U.S. flu vaccine distribution logistics could use an update, according to Pinar Keskinocak. The researcher at the Georgia Institute of Technology co-led a recent study that compared the current approach with a proposed allocation method calculated to save many more lives in a pandemic or similarly intense influenza outbreak that taxes vaccine supplies.
The study's recommendations, which apply to resupplying vaccine stocks during a running outbreak, boil down to this: To put a bigger dent in the spread of flu, replenish vaccine stocks in regions where they are being used up and don't replenish them in areas where vaccines are just sitting on shelves, because few people are getting flu shots there.
The tweak in the supply chain could also save thousands of lives annually in regular flu seasons in the U.S., which can be plenty deadly. A flu season can take more lives than murders in the same time period.
“Even seasonal flu kills tens of thousands of people each year, so we would benefit immediately,” said Keskinocak, who is William W. George Chair and Professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering and Director for the Center of Health and Humanitarian Systems.
“In a pandemic, nearly no one would have natural immunity, so the death toll could be significantly high if we don’t improve vaccine coverage.”
What makes a pandemic a pandemic? The flu virus represents a mutation that human immune systems have not had a chance to build prior resistance to, thus the lack of natural immunity. When the next one strikes, in addition to the many lives saved, the researchers’ recommendations could massively prevent flu infections, secondary infections like bronchitis, hospitalizations, and unnecessarily high medical costs.
Keskinocak, co-principal investigator Julie Swann from North Carolina State University, and first author Zihao Li of Georgia Tech published their results in the journal Plos One in October 2018, around the start of the 2018-19 flu season. The research was supported by the Harold R. and Mary Anne Nash Junior Faculty Endowment Fund.
When a pandemic hits, or a flu season that taxes the vaccine stocks, vaccine supply may become limited but then catch up over time. When that happens, the vaccine distributors commonly take what’s called the population-based approach.
“Areas with larger populations get more vaccine, proportional to the population. It’s a straightforward approach that seems fair,” Swann said.
As more vaccine becomes available over time, restocking follows the same principle, and that is where distribution logic breaks down. In some regions, few people get vaccinated, but under population-based allocation, resupply stocks go there anyway and may go to waste. Meanwhile, restocking may fall short of demand elsewhere, where people are lining up for inoculations.
As a result, in a pandemic, people eager for a vaccination might not get one despite adequate vaccine production, and the resulting additional unvaccinated people are more likely to get the flu and also spread it to others. That intensifies the outbreak for the entire population.
The wasted vaccine stocks also drain medical finances, and the new model would releave some of that strain even in regular flu seasons.
“Production, storage, and delivery of vaccine are costly, and unused inventory can’t just be thrown away. It costs money to dispose of,” Keskinocak said.
Restocking doses where they are actually being used would benefit the entire population by boosting the total number of vaccinated individuals, who would then be less likely to get sick and to infect other people. That would tamp down the flu wave for everybody.
Leftover inventory could be slashed to about 20 percent of current levels, saving considerable costs, and the data about which areas were not resupplied could be used to identify areas where more people need encouragement to get vaccinated.
“The data would tell you where you need continued education about the importance of vaccination, and some of the money saved from unnecessary resupplying could be invested in public health campaigns,” said Swann, who collaborated with the Centers for Disease Control and Prevention during the 2009-10 H1N1 Swine flu pandemic.
But the needed data is missing at present in the U.S. vaccine distribution system.
“Surprisingly few states have systems in place that tell them how much vaccine has been administered where and how much is still left in inventory at provider locations,” Swann said.
The next “big one” flu pandemic will sneak up on humanity someday.
Ultimately, the best way to cut its death toll by more than half and save possibly hundreds of thousands of lives will be for virtually everyone to get vaccinated against influenza annually. Currently, fewer than 50 percent of Americans do.
The 1918-19 outbreak, which may have consisted of multiple concurrent influenzas, killed 678,000 people in the U.S. Other “big ones:” The 1957 “Asian flu” killed 116,000 in the U.S.; the 1968 “Hong Kong flu” killed 100,000. The 2009 bird flu pandemic, which was a less contagious virus, killed 12,500 people in the U.S. and hospitalized some 275,000.
Also Read:
Want to beat antibiotic-resistant superbugs? Rethink that strep throat remedy.FDA Taps Georgia Tech to Help Reduce Cost of Making Antibiotics
Thinking about grad school?
Here's how to apply to Georgia Tech.
