Camila Ramos

Bio: Camila Ramos is an academic researcher from Pontifical Catholic University of Chile. The author has an hindex of 2, co-authored 2 publications receiving 7 citations.

Appointment and patient scheduling in chemotherapy: a case study in Chilean hospitals

Abstract: This research addresses a scheduling problem for chemotherapy patients, which is divided in two subproblems: patient scheduling on an infinite horizon and daily patient scheduling. We consider the requirement for available laboratory hours to prepare the medicine for every patient as an additional complexity. A methodology was formulated that addresses the problem in two stages. The first one is based on previous research and implements a scheduling policy for chemotherapy. The result of this first stage is the input for the second stage, which is addressed by generating treatment patterns. The benefits of both stages of the proposed methodology are evaluated for two real cases, one of them in the Chemotherapy Division of Hospital Salvador, and the other in the Cancer Center, of the Clinical Hospital of the Pontificia Universidad Catolica de Chile, both in Santiago, Chile. Regarding the costs’ impact, the method proposed manages to reduce 20% and 17% the operational costs in these cases, due to less extra treatment hours needed. On the other hand, the proposed daily scheduling method for patients presents an improvement of 21% and 9% in care slots usage and 22% and 17% in laboratory slots usage for an average demand day, which translates in a reduction of both extra hours used and workday duration, for the case of the Chemotherapy Division and Cancer Center, respectively.

Un análisis cualitativo de los discursos de representantes de sindicatos, movimientos sociales y organizaciones no gubernamentales, sobre el rol de las empresas y el Estado chileno

Abstract: El presente articulo da cuenta de los principales argumentos de la vision que poseen representantes de la sociedad civil sobre el accionar de las empresas y el Estado chileno. Por medio de una metodologia cualitativa, se realizaron 24 entrevistas semi-estructuradas a representantes de tres tipos de organizaciones pertenecientes a la sociedad civil: sindicatos, organizaciones sin fines de lucro y movimientos sociales. Los temas a indagar fueron el accionar de las empresas chilenas y su vinculacion con la sociedad y comunidad en las cuales operan, asi como el como el rol que posee el Estado en asegurar derechos e implementar politicas publicas y programas sociales. Los resultados preliminares de nuestra investigacion nos muestran un descontento con el funcionamiento de la institucionalidad economica y politica chilena. Los argumentos de nuestros entrevistados critican el rol que juegan las empresas chilenas en el desarrollo de su responsabilidad social y el disminuido rol que posee el Estado para regular el actuar de las empresas y garantizar la proteccion de derechos universales.

Artificial intelligence in healthcare operations to enhance treatment outcomes: a framework to predict lung cancer prognosis

Abstract: Artificial Intelligence (AI) is critical for data-driven decision making to increase resource utilization, operational performance, and service quality in various industry domains, particularly in healthcare. Using AI in healthcare operations can significantly improve treatment outcomes and enhance patient satisfaction while reducing costs. In this paper, we propose a multi-stage framework to build an AI-based decision support tool that can predict the 5-year survivability of lung cancer patients. We evaluate the proposed framework using the Surveillance, Epidemiology, and End Results dataset pertaining to the 1973–2015 period obtained from the National Institutes of Health. The first stage entails data preprocessing and target creation. The second stage applies six AI algorithms with feature selection through Particle Swarm Optimization and hyperparameter tuning with Cross-Validation. These Algorithms include Logistic Regression, Decision Trees, Random Forests (RF), Adaptive Boosting (AdaBoost), Artificial Neural Network, and Naive Bayes. The results show that RF and AdaBoost models yield an AUC rate of 0.94 and outperform the other models. Stage 3 utilizes permutation importance to interpret the RF and AdaBoost models and applies Tree-based Augmented Naive Bayes to gain insights regarding the interrelations among important features. The results of Stage 3 delineate that the number of lymph nodes containing metastases), the number of tumors that patients have had in their lifetime, the patient’s age, and the microscopic composition of cells rank among the topmost important features and can significantly impact patient survivability. We think this study has significant practical implications in helping physicians predict prognosis and develop treatment plans for lung cancer patients.

