Health Care Management Science最新文献

{"title":"Modeling framework and reference model for data-driven simulation of patient flows in emergency departments.","authors":"Michael Schlecht, Virginie Goepp, Roland De Guio, Jürgen Köbler","doi":"10.1007/s10729-026-09792-4","DOIUrl":"https://doi.org/10.1007/s10729-026-09792-4","url":null,"abstract":"<p><p>Discrete event simulation (DES) of patient flows is essential for the design of emergency departments (EDs), because it enables exploration of scenarios without disrupting real systems. Although DES is beneficial, it is limited by high modeling requirements. In simulations, each scenario to be analyzed must be individually modeled, which consumes significant time and resources. Moreover, models can rapidly become obsolete. This can be caused by changes in patient population, such as an increase in the number of cases during flu season and other seasonal variations. This study explored how to efficiently support simulation modeling from conceptual modeling until specific programmed models to overcome these challenges, thereby enabling consideration of real patient populations in ED simulations. A modeling framework for healthcare simulation and reference model were developed for managing patient population data, generating simulation data using Monte Carlo simulation, and conducting simulation experiments using data-driven simulation techniques. The framework supports conceptual modeling using a detailed set of steps and modeling views, thereby allowing to separate modeling concerns throughout the process. It also integrates an instantiation mechanism to build specific programmed models based on a reference model. A real-life study of an ED demonstrated the developed approach based on two illustrative examples.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149165150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prototyping and evaluation of a clinical decision support system in long-term care in German nursing homes.","authors":"Maximilian Pilz, Anne Gebert, Matthias Brünett, Laura Steffny, Christina Schubert, Jonas Flechsig, Alexander Scherrer","doi":"10.1007/s10729-026-09794-2","DOIUrl":"https://doi.org/10.1007/s10729-026-09794-2","url":null,"abstract":"<p><p>Demographic change in Germany is increasing the demand for professional long-term care. Given rising requirements and simultaneous staff shortages, the need for digital systems is growing to effectively support nursing staff and mitigate staffing bottlenecks. This article introduces a hybrid clinical decision support system (CDSS) designed to generate actionable intervention recommendations by combining structured data and narrative nursing documentation. The CDSS consists of three interacting components: (1) knowledge models that encode state-of-the-art nursing knowledge, (2) a rule-based expert system that applies these models to generate individualized nursing interventions within the application fields mobility and pain management, and (3) a large language model (LLM) that extracts indicators that are necessary for knowledge-based decision-making from free-text entries to fill documentation gaps. A prototype was implemented and descriptively evaluated in two German nursing homes. Overall, 72% of the CDSS recommendations were rated as \"correct\" by nursing professionals, meaning appropriate for the care situation. In a separate evaluation, the LLM achieved 76% agreement rate in extracting care-relevant information from narratives. These results suggest that a hybrid architecture integrating expert knowledge, rule-based logic, and language models may have the potential to enhance nursing planning in long-term care settings.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13653949/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149166119","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization of the organization of a hemodialysis center.","authors":"Marie-Claude Normand, Marie-Laure Raphael Brossard, Guillaume Bollée, Nadia Lahrichi","doi":"10.1007/s10729-026-09795-1","DOIUrl":"https://doi.org/10.1007/s10729-026-09795-1","url":null,"abstract":"<p><p>Hemodialysis treatment requires patients to visit the hospital multiple times per week, with each session lasting several hours. Planning these treatments is challenging and requires interdependent decisions on nurse staffing, patient scheduling and daily assignment of patients to chairs and nurses. These decisions are complicated by heterogeneous patients acuity levels, diverse chair requirements, spatial constraints, and the need to maintain equitable nurse workloads. In collaboration with the hemodialysis center at the Centre Hospitalier de l'Université de Montréal (CHUM), a major teaching hospital in Montreal, we develop a sequential optimization approach that integrates long-term nurse staffing and patient scheduling followed by a multi-objective daily nurse-to-patient-to-chair assignment. The staffing and scheduling model balances workload across appointment periods, while the daily assignment model explicitly incorporates patient acuity, patient-chair requirements, and spatial clustering of chairs. Computational experiments based on real-world data show that schedule optimization reduces the maximum workload per appointment period, while optimized daily assignments decrease peak nurse workload by approximately 30% and substantially reduce non-contiguous chair allocations. Sensitivity analyses highlight trade-offs between workload equity, patient-chair alignment, and spatial efficiency. The proposed framework provides actionable insights for managing recurrent infusion services and is readily adaptable to other ambulatory care settings characterized by regular demand and shared critical resources.