The study was supported by the Harold R. and Mary Anne Nash Junior Faculty Endowment Fund, and by the following Georgia Tech benefactors: William W. George, Andrea Laliberte, Joseph C. Mello, Richard “Rick” E. and Charlene Zalesky. Any findings, conclusions, or recommendations are those of the author(s) and not necessarily of the funders.
Media relations assistance: Ben Brumfield
(404) 660-1408
Research News
Georgia Institute of Technology
177 North Avenue
Atlanta, Georgia 30332-0181 USA
Writer: Ben Brumfield
]]>To address that need, systems engineers at the Georgia Institute of Technology are using computer models to help resource-poor nations improve supply chain decisions related to the distribution of breast milk and non-pharmaceutical interventions for malaria. They are also forecasting what health care services would be available in the event of natural disasters in Caribbean nations.
“We are using mathematical models implemented in user-friendly tools like Microsoft Excel to improve the allocation of limited resources across a network, especially in resource-poor settings,” said Julie Swann, an associate professor in the H. Milton Stewart School of Industrial and Systems Engineering at Georgia Tech.
Swann reported on three global health case studies designed to improve the allocation of limited health care resources on Feb. 19, 2012 at the annual meeting of the American Association for the Advancement of Science (AAAS) in Vancouver, Canada.
For the first project, Swann and a group of graduate students created models to strategically determine how a nongovernmental organization (NGO) in South Africa should expand its breast milk donation and distribution network to the whole country. In the network, healthy mothers donate breast milk, which is stored in a local repository, transferred to a milk bank to be processed and then distributed to neonatal units where mothers cannot provide it themselves because of disease status or physical inability.
“We wanted to determine how we could provide breast milk to the most people while also being geographically equitable in terms of access,” explained Swann, who holds the Harold R. and Mary Ann Nash chair at Georgia Tech. “We looked at the cost of equity and how that changed the distribution design.”
To determine where the organization should expand its network and the best way to do so, the team used operations research to examine the existing and proposed locations in the network as well as what type of transportation would work best to cover the increased geographic area. The model recognized that breast milk supply increases with higher income and education levels and low HIV prevalence, while breast milk demand increases with lower income and education levels and high HIV prevalence.
The researchers recently recommended locations for expansion to the NGO and advised the organization to pay a courier service to carry the milk to the neonatal units, in order to balance cost and reliability and improve efficiency. Volunteers, who are inherently less reliable, were driving the milk from one location to another.
In another project, done in collaboration with the World Health Organization, Swann and a team of undergraduate and graduate students used models to optimize the distribution of non-pharmaceutical interventions for malaria, such as nets or sprays, with pilot data from a country in Africa called Swaziland.
Their models provided a time-based deployment plan for the country, including details on what geographic zones to target for spraying, when to deploy in each zone, how many people can be protected in each zone, what resources should be located at the distribution centers, and the opening and closing dates of the distribution centers.
The researchers showed that using a systems approach to examine allocation decisions could increase the number of people covered with the same amount of funding by more than 25 percent. The team worked with Pinar Keskinocak, a professor in the Stewart School of Industrial and Systems Engineering at Georgia Tech, to develop a teaching game based on the work. The game has been used worldwide in classes of humanitarian students.
For the third project, Swann and a team of graduate students are using technology to estimate the performance of disaster preparedness plans in advance of an event. The project is part of the Caribbean Hazard Assessment Mitigation and Preparedness (CHAMP) initiative, which is supported by a Georgia Tech alumnus and led by Reginald DesRoches, a professor in the School of Civil and Environmental Engineering at Georgia Tech.
In Puerto Rico, Swann’s team evaluated the existing hospital networks and other health care provider locations described in the island’s emergency preparedness plans.
“To forecast the country’s ability to provide health services following an earthquake, we took population data and overlaid it with projections of earthquake locations and severity to estimate the capacities and amount of congestion that would result at health care facilities,” said Swann.
The researchers recently presented the initial results of their study to the Puerto Rico Department of Health and made recommendations for health care resources and hospital capacities based on predicted bottlenecks in the system. They are currently examining Belize’s hurricane evacuation plans. Keskinocak and Stewart School of Industrial and Systems Engineering associate professor Ozlem Ergun and visiting assistant professor Pelin Pekgun-Cakmak are also contributing to the CHAMP initiative.
“We have found that technology innovations like mathematical models can help to solve problems in global and public health, such as the allocation of limited health care resources,” noted Swann.
Research News & Publications Office
Georgia Institute of Technology
75 Fifth Street, N.W., Suite 314
Atlanta, Georgia 30308 USA
Media Relations Contacts: Abby Robinson (abby@innovate.gatech.edu; 404-385-3364) or John Toon (jtoon@gatech.edu; 404-894-6986)
Writer: Abby Robinson
]]>A new online tool takes the guesswork out of developing individualized catch-up immunization schedules by allowing parents and health care providers to easily create a schedule that ensures missed vaccines and future vaccines are administered according to approved guidelines.
