accountability for Women’s and Children’s Health was created to help track and collect data on pregnant women and their newborns. It also helps discern the needs of accessibility in each area. This article doesn’t specify a specific region, but rather the data science behind the mapping of populations.
Sen’s definition of development aligns with this article because he talks about the unfreedoms that develop when there is an economic gap. Since some women do not have the money or capacity to travel long and far distances to get the care they deserve, they are falling prey to the developmental issues of this world’s inequality. The authors attempt to create new ways to map and visualize the population of women who need care, so that more birthing centers and specialists can be in place for the women who need it. This would eliminate the economic gap that exists now. If there were more equal and more spread out health care centers, women in all areas would have access to the help that Sen’s definition of development says they deserve. This article looks at maternal and newborn health and how to improve it. It includes several tables, which show different areas of the world and the current uses of data science in order to improve upon maternal and newborn health. It also has a data table looking at what kinds of data science and technology might be better suited for the job. In these tables there are all kinds of data science being used, and some of the more frequent types are using GIS to collect data from spatial analysis and modelling, in order to gather a mapping of several maternal and newborn health indicators. The authors of this article are looking at the inaccessibility for some women in regards to health care facilities. They mention specifically how some women are unable to reach birthing centers or health facilities, and they suggest specific solutions for using data science to improve the quality of life for these women and their newborns.
Mcpadden, J., Durant, T. J., Bunch, D. R., Coppi, A., Price, N., Rodgerson, K., … Schulz, W. L. (2019). Health Care and Precision Medicine Research: Analysis of a Scalable Data Science Platform. Journal of Medical Internet Research, 21(4). doi: 10.2196/13043
This article focuses on healthcare as a whole. Specifically, it discusses how big data needs to be modified to fit the rapidly moving data collection occuring today. The authors give very precise conclusions and methods demonstrating how the use of overarching data science platforms can be used to combine the large collections of data already existing in this world. This would be a very cost-efficient way to create pools of data that would help medicine distribution. They also discuss how big data has been a major aspect of collecting healthcare data. The authors want to make this data available on a single platform and make it easily and instantly accessible to those around the world. They look at how there are several newly developed platforms that take a look at the complications of big data, and ways to fix their downfalls. These platforms attempt to collect all of the data on healthcare into one place, making it more easily accessible to the public.
This is related to Sen’s definition of development, because it’s making the data more accessible to all. As well as the data, this would also help to pinpoint which areas need the most help after a natural disaster, or famine, or medical emergency. Creating a platform that connects all of the randomly collected data of healthcare that we currently have worldwide, would help to create equality for all. This equality is discussed deeply in Sen’s definition, in which he pushes the expansion of freedoms to be the ultimate goal of development. The authors are discussing the healthcare and medicinal aspects of human development, and suggest ways to help improve number three of the sustainable goals: health and well-being for all. A collective database where all data from healthcare around the world could live, would heavily impact this goal. There are some very specific plans and ideas in this article, that would help the right medicines get to the right people and help patients get the medical resources and facilities they need and deserve. There are lots of data science methods proving the point of the article. One example is the Hadoop platform. The Hadoop platform takes data and processes it and makes it open data, essentially attempting to create a useful, compact data collection for free. They also use Elasticsearch, which is a search engine for all kinds of data. These data platforms are open and free, and basically what this article is advocating for: a large dataset that includes all of the data already recorded, in order to send help where it needs to go. There are several data sets used as well. Specifically, there are several JSON files used, with physiological and laboratory data. A JSON file is used primarily as a way to send and transmit large quantities of data over different applications and websites. The authors are trying to determine if there is a way to combine all of the data sets collected from healthcare, and organize them in a way that will make it easier to send help to those who need it most.
Alegana, V. A., Atkinson, P. M., Pezzulo, C., Sorichetta, A., Weiss, D., Bird, T., … Tatem, A. J. (2015). Fine resolution mapping of population age-structures for health and development applications. Journal of The Royal Society Interface, 12(105), 20150073. doi: 10.1098/rsif.2015.0073
Where the other articles have focused more on maternal health and mapping out where women of child-bearing age are, this article addresses the population of children under five years old. It speaks of census data, and how it is often old and outdated, so it is up to data science to help make improvements. According to the article, we still have a very poor understanding of the countries and regions around us, and by gathering newer and more accurate data, we could create better, more effective plans that could really impact those that need it most. Specifically, this article targets the plans for vaccination strategies, educational planning or maternal healthcare delivery, and looks at how to improve the population count in order to improve the health and overall well-being of young children’s lives.