Improving patient-care services at an oncology clinic using a flexible and adaptive scheduling procedure

Abstract: This paper studies an online scheduling problem dealing with patients’ multiple requests for chemotherapy treatments at the cancer centre of a major metropolitan hospital in Canada. The proposed solution to the problem is an adaptive and flexible procedure that systematically combines two optimization models. The first model is intended to dynamically schedule incoming appointment requests, which arrive in the form of waiting lists, and the second model is used to reschedule already booked appointments with the goal of better allocating resources as new information becomes available. The performance and potential impact of the proposed procedure is assessed using historical data provided by the cancer centre. Moreover, a sensitivity analysis is carried out to draw insights that may help hospital managers to deal more efficiently with both incoming requests and unexpected events.

Appointment Scheduling Problem in Complexity Systems of the Healthcare Services: A Comprehensive Review

Abstract: This paper provides a comprehensive review of Appointment Scheduling (AS) in healthcare service while we propose appointment scheduling problems and various applications and solution approaches in healthcare systems. For this purpose, more than 150 scientific papers are critically reviewed. The literature and the articles are categorized based on several problem specifications, i.e., the flow of patients, patient preferences, and random arrival time and service. Several methods have been proposed to shorten the patient waiting time resulting in the shortest idle times in healthcare centers. Among existing modeling such as simulation models, mathematical optimization techniques, Markov chain, and artificial intelligence are the most practical approaches to optimizing or improving patient satisfaction in healthcare centers. In this study, various criteria are selected for structuring the recent literature dealing with outpatient scheduling problems at the strategic, tactical, or operational levels. Based on the review papers, some new overviews, problem settings, and hybrid modeling approaches are highlighted.

A finite-horizon Markov decision process model for cancer chemotherapy treatment planning: an application to sequential treatment decision making in clinical trials

Abstract: Cancer is one of the major diseases that seriously threaten the human life. Increasing interest in cancer treatment strategies for chemotherapy treatment planning and optimal drug administration has created new applications for mathematical modeling. In this paper, we develop a finite-horizon Markov decision process (MDP) model for cancer chemotherapy treatment planning that could advise selection of the optimal policy for the chemotherapy regimen according to the patient’s condition. The proposed model uses a finite action space of optimal cancer chemotherapy regimens for gastric and gastroesophageal cancers resulted from the proposed optimization model and a finite state space of patients’ toxicity levels. Results show that the proposed approach yields the optimal sequence of gastric and gastroesophageal cancer chemotherapy treatment regimens for a period of chemotherapy treatment which makes possible designing clinical trials for sequential treatments.

Efficient referee assignment in Argentinean professional basketball leagues using operations research methods

Abstract: The top two divisions of the Argentinean professional basketball system have since 2014–2015 used a season schedule format similar to that used by the NBA in which games are played all through the week, replacing the previous setup where all games were scheduled on weekends. This change has confronted the Argentinean league organizers with new scheduling challenges, one of which is the assignment of referees to games. The present article addresses this assignment problem using a tool based on an integer linear programming model. The objective is to minimize the total cost of trips made by the referees while also satisfying a series of other conditions. The problem is broken down into a series of relatively small subproblems representing successive periods of the season, and the solution is obtained using a rolling horizon heuristic. The approach was tested by applying it to the First Division’s 2015–2016 season, the last one before introducing the approach presented in this article, when referees were still assigned using manual methods. The travel costs simulated by the model were 26% lower than the total travel costs actually incurred under the manual assignments, and all of the restrictions that had been requested by league officials were satisfied. The model was used by the First Division for the 2016–2017 and 2017–2018 seasons and in 2017–2018 also by the Second Division.