“The immunization schedule is complex,” said Larry Pickering, executive secretary of the Advisory Committee on Immunization Practices (ACIP) of the Centers for Disease Control and Prevention (CDC) and a collaborator on the project. “By using the online immunization scheduler, parents can ensure that their children stay current on all recommended vaccines, and they can also obtain useful information about vaccines and vaccine-preventable diseases.”
The online catch-up immunization scheduling tool, which was developed by the Georgia Institute of Technology and the Centers for Disease Control and Prevention (CDC), is available at https://www.vacscheduler.org/. Since the new tool launched in January 2012, the site has recorded nearly 63,000 visits, 22 percent of them repeat visitors. Nearly half of the visitors identified themselves as health care providers.
The new online tool replaced a downloadable software program that was released by Georgia Tech and the CDC in 2008. The original software was designed by Professor Pinar Keskinocak and former graduate student Faramroze Engineer from the Georgia Tech Stewart School of Industrial and Systems Engineering. Researchers in the Georgia Tech Research Institute (GTRI) converted the software program into the new online tool and adapted it to show different views tailored for parents and health care professionals.
“We’ve resolved several issues that existed with the downloadable catch-up immunization scheduling program by creating the online tool,” explained Keskinocak. “For instance, some physicians told us that they were not able to download the original software program to their work computers because of information technology security restrictions and some users expressed concern because the program had to be downloaded again whenever updates to the vaccination rules were issued.”
The online tool removes the challenging task of simultaneously considering complex rules, guidelines and discretionary considerations when creating a catch-up schedule. A physician or caregiver simply inputs a child’s date of birth and previous immunization dates, and selects whether to administer the vaccines as soon as possible or to administer the vaccines when recommended. Then the program displays a personalized schedule of the recommended dates to administer all future vaccines, which can be saved to the user’s computer.
“I have found the online scheduling tools to be very user friendly and helpful,” said Thomas J. Steiner, the pediatric lead physician with Kaiser Permanente Gwinnett, in Duluth, Ga. “One of the most useful aspects is the fact that after the patient’s immunizations are entered, you can print a ‘catch up’ schedule which can be given to the patient and scanned into the patient’s chart.”
Vaccines included in the scheduler are those required between birth and six years of age: Hepatitis A and B, Rotavirus, Diphtheria/Tetanus/Pertussis, Haemophilus influenzae type b, Pneumococcal, Polio, Measles/Mumps/Rubella, Varicella (Chickenpox).
The scheduler follows the guidelines developed and revised each year by ACIP in collaboration with the American Academy of Pediatrics and the American Academy of Family Physicians. These guidelines include the feasible number, timing and spacing of doses of each vaccine based on the child’s age, the number of doses and the age at which each dose was administered.
In addition, each dose of each vaccine has a minimum, maximum and recommended age for administration, and there are minimum and recommended gaps between doses. These gaps as well as future administrations of a particular vaccine may vary depending on the age of the child and the age at which previous doses were administered.
If a child requires more than one live vaccine to be administered, there are two options: administer all live vaccines on the same day or wait 28 days between live vaccine injections. There also may be discretionary considerations such as limiting the number of simultaneous administrations a child receives or the number of visits required to complete the series for all vaccines.
GTRI researchers converted the downloadable program into software that could run online. While doing so, they added the capability to show slightly different information depending on whether the visitor was a health care professional or a parent.
“We can have the same algorithm and recommendation rules, but the interface can vary slightly based on the audience,” said Sheila Isbell, a GTRI research scientist who led the software conversion effort. “If the visitor is a parent, we can show parent-friendly footnotes instead of physician-specific ones and provide more basic information about the vaccines and the importance of completing the immunization regimes.”
As part of the redesign for online operation, the researchers also separated the information that are likely to be changed and housed it in a database that would be easier to update as recommendations change. Housing the rules in a database could also allow the system to be used in other countries where vaccination schedules differ from those of the United States.
For the future, the GTRI team is creating a version that combines child and adolescent schedules to allow it to serve persons up to 18 years of age. A version designed for mobile devices is also under development.
In addition to Isbell, GTRI researchers Scott Appling, Therese Boston, Josh Cothran, Moon Kim and Arya Irani also contributed to the software conversion project, which was supported by GTRI’s Independent Research and Development program.
