About

Maria Mayorga is the director and Goodnight Distinguished Chair in Operations Research at North Carolina State University, where she is a professor in the Edward P. Fitts Department of Industrial and Systems Engineering, part of the Healthcare Systems Engineering group. She joined NC State in August 2013 as part of the Chancellor’s Faculty Excellence Program cluster hire in personalized medicine. Her research focuses on addressing fundamental barriers in evaluating the effectiveness of health interventions and policies by explicitly considering individual patient preferences within heterogeneous patient populations. She is particularly interested in optimally allocating resources in emergency medical service systems and creating analytical models of health systems that incorporate patient-level data. Mayorga employs techniques such as simulation, dynamic programming, applied probability, queuing theory, and mathematical programming, utilizing multiple sources of secondary data and a mixed methods approach to predict health outcomes in complex settings. Her interdisciplinary research involves collaborations with health services researchers, epidemiologists, economists, and medical doctors. Prior to her current role, she was a faculty member at Clemson University in the Department of Industrial Engineering for seven years. She has authored over 90 publications and her research has been supported by NIH and NSF. She received the NSF CAREER Award for her work on incorporating patient choice into predictive models of health outcomes. Her research interests include predictive models in healthcare, healthcare operations management, emergency response, and humanitarian logistics, with the goal of informing policy decisions and reducing health disparities through the application of operations research, mathematical models, statistics, simulation, machine learning, and artificial intelligence.

Research topics

• Computer Science
• Medicine
• Economics
• Engineering
• Machine Learning
• Psychiatry
• Business
• Management science
• Data science
• Mathematics
• Environmental health
• Operations research
• Mathematical optimization
• Econometrics
• Psychology
• World Wide Web
• Internal medicine
• Geography
• Intensive care medicine
• Virology
• Operations management

Selected publications

• Reducing Manual Labeling Effort in Imbalanced Data Sets: Active Learning for Detecting Illicit Massage Business Reviews

  Operations Research · 2026-02-12

  article

  Smarter Labeling to Detect Hidden Human Trafficking Risks Human trafficking investigators face the immense challenge of sifting through vast amounts of online data to uncover illicit activities. In their article, Reducing Manual Labeling Effort in Imbalanced Data Sets: Active Learning for Detecting Illicit Massage Business Reviews, Tobey, Mayorga, Bosisto, and Özaltın present a novel framework that uses reinforcement learning–based active learning to reduce the burden of manual data labeling, improving detection of illicit massage business reviews on Yelp. By strategically selecting the most informative reviews for expert annotation, the approach achieves strong performance despite limited and imbalanced data sets, easing the emotional and time costs of reviewing disturbing content. The study demonstrates that their method outperforms benchmark active learning strategies, remains effective even with large query batches, and generalizes across regions. Beyond combating human trafficking, the framework offers a scalable solution for other domains with scarce, sensitive, or costly-to-label data.

  PublisherDOI

• Advancing Simulation in Healthcare and Life Sciences: A Panel Discussion of Future Research Directions

  2025-12-07

  article
  PublisherDOI

• Estimating the long-term health impact and program cost-effectiveness of providing direct screening services to low-income, medically underserved patients through the Colorectal Cancer Control Program (CRCCP)

  Cancer Causes & Control · 2025-05-29

  articleOpen access

  PURPOSE: The Colorectal Cancer Control Program (CRCCP) aimed to increase colorectal cancer (CRC) screening among U.S. medically underserved populations through promotion and provision of CRC screening. We used simulation modeling to estimate the lifelong health impact and program cost-effectiveness of direct screening services, typically a single cycle of routine screening/follow-up testing provided through the CRCCP ("intervention"). METHODS: Data for this study were from CDC's Colorectal Clinical Data Elements (CCDE), which captured screening and follow-up services received from CRCCP between 2009 and 2020. We used microsimulation to model the evolution of polyps and CRC for average-risk individuals in intervention and "counterfactual" (control) groups, under multiple scenarios. We calculated and compared lifetime CRC outcomes (cases, deaths, life-years) for individuals with and without the CRCCP intervention. Clinical and implementation costs incurred by the CRCCP were used to estimate programmatic/intervention costs. Results are reported overall and by initial screening modality received (colonoscopy or stool testing) and assumed lower vs. higher "background" (non-intervention) screening scenarios. RESULTS: With conservative assumptions, our findings suggest that CRCCP-provided screening averted 806 CRC cases, avoided 392 CRC deaths, and added 5,368 life-years per 100,000 individuals vs. no intervention. Cost-effectiveness analysis revealed that the program's cost per life-year gained varied by screening modality and scenario assumptions-ranging from $25,740 to $27,583 for colonoscopy screening and $70,410 to $75,979 for stool testing. CONCLUSION: CRCCP-provided screening/testing services were found to produce substantial potential health gains. Our analysis estimates the cost-effectiveness of providing one cycle of screening/testing to medically underserved individuals to inform programmatic decisions.