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149108886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A distribution-aware optimization model for improving operating room utilization and out-patient flow.","authors":"Yi Shen, Bruce W Rogers, Michael M Zavlanos","doi":"10.1007/s10729-026-09790-6","DOIUrl":"10.1007/s10729-026-09790-6","url":null,"abstract":"<p><p>Operating rooms (OR) are responsible for the majority of total hospital revenues and costs, making OR scheduling a critical component of hospital operations as it controls the patient flow in and out of the system. A major challenge in determining effective OR schedules is the uncertainty surrounding new (types of) cases related to, e.g., surgery duration and the post-surgical lengths of stay (LOS). We propose a distribution-aware learning method that estimates the distributions of surgery duration and LOS for each type using historical data. For types with insufficient historical data, we develop a transfer learning method that calculates Wasserstein barycenters to estimate the distributions from similar types with sufficient data points. Using the estimated distributions, we formulate a mixed-integer program that maximizes OR utilization, minimizes OR overtime, and controls the variability in daily discharges. We validate the proposed optimization and distribution-aware learning model in three surgery departments at the University Health System (UHS). The results show that the OR schedules created by the proposed method significantly outperform their human scheduler counterparts and two algorithmic baselines, a greedy algorithm and an optimization model using machine learning predictions. Equally important, the model parameters transfer across time and healthcare sites for the same surgery department, showing robustness of our approach to distribution shifts.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13612687/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149038210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Network data envelopment analysis in healthcare: A systematic literature review.","authors":"Guilherme P Afonso, José R Figueira, Diogo C Ferreira","doi":"10.1007/s10729-026-09793-3","DOIUrl":"10.1007/s10729-026-09793-3","url":null,"abstract":"<p><p>Healthcare performance assessment using nonparametric benchmarking approaches has risen in the literature in recent years. Several studies have been published employing data envelopment analysis (DEA) to evaluate healthcare performance. Among them, network-DEA use has caught special attention due to its advantages in considering more complex systems with departments interacting with each other. Accordingly, this systematic literature review aims to understand and analyze what has been done in the last years using network-DEA to study healthcare and provide helpful findings to those interested in the subject. Following the PRISMA guidelines, a systematic literature review was performed, selecting 40 relevant documents after 1,554 studies were collected and evaluated. All documents analyzing healthcare using network-DEA available in Scopus or Web of Science have been included until February 2025. From them, helpful information such as the framework used, the variables selected, formulation's characteristics, and other metadata have been collected and summarized. The findings suggest that there are topics clearly more studied (e.g. hospitals) than others (e.g., pharmacies). Moreover, the frameworks present several differences, albeit some similarities have been detected within the same case study. As for the variables, an extensive list has been identified, albeit most studies employ the number of beds, physicians, and nurses as well as operating expenses as inputs, inpatient discharges and outpatient visits as outputs, and the overall patient treated as links. By providing this information, this review aims to assist researchers in using network-DEA models to study healthcare by offering essential tools and highlighting gaps in the literature.