Beyond advising on vaccination schedules, the tool may also encourage interactions between parents and physicians.
“By using the scheduler, parents will enhance their knowledge of vaccines and the diseases they prevent, and receive assistance in formulating questions that can be discussed with their child’s physicians and nurses, resulting in more productive interactions,” said Pickering, who is also a professor of pediatrics at Emory University School of Medicine.
Research News & Publications Office
Georgia Institute of Technology
177 North Avenue
Atlanta, Georgia 30332-0181
Media Relations Contacts: John Toon (404-894-6986)(jtoon@gatech.edu) or Lance Wallace (404-407-7280)(lance.wallace@gtri.gatech.edu).
Writer: Abby Robinson
Research News & Publications Office
(404) 894-6986
]]>The APCD was established by the Georgia General Assembly (O.C.G.A. 31-53-40) by Senate Bill 482 in 2020 to address growing concerns over the cost, quality, and access to healthcare across the state. The Office of Health Strategy and Coordination (OHSC) is responsible for creating and implementing the APCD, and the APCD's administrator is GTRI’s Center for Health Analytics and Informatics (CHAI).
When in full operation, the APCD will provide regular reports on Georgia health care issues and accept requests from stakeholders for other customized data. Beyond benefits to researchers and policymakers, the data will help support price transparency and drive consumer-focused tools reporting on such issues as quality, cost, and patient outcomes. The APCD’s information will not include any personally identifiable information about patients.
“The APCD will serve as a platform to help us really understand and improve the quality of health care in Georgia,” said Megan Denham, a GTRI senior research associate who serves as Implementation Project Director for the system. “It will help the citizens of Georgia understand more about their care and know what to expect so they can make informed decisions. Policymakers will use the data to drive funding allocations and make interventions. For our large community of researchers, it will allow them to leverage a really broad view of health data.”
Development of the system will put Georgia among the more than two dozen U.S. states that are able to make critical health care decisions based on data about the specific needs of their citizens, said Jon Duke, director of GTRI’s Health Emerging and Advanced Technologies (HEAT) Division.
“The Georgia APCD will move Georgia into the ranks of states that have a deeper understanding of their population’s health, health care costs and utilization, and opportunities for improvement,” Duke said. “We’ve seen report after report of how all-payer claims databases have led to concrete reductions in cost, improvements in care, and more informed policy-making across a wide range of topics. It will be a huge win for Georgia.”
The system will initially include information for about 5.4 million Georgia citizens – more than half of the state’s population – and is expected to be the largest aggregator of the state’s health data. The information will include data from Medicare, Medicaid, and the state health benefit plan, along with commercial claims payers.
Data will be provided in aggregate, and maintained without personally identifiable information. “Privacy and security are paramount,” said Duke. “There’s a huge focus on privacy protection, and we have an incredible team of collaborators across the state working to help ensure that we provide only the minimum data necessary for key use cases. The APCD will not analyze or share patient identifiers such as medical record numbers, names, or addresses.”
Beyond data on specific treatment protocols, the system will also provide information on their context. For instance, data on a knee replacement surgery could include information on imaging done, diagnostic testing, and presurgical activities leading up to the procedure, as well as physical therapy afterward – and both cost and outcome measures.
“It’s much more than just the surgery,” said Denham. “We want to look at it as a whole, and also consider the components. That gives more information about the care that people are receiving and what they can expect.”
Beyond the care itself, the system will provide generalized information about patients receiving it – demographics, the symptoms that led to the diagnosis, relevant medical conditions such as arthritis and diabetes, and other claims made by the patient.
“All of these things can be brought together to help understand the equation,” said Duke. “People who have had knee replacement surgery can be looked at in the aggregate so we can assess potential risk factors for poor outcomes, or conversely, factors that may support patients recovering more quickly.”
Certain claims-paying entities are required by law to provide data to the APCD, while others are invited to submit information voluntarily. Beyond the value to policymakers and researchers, information about Georgia-based costs will also be helpful in understanding what consumers pay as their share of health care service costs.
“Price transparency is a key goal for the APCD. While there are many factors affecting what data can be shared, in other APCD states, there are excellent tools designed to support consumer knowledge about the cost of different procedures at different locations where someone might go for a specific procedure,” Duke said. “Some tools provide data on health care quality from Medicare and Medicaid which allows for some integrated perspective on cost and quality measures.”
The APCD plans to regularly provide reports on specific Georgia health care issues, such as the incidence and context of chronic diseases that affect large populations in Georgia. These will include diabetes, hypertension, heart disease, and heart failure. The system will also provide data on cancer, as well as maternal and child health, and the median rate for “surprise billing.”
