Abstract
Biomarker testing, where a biochemical marker is used to predict the presence or absence of a disease in a subject, is an essential tool in public health screening. For many diseases, related biomarkers may have a wide range of concentration among subjects, particularly among the disease positive subjects. Furthermore, biomarker levels may fluctuate based on external or subject-specific factors. These sources of variability can increase the likelihood of subject misclassification based on a biomarker test. We study the minimization of the subject misclassification cost for public health screening of non-infectious diseases, considering regret and expectation-based objectives, and derive various key structural properties of optimal screening policies. Our case study of newborn screening for cystic fibrosis, based on real data from North Carolina, indicates that substantial reductions in classification errors can be achieved through the use of the proposed optimization-based models over current practices.
Acknowledgments
We are grateful to Professor Ziya, the AE, and three anonymous Reviewers for excellent suggestions that greatly improved the analysis and presentation of the paper. We are thankful to Dr. Scott J. Zimmerman, Director of the North Carolina State Laboratory of Public Health, for offering us valuable insights into public health screening practices for cystic fibrosis. We are also grateful to Dr. Sara Beckloff, Manager of the North Carolina State Laboratory of Public Health’s newborn screening, for helping us with the data collection process.
Notes
1 SD denotes the standard deviation around the mean
Additional information
Funding
Notes on contributors
Saloumeh Sadeghzadeh
Saloumeh Sadeghzadeh is a Ph.D. candidate in the Department of Industrial and Systems Engineering at Virginia Tech, and she will be joining the faculty of School of Management at Binghamton University in the summer of 2019. Her research interests lie in applying stochastic modeling, optimization, and data analytics methodologies to problems arising in health care and public policy domains.
Ebru K. Bish
Ebru K. Bish is an associate professor of Industrial and Systems Engineering and an associate professor of Health Sciences at Virginia Tech. Dr. Bish’s research interests lie in stochastic modeling, optimization, and decision-making under uncertainty, with applications to public health policy and health implementation science. Her specific research focuses on public health screening and surveillance of infectious diseases and genetic disorders; and on improving the safety of health care delivery. She is the recipient of the INFORMS Pierskalla Award for the Best Paper in Healthcare (first prize winner, runner-up, and a finalist), INFORMS JFIG Best Paper Award, and IIE Transactions Best Applications Paper Award. She is currently serving as the President of the INFORMS Health Applications Society.
Douglas R. Bish
Douglas R. Bish is an associate professor in the Department of Industrial and Systems Engineering and an associate professor of Health Sciences at Virginia Tech, with a secondary appointment at the Virginia Tech-Carilion School of Medicine. His research interests are on the application of operations research and related methodologies to solve problems in health care, emergency management, and logistics. He is the recipient of the National Science Foundation CAREER award. He is also the recipient of the INFORMS Pierskalla Award for the Best Paper in Healthcare (first prize winner, runner-up, and a finalist) and IIE Transactions Best Applications Paper Award.