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149024759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stochastic appointment scheduling with patient-and-time-dependent probability distributions.","authors":"Soheyl Khalilpourazari, Hossein Hashemi Doulabi","doi":"10.1007/s10729-026-09788-0","DOIUrl":"https://doi.org/10.1007/s10729-026-09788-0","url":null,"abstract":"<p><p>Outpatient appointment scheduling, in settings ranging from primary care practices to specialty consultation clinics, requires balancing provider idle time, overtime, and patient waiting time. Uncertainty in service times, patient punctuality, and attendance makes scheduling a challenging task, resulting in high clinic costs and low patient satisfaction. Addressing these uncertain factors is particularly difficult because they follow patient-and-time-dependent probability distributions. Existing models fail to simultaneously incorporate such distributions and often assume identical distributions for all patients in all time slots, mainly due to the increased modeling and solution complexity. In this research, we propose a novel stochastic programming model that captures an exponential number of scenarios using a polynomial number of variables and constraints without relying on sampling methods. We incorporate patient-dependent probability distributions for service times, and patient-and-time-dependent distributions for no-shows and arrival times, and we discuss how these distributions can be estimated from routinely collected electronic health record data. To enhance the model, we explore the impact of personalized reminders on no-show rates and scheduling effectiveness. Besides, we investigate how changes in attendance rates, influenced by incentives or negative clinic experiences, impact the appointment scheduling efficiency. The results demonstrate that, using our proposed model, we optimally solve several instances with up to 14 patients in a reasonable computational time. The generated schedules substantially outperform classical Bailey-type appointment rules, whose best-performing variant increases the total expected cost by 97% on average relative to our schedules. Moreover, the generated schedules reduce total costs by 34% on average by incorporating patient-dependent service times, 12% by considering patient-and-time-dependent unpunctuality, and 67% by integrating patient-and-time-dependent no-shows. Furthermore, we show that personalized reminders have the potential to reduce total costs by 23%, and sensitivity analyses confirm that these benefits are robust to moderate estimation errors in the input distributions. Our approach has a significant potential to improve the efficiency of healthcare services by reducing patient waiting time, provider idle time, and overtime costs, and it highlights the value of personalized communication strategies in improving patient attendance.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149024697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Counterfactual prescriptions via hierarchical ML for missed chemotherapy appointment prevention.","authors":"Mohammadreza Rajabzadeh, Arik Senderovich, Adam Diamant","doi":"10.1007/s10729-026-09787-1","DOIUrl":"https://doi.org/10.1007/s10729-026-09787-1","url":null,"abstract":"<p><p>Missed medical appointments, including cancellations and no-shows, disrupt clinical workflows, reduce resource efficiency, and can compromise patient care. This study develops a machine learning (ML) framework to jointly predict cancellations and no-shows using approximately 1.8 million chemotherapy appointments from Dana-Farber Cancer Institute in Boston, Massachusetts, USA. We implement a hierarchical ML approach that first detects cancellations and then predicts no-shows among the remaining cases. Combining static appointment features with dynamic temporal features derived from prior scheduling history, the model achieves F1-scores of 0.80 (cancellations) and 0.75 (no-shows), outperforming single-stage multiclass baselines in identifying the two non-attendance outcomes. To provide actionable insights, our ML pipeline also predicts the underlying reason for a missed visit. Lacking labeled no-show reasons, we apply a semi-supervised learning approach using short-notice cancellations as proxies and achieve F1-scores of 0.60 for cancellation reasons and 0.73 for no-show reasons. Finally, we use both models to conduct a counterfactual analysis to assess whether modifiable scheduling factors - such as appointment timing and provider consistency - can reduce cancellations and missed visits. We find that interventions informed by the literature, such as patient confirmations and scheduling lead time, are less effective in this setting than previously reported. We also evaluate two model-guided operational strategies motivated by the observed prediction patterns. Our findings highlight the value of designing predictive models with prescriptive intent, particularly when the goal is to tailor interventions to the specific operational context of a medical clinic.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149024702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Paving the way for more accessible cancer care in low-income countries with optimization.","authors":"Abel Sapirstein, Lauren N Steimle, Mathieu Dahan","doi":"10.1007/s10729-026-09754-w","DOIUrl":"10.1007/s10729-026-09754-w","url":null,"abstract":"<p><p>Cancers are a growing cause of morbidity and mortality in low-income countries. Geographic access plays a key role in both timely diagnosis and successful treatment. In areas lacking well-developed road networks, seasonal weather events can lengthen already long travel times to access care. Expanding facilities to offer cancer care is expensive and requires staffing by skilled medical professionals, which are often in short supply. In this article, we propose a mathematical model to improve geographic access to cancer care by jointly considering expansions to care facilities and improvements to the road network. We model this as a