About

Osman Ozaltin is a Professor of Personalized Medicine in the Edward P. Fitts Department of Industrial and Systems Engineering at NC State University. He joined the university in August 2013 as part of the Chancellor’s Faculty Excellence Program in Personalized Medicine. His research interests encompass theoretical, computational, and applied aspects of mathematical programming, with a focus on multilevel stochastic optimization problems related to public health policy-making, personalized medical decision-making, and healthcare delivery. Ozaltin is also interested in developing efficient algorithms for large-scale combinatorial problems in bioinformatics, utilizing methods such as integer programming, combinatorial optimization, stochastic programming, bilevel programming, quadratic programming, and decomposition algorithms. Prior to his current role, he was an Assistant Professor of Management Sciences at the University of Waterloo in Canada. His work has been published in top academic journals, including Operations Research and Mathematical Programming. Ozaltin received the Distinguished Institute of Industrial Engineers Best Dissertation Award in 2013 for his research on optimizing the annual influenza vaccine design. His educational background includes a BS in Industrial Engineering from Bogazici University in Istanbul, Turkey, and MS and Ph.D. degrees in Industrial Engineering from the University of Pittsburgh.

Selected publications

• IP61-07 A DYNAMIC APPOINTMENT SCHEDULING ALGORITHM TO PRIORITIZE HIGH-RISK RENAL COLIC PATIENTS FOR EARLY FOLLOW-UP

  The Journal of Urology · 2026-04-27

  article
  PublisherDOI

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

  Operations Research · 2026-02-12

  articleSenior author

  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

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

  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

• Improving deceased donor kidney utilization: predicting risk of nonuse with interpretable models

  Frontiers in Artificial Intelligence · 2025-08-13 · 1 citations

  articleOpen accessCorresponding

  Background: Many deceased donor kidneys go unused despite growing demand for transplantation. Early identification of organs at high risk of nonuse can facilitate effective allocation interventions, ensuring these organs are offered to patients who could potentially benefit from them. While several machine learning models have been developed to predict nonuse risk, the complexity of these models compromises their practical implementation. Methods: We propose simplified, implementable nonuse risk prediction models that combine the Kidney Donor Risk Index (KDRI) with a small set of variables selected through machine learning or transplantation expert input. Our approach also account for Organ Procurement Organization (OPO) level factors affecting kidney disposition. Results: The proposed models demonstrate competitive performance compared to more complex models that involve a large number of variables while maintaining interpretability and ease of use. Conclusion: Our models provide accurate, interpretable risk predictions and highlight key drivers of kidney nonuse, including variation across OPOs. These findings can inform the design of effective organ allocation interventions, increasing the likelihood of transplantation for hard-to-place kidneys.

  PublisherOA PDFDOI

• Risk-Averse Placement Optimization in Refugee Resettlement

  SSRN Electronic Journal · 2025-01-01

  preprintOpen access
  PublisherDOI

• Temporal pattern mining for knowledge discovery in the early prediction of septic shock

  Pattern Recognition · 2024-03-18 · 4 citations

  articleSenior authorCorresponding
  PublisherDOI

• Evaluating the Safety and Quality of Intraoperative Anesthesia Handoffs from the Perspective of Anesthesia Providers

  Proceedings of the Human Factors and Ergonomics Society Annual Meeting · 2024-09-01

  article

  Handoffs, that is, care transitions, convey information, responsibility, and authority between care providers. Intraoperative handoffs, which occur during surgery either due to shift changes or breaks, are high-risk, error-prone and linked with inadequate verbal communication and documentation. We explored perspectives about safety and quality of intraoperative handoffs between anesthesia providers at an academic medical center. Through an anonymous online survey, we asked participants to share their opinions on current handoff practices including teamwork, staffing and work pace, and handoffs and information exchange. The results showed positive perceptions about teamwork, while only half of the participants were positive about staffing and work pace. We also found that opinions of participants about staffing and work pace vary based on their role. Our study emphasizes the importance of considering diverse perspectives and employing a systems-based approach to address challenges and implement effective interventions for safe, high-quality handoffs in intraoperative care.

  PublisherDOI

• Risk score models for urinary tract infection hospitalization

  PLoS ONE · 2024-06-14 · 2 citations

  articleOpen accessSenior authorCorresponding

  Annually, urinary tract infections (UTIs) affect over a hundred million people worldwide. Early detection of high-risk individuals can help prevent hospitalization for UTIs, which imposes significant economic and social burden on patients and caregivers. We present two methods to generate risk score models for UTI hospitalization. We utilize a sample of patients from the insurance claims data provided by the Centers for Medicare and Medicaid Services to develop and validate the proposed methods. Our dataset encompasses a wide range of features, such as demographics, medical history, and healthcare utilization of the patients along with provider quality metrics and community-based metrics. The proposed methods scale and round the coefficients of an underlying logistic regression model to create scoring tables. We present computational experiments to evaluate the prediction performance of both models. We also discuss different features of these models with respect to their impact on interpretability. Our findings emphasize the effectiveness of risk score models as practical tools for identifying high-risk patients and provide a quantitative assessment of the significance of various risk factors in UTI hospitalizations such as admission to ICU in the last 3 months, cognitive disorders and low inpatient, outpatient and carrier costs in the last 6 months.

  PublisherOA PDFDOI

• Incorporating Face Mask Usage in Agent-Based Models Using Personal Beliefs and Perceptions: An Application of the Health Belief Model

  2024-12-15 · 1 citations

  article

  The modelling of human behavior is a critical component of any simulation tool that aims to represent the spread of an infectious disease throughout a population. However, few modeling approaches attempt to incorporate protective behaviors using models grounded in theories from the behavioral sciences. Here, we demonstrate how to incorporate human behavior accounting for personal beliefs and perceptions by using a commonly known behavioral framework. We implemented the proposed model within an agent-based simulation to drive the agent's decision related to wearing a face mask. We used survey data to characterize a synthetic population, and investigate the effect of policies that aim to modify beliefs with the goal of promoting face mask usage. Our results highlight the importance of incorporating the individual drivers of behavior to better represent adoption of protective actions against health threats, enhancing the ability of simulation tools to quantify the impact of policy interventions.

  PublisherDOI

Awards & honors

• Distinguished Institute of Industrial Engineers Best Dissert…