Beyond reports on broad issues important to providing a big picture of health in Georgia, aggregated data on these five million patients can also be made available to state agencies, policymakers, researchers, health care organizations, and others. Requests for standard and customized data sets and reports will be reviewed by a data release and review committee, based on alignment with the APCD objectives, the qualifications of the requesters, and other factors.
Development of the Georgia APCD benefits from the lessons learned from similar projects established in other states, as well as guidance and input from a broad range of industry and academic stakeholders. “We’re taking the best of what other states have learned and put them together to meet the specific needs of our state,” Duke said. “The legislation creating our APCD was well thought-out and reflects the best ideas from APCDs nationally.”
Writer: John Toon (john.toon@gtri.gatech.edu)
GTRI Communications
Georgia Tech Research Institute
Atlanta, Georgia
The Georgia Tech Research Institute (GTRI) is the nonprofit, applied research division of the Georgia Institute of Technology (Georgia Tech). Founded in 1934 as the Engineering Experiment Station, GTRI has grown to more than 2,900 employees, supporting eight laboratories in over 20 locations around the country and performing more than $800 million of problem-solving research annually for government and industry. GTRI's renowned researchers combine science, engineering, economics, policy, and technical expertise to solve complex problems for the U.S. federal government, state, and industry.
]]>Michelle Gowdy
Michelle.Gowdy@gtri.gatech.edu
404-407-8060
]]>Several Ivan Allen College of Liberal Arts researchers participated in the annual conference, which this year focused on the power of interdisciplinary collaboration.
Lindsey Bullinger, assistant professor in the School of Public Policy; David Edwards, executive director of the Center for Urban Research; and Professor Michael Best of the Sam Nunn School of International Affairs served on the organizing committee.
Among the IAC presenters were:
Edwards, who presented on “Closing Racial Equity Gaps by Improving the Health of Urban Neighborhoods”
Mayra Pineda-Torres, assistant professor in the School of Economics, who spoke about “The Economics of Reproductive Healthcare Access”
Shatakshee Dhongde, associate dean for academic affairs and associate professor in the School of Economics and Ph.D. student Roshani Bulkunde presented on multidimensional economic hardship in the U.S. during the Covid-19 pandemic as part of an interdisciplinary poster session.
Ivan Allen College’s School of Economics and the School of Public Policy have both recently expanded capacity in health economics and policy — investing in new faculty and establishing the Health Economics and Policy Innovation Collaborative to promote interdisciplinary research in the subject.
“Healthcare is an issue that affects everyone, and we’re excited to help lead the way in finding ways to encourage policies that improve access and health outcomes, bring down costs, and advance health equity,” said Aaron Levine, associate dean for research and outreach, who also attended the conference.
For more information on HEPIC, visit the collaborative’s website.
]]>The PTC brings clinical experts together with Georgia Tech scientists and engineers to develop technological solutions to problems in the health and care of children. The Center provides extraordinary opportunities for interdisciplinary collaboration in pediatrics, creating breakthrough discoveries that often can only be found at the intersection of multiple disciplines.
Garcia will work under the leadership of PTC Co-Directors Dr. Stanislav Emelianov (Georgia Tech) and Dr. Wilbur Lam (Children’s) of Georgia Tech’s Wallace H. Coulter Department of Biomedical Engineering at Georgia Tech and Emory University. Dr. Naveen Muthu of Children’s Physician Group will be Garcia’s counterpart in leading Pillar 1.
Since 2021, Garcia has served as an assistant professor in Georgia Tech’s H. Milton Stewart School of Industrial and Systems Engineering. His research group has published numerous journal and conference papers, and book chapters related to data-driven machine learning and optimization in healthcare, including various applications in diagnosis and disease management of concussion, opioids, cardiovascular disease, glaucoma, and maternal health. He has received federal funding as a primary investigator from both the National Institutes for Health and the Agency for Healthcare Research and Quality. He and his research group have received several national and international recognitions for their work.
Garcia also teaches graduate-level courses in machine learning and optimization for healthcare. He received his Ph.D. in industrial and operations engineering at the University of Michigan and was a postdoctoral fellow at the MGH Institute for Technology Assessment.
]]>“Given the year-long life-cycle of the disease, mathematical modeling is a valuable tool for fine-tuning interventions and evaluating resource allocation decisions,” said Pinar Keskinocak, professor in the School of Industrial and Systems Engineering (ISyE) and the director of the Center for Health and Humanitarian Systems.
Read the full story here.