multi-period stochastic facility location network design problem. For each period, a decision maker must simultaneously choose a set of facilities at which to add tertiary cancer services and a set of roads to improve while facing demand and travel time uncertainty. Once demand for cancer care and weather events are realized, patients observe road conditions and use the transportation network to travel towards the closest facility with available cancer services. We create a new path-based formulation of this problem and develop a new branch-price-and-cut algorithm with acceleration techniques that take advantage of this formulation's structure. We demonstrate our approach using Rwanda as a case study and show that the reductions in travel time to cancer care directly attributable to the road network improvements can be as high as one hour.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 4","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13582274/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148982558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Operating-Room scheduling under uncertainty: balancing elective and emergency surgeries.","authors":"Hajar Sadegh Zadeh, Lele Zhang, Mark Fackrell, Hamideh Anjomshoa","doi":"10.1007/s10729-026-09791-5","DOIUrl":"10.1007/s10729-026-09791-5","url":null,"abstract":"<p><p>Balancing elective and emergency surgeries in operating room (OR) scheduling is challenging due to uncertainty in surgery durations and emergency arrivals. Traditional approaches, such as dedicated OR allocation and the Break-in-Moment (BIM) policy, can result in underutilised capacity and high emergency cancellation rates. This paper proposes a two-stage stochastic optimisation model that incorporates endogenous buffer allocation within the OR schedule. Rather than relying on policy-based or heuristically defined buffer times, the proposed framework determines the timing and placement of buffer slots as part of the optimisation process. In the first stage, elective surgeries and buffer placements are jointly determined at the beginning of the week. In the second stage, OR allocations are adjusted in response to realised emergency arrivals and surgery-duration deviations. The model is solved using the Sample Average Approximation (SAA) method and benchmarked against deterministic, perfect-information, and robust optimisation approaches. We validate the model using a synthetic dataset calibrated to real OR data from a public hospital. Computational experiments show that the proposed endogenous buffer-allocation approach achieves significant cost and cancellation reductions compared with all benchmark methods, while closely approaching the idealised perfect-information solution. Results over a six-month period indicate an 18% reduction in total weekly costs, an increase in average OR utilisation from 78% to 84%, and a substantial decrease in emergency cancellations. These findings demonstrate the value of endogenous buffer allocation for improving OR efficiency and responsiveness under uncertainty.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 3","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13562213/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148929782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Electric ambulances: will the need for charging affect response times?","authors":"Nanne A Dieleman, Caroline J Jagtenberg","doi":"10.1007/s10729-026-09786-2","DOIUrl":"10.1007/s10729-026-09786-2","url":null,"abstract":"<p><p>Ambulance providers currently rely on diesel vehicles for patient transport in their daily operations, but the first providers will likely transition to electric vehicles in the coming years. Prior to this transition, they would want to assess whether the non-negligible charging times impact response times. Our paper introduces this novel application and performs a study focused on range and charging infrastructure. We developed ELASPY, an open-source decision support system based on discrete-event simulation built in Python, to simulate the emergency response process, and used it to predict under which battery capacities and charger locations an electric ambulance fleet would achieve response times comparable to the equivalent diesel fleet. We also include a simulation-based optimization framework for charger allocation. We present a case study for the province of Utrecht, the Netherlands, from which derive managerial insights for ambulance providers. Our results did not reveal concerning signals for daily operations under the expected operating conditions. However, the sting is in the tail, and even ambulance providers with a low busyness will have to think about calamities such as prolonged power outages. We encourage decision makers to insert their own historical incident data into ELASPY and assess how transitioning from diesel to electric ambulance vehicles would affect response times in their region. The software is publicly available including documentation and set-up guidelines.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":"29 3","pages":""},"PeriodicalIF":2.8,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13534167/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148873899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}