  PublisherOA PDFDOI

• Organizational decision‐making during COVID‐19: A qualitative analysis of the organizational decision‐making system in the United States during COVID‐19

  UNC Libraries · 2025-05-06

  articleOpen access

  This study sought to understand COVID‐19‐related organizational decisions were made across sectors. To gain this understanding, we conducted semi‐structured interviews with organizational decision‐makers in North Carolina about their experiences responding to COVID‐19. Conventional content analysis was used to analyse the context, inputs, and processes involved in decision‐making. Between October 2020 and February 2021, we interviewed 44 decision‐makers from the following sectors: business ( n = 4), community non‐profit ( n = 3), county government ( n = 4), healthcare ( n = 5), local public health ( n = 5), public safety ( n = 7), religious ( n = 6), education ( n = 7) and transportation ( n = 3). We found that during the pandemic, organizations looked to scientific authorities, the decisions of peer organizations, data about COVID‐19, and their own experience with prior crises. Interpretation of inputs was informed by current political events, societal trends, and organization mission. Decision‐makers had to account for divergent internal opinions and community behaviour. To navigate inputs and contextual factors, organizations decentralized decision‐making authority, formed auxiliary decision‐making bodies, learned to resolve internal conflicts, learned in real time from their crisis response, and routinely communicated decisions with their communities. In conclusion, aligned with systems and contingency theories of decision‐making, decision‐making during COVID‐19 depended on an organization's ‘fit’ within the specifics of their existing system and their ability to orient the dynamics of that system to their own goals.

  PublisherDOI

• The potential impact of the Affordable Care Act and Medicaid expansion on reducing colorectal cancer screening disparities in African American males

  UNC Libraries · 2025-02-06

  articleOpen accessSenior author

  Few investigations have explored the potential impact of the Affordable Care Act on health disparity outcomes in states that chose to forgo Medicaid expansion. Filling this evidence gap is pressing as Congress grapples with controversial healthcare legislation that could phase out Medicaid expansion. Colorectal cancer (CRC) is a commonly diagnosed, preventable cancer in the US that disproportionately burdens African American men and has substantial potential to be impacted by improved healthcare insurance coverage. Our objective was to estimate the impact of the Affordable Care Act (increasing insurance through health exchanges alone or with Medicaid expansion) on colorectal cancer outcomes and economic costs among African American and White males in North Carolina (NC), a state that did not expand Medicaid. We used an individual-based simulation model to estimate the impact of ACA (increasing insurance through health exchanges alone or with Medicaid expansion) on three CRC outcomes (screening, stage-specific incidence, and deaths) and economic costs among African American and White males in NC who were age-eligible for screening (between ages 50 and 75) during the study period, years of 2013-2023. Health exchanges and Medicaid expansion improved simulated CRC outcomes overall, though the impact was more substantial among AAs. Relative to health exchanges alone, Medicaid expansion would prevent between 7.1 to 25.5 CRC cases and 4.1 to 16.4 per 100,000 CRC cases among AA and White males, respectively. Our findings suggest policies that expanding affordable, quality healthcare coverage could have a demonstrable, cost-saving impact while reducing cancer disparities.

  PublisherDOI

• Optimizing Masks and Random Screening Test Usage within K-12 Schools

  MDM Policy & Practice · 2025-01-01

  articleOpen accessCorresponding

  Background. COVID-19 tremendously disrupted the global health system. People of all ages were at risk of becoming infected. Frequent school closures raised concerns about both the physical and mental health of school-age children. Many studies discussed the effectiveness of various interventions, while few focused on optimizing such interventions. Methods. This study aimed to optimize the usage of random screening tests and masking requirements within K-12 schools. We simulated the disease transmission within a school setting and sought to find the most efficient schedules for schools to arrange their weekly screening tests and mask mandates. The goal was to minimize the number of the end-of-semester infections as well as to use the minimum number of resources. We applied the nondominated sorting genetic algorithm, NSGA-II, to solve this multiobjective optimization problem. We also compared results when polymerase chain reaction (PCR) versus rapid antigen tests were used. Results. The NSGA successfully found Pareto solutions when optimizing the end-of-semester infections, the total number of tests, and the total number of weeks masking. The screening tests and masks can serve as alternatives to one another when prioritizing minimizing the number of infections. In addition, due to the faster return of testing results and lower accuracy, the rapid antigen tests had a similar effect as PCR tests. Conclusion. Our study provides policy makers in K-12 schools with valuable insights. The conclusions derived from this research can serve as a solid foundation for making informative decisions regarding random screening tests and universal masking policies. Highlights Our simulation optimization framework was used to design weekly schedules for random screening tests and masking within K-12 schools to mitigate COVID-19 infections. We considered multiple objectives and applied the NSGA-II algorithm to find a Pareto solution set. Based on local context and preferences, decision makers can trade off testing and masking to achieve a similar number of end-of-semester infections. When a few weeks of masks are mandated, it is best to use them at the beginning of a semester.