“Potential Impact of a Diagnostic Test for Detecting Prepatent Guinea Worm Infections in Dogs,” Hannah Smalley, Pinar Keskinocak, Julie Swann, Christopher Hanna, and Adam Weiss, The American Journal of Tropical Medicine and Hygiene, 2024, DOI: https://doi.org/10.4269/ajtmh.23-0534
]]>“Georgia has a problem with access to care — the whole country does,” said Meghan Meredith, a fourth-year Ph.D. student in the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) who has spent much of her academic career studying the problem, which is particularly acute in rural, lower-income places.
Many of these places have been designated “maternity care deserts” by the March of Dimes. If a county doesn’t have any obstetric care or providers, it’s considered a desert. Another commonly used measure is whether a pregnant woman lives within 50 miles of critical care obstetrics (CCO).
These measures are often referred to in academic literature and popular media to highlight a lack of healthcare access, and by public policy leaders trying to address the issue. But it’s become evident to Georgia Tech researchers that they just don’t add up.
“These measures don’t capture the complete picture,” said Meredith. “They aren’t an accurate representation of access to care.”
And that’s what concerns Meredith and her faculty advisor, ISyE Assistant Professor Lauren Steimle.
“We’ve been interested in access to maternal care for a long time, and in countless news stories, the maternity care desert measure is reported on,” Meredith said. “We recognized the limitations, so we thought, ‘Let’s write a paper that explains how this measure is not a complete representation of access.’”
They published their work recently in the journal BMC Health Services Research.
To study these measures of access, Meredith and Steimle used the same kind of computer-based mathematical model that helps companies decide where to place a new distribution center, retail outlet, or even electric car charging stations: a facility location model.
“This model helps us determine where to place facilities, so demand is sufficiently covered with the fewest number of facilities,” said Steimle. “There are tons of potential applications for this model, but we’re using it for healthcare.” For this study, they used the model to identify where Georgia would need to expand healthcare facilities to improve access under the commonly used measures.
Here’s some of what the researchers found:
• Of the 1,910,308 reproductive-age women in Georgia, 104,158 (5.5%) live in maternity care deserts, while 150,563 (7.9%) live more than 50 miles from CCO services; 38,202 live in both situations.
• Fifty-six counties in Georgia meet current “maternity care desert” measures, which means eliminating these deserts would require 56 new obstetric hospitals. That would increase the number of obstetric hospitals statewide from 83 to 139 (a 67% increase).
• Strategically expanding 16 hospitals (a 19% increase) would reduce the number of reproductive-age women living in deserts by half.
• 82% of reproductive-age women designated as living in maternity care deserts live within 25 miles from an obstetric hospital.
The researchers conclude that policymakers should be warned: Using the maternity care desert measure alone as a basis for where and how to invest in healthcare resources isn’t a great idea.
“If we really want to improve pregnancy outcomes, our measures of access should promote risk-appropriate and regionalized care systems,” Steimle said.
Turns out, Georgia is already headed in that direction.
To illustrate the problems with the maternity care desert measure, Steimle compared Georgia with a very different state on the opposite side of the U.S.: Nevada.
“A major problem with the maternity care desert measure is its emphasis on county-by-county infrastructure,” she said. “It’s a one-size-fits-all approach that doesn’t tell the whole story about access to care.”
For example, Georgia has 159 counties and more than three times the population of Nevada. Meanwhile, Nevada has twice the square mileage of Georgia — and 16 very large counties.
At 18,147 square miles, Nye County is Nevada’s largest, and it’s been labeled a maternity care desert. There’s also lots of actual desert in Nye, which is larger than nine U.S. states. So, it’s difficult to accurately compare a vast jurisdiction like Nye with, say, central Georgia’s Lamar County. Lamar, also labeled a desert, is a mere 185 square miles in size. It's also surrounded by counties that are veritable oases of care.
“A lot of people in Georgia may be falsely labeled as not having access, at least geographically speaking, when in fact they have services nearby,” noted Steimle. “Meanwhile, in a state like Nevada, some women may be labeled as having access, but might be very far from obstetric hospitals in their county.”
Steimle also point out that measuring access on a county-by-county basis ignores efforts to coordinate care across the whole state. “The maternity care desert model doesn’t hold up. And it doesn't reflect Georgia’s approach to a regionalization system.”
Since 2009, the Georgia Department of Public Health has organized the state into six geographic perinatal regions (the perinatal period covers pregnancy, childbirth, and early postpartum). The idea is to coordinate the delivery of health services to ensure people in all regions have access to risk-appropriate maternal care.
