- Methodology: Mathematical Modeling, Game Theory, Data Mining, MCDM
- Application: Healthcare Operations, Supply Chain Management, Health Economics
- “Economics of introducing a mobile clinic as an added or exclusive modality for dialysis service” with N. Murthy, and E. Cil, In final preparation for submission to Production and Operations Management.
- “A decision support system for multi-objective automatic clustering: a framework development”, with S. Sheikh, and A. Oztekin, Under review.
- “Parking Lot Site Selection Using A Fuzzy AHP-TOPSIS Framework in Tuyserkan, Iran” with S. kazazi, A. Akbari, and H. Assefi, Journal of Urban Planning and Development, Vol: 144, No:3, 2018.
- “M-machine, No-wait Flow-shop Scheduling With Sequence Dependent Setup Times And Truncated Learning Function to Minimize The Makespan”, with V. Azizi, and A. S. Kheirkhah, International Journal of Industrial Engineering Computation, Vol:7, No:2, 2016.
- “Lot-streaming in No-wait M-machine Multi-product Flow-shop, Considering Sequence Dependent Setup Times And Position Based Learning Factors” with V . Azizi, International Journal of Engineering, Vol:28, No:7, 2015.
15% of U.S. adults, about 37 million people, are estimated to have chronic kidney disease (CKD). End-stage renal disease (ESRD) is the last stage of CKD in which kidneys lose their entire function of removing waste products from the blood. Renal transplantation and dialysis are the only treatment options for ESRD patients. At around $100 Billion, payments for CKD and ESRD accounts for more than 10% of Medicare’s budget. Motivated by Medicare’s new reimbursement strategy, in my research, coauthored by Prof. Murthy and Dr. Eren Cil, I examine the possibility of introducing a new and non-traditional dialysis service modality to the current dialysis network in the U.S. that can reduce hospitalization costs undertaken by Medicare. We develop a framework to consider the strategic interaction between Medicare and a dialysis service provider and examine the potential benefit to Medicare with a new payment policy.
About 48% of people with severely reduced kidney function are not aware of even having CKD. Early and accurate identification of ESRD patients is essential as it can delay the need for dialysis. Clustering, as an unsupervised machine learning technique, has various valuable applications in healthcare, from predicting and diagnosing chronic disease based on patients’ medical history to analyzing medical images. Determining an efficient algorithm that can accurately estimate the clusters based on the nature of the data set is critical. Despite the numerous improvements in automatic clustering, there is a lack of generalizability among the developed performance metrics for automatic clustering algorithms. In most cases, each performance metric considers a limited number of objectives and ignores other clustering validation aspects. In my research, coauthored by Dr.Oztekin and Dr.Sheikh, I design an integrated-collaborative decision support system (DSS) for multi-objective automatic clustering. After developing a mixed-integer non- linear programming model, we propose a six-step DSS framework to solve the problem. The developed framework can improve the accuracy of chronic disease detection in surveillance systems.