When looking at Sen’s definition of development, he strongly believes in the advancement of quality of life above everything else. He defines development to be the improvement of the freedoms that all people should be able to enjoy. By creating a more accurate population count of children, their lives would be improved. They would have access to facilities and resources to prevent illnesses and get treated if they do become ill. Being able to implement plans that will work for each region is highly important. Much like what Owen Barden said, one plan will not fit all countries. A healthcare plan that works for one area may not work for any other. Getting a population count would help to create a very specific plan for each area, in which each population could get the care and resources they need. The article discusses healthcare and improvements in child’s healthcare specifically. Sustainable goals three and four are discussed. Conducting a census, while possibly helpful directly after, is inefficient because it becomes outdated quickly and often does not get repeated for at least ten years. There are several data science methods used in this article in order to provide suggestions and new approaches. Global positioning services are used greatly, in order to specifically map where each population is. Specifically within GPS, there are several covariates, such as distance from roads, night-time lights, and enhanced vegetation in order to get better estimates for the number of children under five years old who live around the world. They used spatio-temporal models, in order to collect specific population counts from a given area at a given time. They were able to calculate the error of these models to be very small. They also used model-based geostatistics to estimate population. This article seeks to investigate and offer improvements for the third-world countries who do not have, but would greatly benefit from, accurate population models. It offers specific approaches to calculate a newer population count, mainly for children under five years old.
Bailey, P. E., Keyes, E. B., Parker, C., Abdullah, M., Kebede, H., & Freedman, L. (2011). Using a GIS to model interventions to strengthen the emergency referral system for maternal and newborn health in Ethiopia. International Journal of Gynecology & Obstetrics, 115(3), 300–309. doi: 10.1016/j.ijgo.2011.09.004
The objective of this article is to use GIS to inform health planners which areas need the most access to emergency health care. The authors of this article discuss the current uses for GIS techniques, and look at how and why it would be just as impactful to use for maternal and newborn health. Right now, this technology is being used to determine where to build new health facilities and where to land fieldworkers or helicopters, but it could also be used to determine where to use emergency transport vehicles, figuring out which facilities to upgrade for obstetric surgery. These authors offer specific scenarios and then counter with a GIS technique that could help fix the problem. They also look at different ways to create a “referral network” based on data collected. This referral network would help direct women to the best facilities for their needs, but the data must be collected and compiled before this could be a useful technique.
Ethiopia is the base of this scholarly article, because of the poor road infrastructure and the fact that there are very few health care facilities. The plans discussed in this article would be short-term plans for Ethiopia, while long-term plans were implemented and began, in order to create a better plan to follow from now into the future.
These plans follow Sen’s definition of freedom because every woman should have access to the facilities and resources they need. These authors understand that they won’t be able to fix the whole health care system in a short period of time, so they give clear plans to help women short-term so that long term plans can begin. The area of human development that these authors are targeting is neonatal health. The mortality of newborns and mothers is shocking in third world countries, specifically in this paper Ethiopia. According to Sen, this is no way to live, as mothers and their babies are not given the freedoms they deserve: resources and facilities to make the process of giving birth safer and easier. This article follows the third sustainable development goal, which serves to improve women’s health. These authors use GIS techniques to identify which healthcare facilities need the most improvements. There was also specific data collected about whether the people of Ethiopia have access to a landline or a cell phone, whether facilities have their own means of transportation for emergency cases, and which health services each facility provides. The primary dataset of this article is the Ethiopian Baseline Assessment for Emergency Obstetric and Newborn Care. This is a dataset containing data about the facilities and emergency health care procedures in Ethiopia. These authors aim to improve the lives of those women in third world countries who do not have safe and easily accessible ways to survive through childbirth and pregnancies. In order to improve this, the article suggests and looks at ways to create a country wide referral system to get women the help they need in a more expeditious manner. This would ensure quicker response times and would help women figure out where they need to travel or which facilities are best suited for their needs.