Each of Georgia’s perinatal regions has a “hub” — a major care center serving as an administrative unit to enable the coordination and delivery of maternal care services. For example, The Emory Perinatal Regional Center at Emory University Hospital is the coordinating center for the 39-county metro Atlanta region.
This regionalization strategy also tries to address the problem of hospital closures, a troubling trend that leads to more deserts. In Georgia, 12 hospitals have closed since 2013; 18 rural hospitals are currently at risk of closure. And this new Georgia Tech study indicates that Georgia would somehow need to add 56 new facilities to eliminate the state’s maternity care deserts — at least by the standards used by the March of Dimes.
“Eliminating maternity care deserts in Georgia would mean adding a larger number of obstetrics facilities to make sure every county has an obstetric hospital,” Steimle said. “But this is likely unrealistic with the current economic forces pushing hospitals to close their obstetric units. With that many facilities in Georgia, some facilities would have a very small number of deliveries, which is not economically sustainable.”
In other words, eliminating maternity care deserts in Georgia wouldn’t sufficiently address the larger problems related to access to care. Instead, Steimle and Meredith advocate for approaches that simultaneously consider the different dimensions of an ideal maternal healthcare system, not just access alone.
For this initial study, Steimle and Meredith just focused on spatial access. They haven’t yet addressed the complex issues of racial disparities, insurance access, or other hurdles facing reproductive-age women in Georgia. That may be coming.
“This is a start,” Steimle said. “Our future work entails thinking about how to come at this with the goal of maximizing or improving outcomes for women.”
And as policy leaders across the country begin to address the maternal mortality crisis, Steimle believes her team’s approach using more sophisticated tools can be helpful. So far, they’ve shared their results with the Centers for Disease Control and Prevention, and members of the Georgia, Iowa, and Nevada departments of public health.
“How do we make measurements that point us toward our end goals? Our tools as mathematical modelers can really help us think through the system holistically and think through strategies before trying them in the real world,” Steimle said. “Think of it as a policy sandbox.”
CITATION: Meghan Meredith, Lauren Steimle, and Stephanie Radke. “The implications of using maternity care deserts to measure progress in access to obstetric care: a mixed-integer optimization analysis.” BMC Health Services Research (June 2024)
doi.org/10.1186/s12913-024-11135-4
]]>Limited resources make it difficult to keep up with rising demand, and NCM’s goal to distribute one million pounds of food annually by 2026 seemed out of reach. Thanks to the Georgia Tech team, that goal is now within grasp.
The team’s first innovation was a 24/7 notification system powered by Python technology. This system monitors affordable food listings from the Atlanta Community Food Bank and sends real-time alerts to NCM staff. By acting quickly on these alerts, NCM’s food supply increases by an additional 20,000 pounds every month while saving $1.31 per pound, allowing the organization to feed more people on a tighter budget.
Recognizing that storage is another hurdle, the team analyzed NCM’s warehouse and recommended changes to maximize space. Their solutions increased storage capacity by 70%, paving the way for NCM to handle larger food deliveries without needing additional facilities.
The students didn’t stop there. They introduced SmartChoice, an inventory system designed specifically for food pantries. This system not only tracks inventory but also lets clients select the food they need based on a points system. This added flexibility means NCM can offer a greater variety of food to better meet individual needs.
“It’s amazing to know that we are a part of the reason why these shelves are so full. It’s an amazing feeling to know that this all helps the community we have been working with this entire time and to know that our work helps families have access to the food they need,” said team member Jacqueline Olsen.
“I was so impressed with their ability to relentlessly dig into what the problem is and get to the very bottom of what we’re trying to accomplish,” said Ryan Jones, executive director of Neighborhood Cooperative Ministries. “We accomplished so much more than we set out to in the first place.”
The Georgia Tech team didn’t just solve problems for NCM — they helped change lives, showing how students can make a lasting difference in their communities.
]]>Steimle’s work applies operations research and machine learning to improve medical decision-making and advance population health, with a focus on maternal and child health. Her recent projects explore maternal healthcare access, prevention of severe maternal morbidity from cardiovascular conditions, and strategies to prevent and control poliovirus outbreaks.
Read the full story here.
]]>This semester’s Capstone Design Expo showcased the ingenuity and problem-solving skills of more than 118 student teams across seven disciplines. Among them, 17 teams represented H. Milton Stewart School of Industrial and Systems Engineering (ISyE), presenting a wide range of solutions, from optimizing scheduling for medical clinics, to refining inventory management for a major auto manufacturer, to enhancing sepsis detection through data-driven patient monitoring.