  PublisherDOI

• Modeling Social Influence on Covid-19 Vaccination Uptake Within an Agent-Based Model

  2025-12-07

  articleSenior author
  PublisherDOI

• Predicting patient enrollment in a telephone-based principal care management service using topic modeling

  PLOS Digital Health · 2025-09-18

  articleOpen accessSenior authorCorresponding

  Diabetic Retinopathy (DR) is a complication related to diabetes that can lead to vision impairment. To assist DR patients, a care management company provides a telephone-based principal care management (PCM) service, which includes care coaching and other services to reduce barriers to care for patients with DR. Despite its benefits, enrollment in the program is suboptimal. This study developed predictive models using call transcripts to investigate factors associated with patient enrollment in the PCM service. We analyzed transcripts of calls made during the enrollment process (prior to enrollment) and feature-engineered the call metadata (i.e., transcript length, number of calls, time between calls, customer and agent sentiment). In addition, we extracted topics discussed in the transcripts using Structural Topic Modeling (STM) and converted them into vector representations. Utilizing call metadata alongside topics, we developed three classification models (call metadata, topic-based, and topic+metadata) to predict patient enrollment, with the latter demonstrating superior performance. The topic+metadata classification model outperformed the other two models in distinguishing between patient enrollment and non-enrollment, with AUC values ranging from 0.81 to 0.99 across models using 3 to 15-topics. The findings suggest that proactively offering to schedule an appointment after the program benefits explanation leads to a higher odds of enrollment. When the scheduling portion of the conversation is not considered, agents should cover all parts of the script over multiple calls. Additionally, agents who explain the program and maintain longer intervals between calls have higher odds of patient enrollment, suggesting that there is value in allowing patients adequate time to reflect between calls. These findings offer valuable insights for agents to evaluate their strategies in patient enrollment. As the first point of contact, enrollment agents play a crucial role in determining whether patients can benefit from care coordination and management programs.

  PublisherDOI

• Decision Tree Framework for Selecting Evidence-Based Colorectal Cancer Screening Interventions Using Metamodels

  2025-12-07

  article
  PublisherDOI

• Detecting Illicit Massage Businesses by Leveraging Graph Machine Learning

  2025-09-01

  article

  Thousands of Illicit Massage Businesses (IMBs) are estimated to be operating in the United States by disguising themselves as legitimate establishments while exploiting trafficked workers, harming both the victims and the massage industry. The increasing digital presence of these illicit businesses presents an opportunity for detection, a crucial task for law enforcement and social service agencies aiming to disrupt their operations. Our research leverages user-generated business reviews from Yelp.com, enriched with data from multiple sources, including RubMaps.ch, U.S. Census records, GIS data, and licensing information. We present a feasibility study of developing a graph convolutional network (GCN) for a novel application and exploring its benefits and drawbacks in identifying IMBs. The novelty of our approach lies in its ability to link and analyze businesses, reviews, and reviewers within a heterogeneous network and employ a relational GCN to capture their complex relationships.

  PublisherDOI

Recent grants

• NIH Grant R01MD004251

  NIH · $733k · 2013

• CAREER: Incorporating Patient Heterogeneity and Choice into Predictive Models of Health and Economic Outcomes

  NSF · $155k · 2013–2017

Frequent coauthors

• Stephanie B. Wheeler

  University of North Carolina at Chapel Hill

  38 shared

• Kristen Hassmiller Lich

  37 shared

• Julie S. Ivy

  North Carolina State University

  36 shared

• Julie Swann

  North Carolina State University

  31 shared

• Hector Toro‐Díaz

  28 shared

• Eric S. Orman

  Michael E. DeBakey VA Medical Center

  27 shared

• A. Sidney Barritt

  University of North Carolina at Chapel Hill

  22 shared

• Laura A. Albert

  Hospital Arnau de Vilanova

  20 shared

Awards & honors

• National Science Foundation CAREER Award