Capstone Design Expo monodisciplinary Industrial Engineering award went to Serving Solutions. The team partnered with North Fulton Community Charities (NFCC), a nonprofit dedicated to preventing hunger and homelessness, to design scalable systems for enhancing the overall customer experience.
“By focusing on operational efficiency and accessibility, we delivered improvements across three key areas,” said Emma MacGregor, a fourth-year ISyE student on the team. “We modernized inventory management by implementing barcode scanners to streamline tracking; we enhanced customer order processes by developing a more accessible interface supported by a digital queueing network and automated ticketing and printing system, and optimized the pantry layout to create more usable space while also reducing travel time through the pantry.”
In addition to MacGregor, the full team consisted of Samhith Aravind, Sachin Bharadwaz, Shaktik Bhattacharyya, Elyse Daniel, Erin Hinnegan, and Zora Ripkova, under the advisement of Xin Chen, James C. Edenfield Chair and ISyE professor.
Professor Chen noted that the team’s success was measured not only in numbers and workflows, but in real benefits for the families NFCC serves.
“Serving Solutions delivered measurable improvements to North Fulton Community Charities (NFCC)’s pantry operations and the families it serves, such as optimization-driven reshelving that expanded usable shelf space by 16.4%," said Chen. “Watching students transform classroom concepts (optimization, stochastic modeling, and applied data science) into practical systems that volunteers can easily run was truly inspiring.
He added that the benefits extend directly to the community, and how partnerships like these strengthen both student learning and nonprofit operations.
“Collaborations with food pantries like NFCC showcase the immense value of ISyE partnerships. When our students engage with mission-driven organizations, they don’t just apply theory; they create solutions that significantly enhance community impact. I look forward to more opportunities where these collaborations continue to drive lasting improvements that strengthen communities.”
To learn more about the expo, read the full capstone story here.
Tens of millions of brackets have been filled out ahead of the NCAA men’s and women’s basketball tournaments. Some fans will choose winners based on the higher seed, others will try to predict shocking upsets, and some may choose who advances based on which mascot would win a fight, but a Georgia Tech professor has his bracket down to a (data) science.
Since 2004, Joel Sokol, director of the Master of Science in Analytics program and the Harold E. Smalley Professor in the H. Milton Stewart School of Industrial and Systems Engineering, has used a pair of analytic methods — logistic regression and Markov chains (LRMC) — to determine the best teams in college basketball. This year, Sokol’s LRMC rankings project the Michigan Wolverines to cut down the nets at the end of the men’s tournament and the Connecticut Huskies as the last team standing in the women’s field.
The algorithm compares all 350-plus Division I basketball teams against each other simultaneously during the regular season and calculates probabilities based on simple data points — who won each game, by how much, and where it was played. When the madness of March begins, Sokol’s bracket forgoes the seeds assigned to teams and fills out his bracket based on the LRMC rankings.
Models used by the tournament selection committee — NET, KPI, KenPom — measure advanced metrics like strength of schedule, possession-by-possession efficiency, opponent quality, and more, but Sokol, with expertise in sports analytics and data science, says the LRMC shows the value of simple data and a large sample size.
“The LRMC can hold its own against those models that are based on much more advanced metrics than just scoreboard data. They may look at all kinds of information, from efficiencies down to individual player performance, but the message really is that if you have a good set of simple data, that’s enough if you know how to interpret it.”
Sokol compares his algorithm to nearly 100 other ranking systems and says the LRMC is often among the top performers, with the higher-ranked teams (in the LRMC rankings) winning approximately 75% of the time — a statistic that holds true in the NCAA Tournament. Sokol says that 25% of tournament games result in an upset.
For 2026, Sokol’s projections predict that all eight No. 1 seeds — four in both the men’s and women’s tournaments — will reach the Final Four, but it’s not always a guarantee that the highest seeds make it out of their respective regions. The inaugural LRMC rankings accurately predicted the No. 3-seeded Yellow Jackets’ Final Four run in 2004 — one of the only predictive models to do so.
Sokol got the idea to compile the LRMC rankings one year before Tech’s run to the national championship game, when the Yellow Jackets were left out of the NCAA Tournament as a bubble team, largely because of a December buzzer-beater loss to Tennessee. Since the first set of rankings, machine learning and artificial intelligence have become more accessible, yet Sokol says ChatGPT and other large language models (LLMs) aren’t quite ready to handle the level of analysis required to shape the rankings.
“These LLMs are good at sounding good, but they're not so good at doing these complex quantitative tasks,” he said.
Ultimately, though, luck is often a stubbornly unquantifiable factor when filling out a bracket, no matter the formula used to make selections, and the odds of filling out a perfect bracket are all but a statistical impossibility.