Health Care Management Science最新文献

{"title":"Reinforcement learning for healthcare operations management: methodological framework, recent developments, and future research directions.","authors":"Qihao Wu, Jiangxue Han, Yimo Yan, Yong-Hong Kuo, Zuo-Jun Max Shen","doi":"10.1007/s10729-025-09699-6","DOIUrl":"https://doi.org/10.1007/s10729-025-09699-6","url":null,"abstract":"<p><p>With the advancement in computing power and data science techniques, reinforcement learning (RL) has emerged as a powerful tool for decision-making problems in complex systems. In recent years, the research on RL for healthcare operations has grown rapidly. Especially during the COVID-19 pandemic, RL has played a critical role in optimizing decisions with greater degrees of uncertainty. RL for healthcare applications has been an exciting topic across multiple disciplines, including operations research, operations management, healthcare systems engineering, and data science. This review paper first provides a tutorial on the overall framework of RL, including its key components, training models, and approximators. Then, we present the recent advances of RL in the domain of healthcare operations management (HOM) and analyze the current trends. Our paper concludes by presenting existing challenges and future directions for RL in HOM.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":""},"PeriodicalIF":2.3,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143811311","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 chance-constrained network DEA approach for evaluating medical service and quality efficiency: a case study of Taiwan.","authors":"Shiu-Wan Hung, Kai-Chu Yang, Wen-Min Lu, Minh-Hieu Le","doi":"10.1007/s10729-025-09700-2","DOIUrl":"10.1007/s10729-025-09700-2","url":null,"abstract":"<p><p>Healthcare efficiency is a critical concern for medical institutions, particularly in balancing service delivery and quality outcomes. This study aims to estimate the medical service efficiency (MSE) and medical quality efficiency (MQE) of 21 county-level and city-level medical institutions in Taiwan over the period from 2015 to 2019. We introduce a novel chance-constrained network Data Envelopment Analysis (DEA) model that integrates the advantages of the range directional measure (RDM), directional distance function (DDF), and enhanced Russell efficiency measure (ERM) to evaluate these efficiencies. Our findings reveal that non-metropolitan areas outperform metropolitan areas in MSE, while metropolitan areas excel in MQE. Furthermore, a truncated regression model is employed to identify the factors influencing MSE and MQE. The results indicate that the number of labor force and county or city attributes significantly negatively impact MSE, whereas these factors positively influence MQE. This study provides targeted optimization suggestions for medical institutions aiming to improve their operational and quality efficiencies.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"99-118"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143515441","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":"Assessing the performance of Portuguese public hospitals before and during COVID-19 outbreak, with optimistic and pessimistic benchmarking approaches.","authors":"Guilherme Mendes Vara, Marta Castilho Gomes, Diogo Cunha Ferreira","doi":"10.1007/s10729-024-09693-4","DOIUrl":"10.1007/s10729-024-09693-4","url":null,"abstract":"<p><p>The COVID-19 pandemic had a profound impact on the tertiary sector, particularly in healthcare, which faced unprecedented demand despite the existence of limited resources, such as hospital beds, staffing resources, and funding. The magnitude and global scale of this crisis provide a compelling incentive to thoroughly analyse its effects. This study aims to identify best practices within the Portuguese national healthcare service, with the goal of improving preparedness for future crises and informing policy decisions. Using a Benefit-of-the-Doubt (BoD) approach, this research constructs composite indicators to assess the pandemic's impact on the Portuguese public hospitals. The study analyzes monthly data from 2017 to May 2022, highlighting critical trends and performance fluctuations during this period. The findings reveal that each COVID-19 wave led to a decline in hospital performance, with the first wave being the most severe due to a lack of preparedness. Furthermore, the pandemic worsened the disparities among examined hospitals. Pre-pandemic top performers in each group improved their performance and were more consistently recognized as benchmarks, with their average benchmark frequency increasing from 66.5% to 83.5%. These top entities demonstrated greater resilience and adaptability, further distancing themselves from underperforming hospitals, which saw declines in both performance scores and benchmark frequency, widening the performance gap. The superior performance of top entities can be attributed to pre-existing strategic tools and contextual factors that enabled them to withstand the pandemic's challenges more effectively. HIGHLIGHTS: • The pandemic aggravated the differences between the hospitals examined. • The top-performing entities further distanced themselves from the remaining entities after the pandemic • Entities considered benchmarks before the pandemic remained the same, and became even more consistent during the pandemic. • The top-performing entities achieved higher scores than their pre-pandemic performance levels. • Benchmarking models for composite indicators with diverse decision-making preferences, and treatment of imperfect knowledge of data.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"1-27"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142739415","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":"Optimizing vaccination campaign strategies considering societal characteristics.","authors":"Serin Lee, Zelda B Zabinsky, Shan Liu","doi":"10.1007/s10729-025-09696-9","DOIUrl":"10.1007/s10729-025-09696-9","url":null,"abstract":"<p><p>Vaccine hesitancy continues to be a public health challenge. This study explores the dynamic interplay between disease transmission, evolving vaccination opinions, and targeted vaccination campaigns. Using a numerical experiment calibrated to the COVID-19 epidemic in King County, WA, during 2023, we optimize vaccination campaigns across various demographics. Our findings suggest that vaccination campaigns are most effective in societies with medium vaccine hesitancy, with optimal outcomes achieved by focusing on the 18-34 age group in the most densely populated regions. In societies with low hesitancy, campaigns may be unnecessary, and resources should target rural areas and the 0-17 age range to maximize impact. In high hesitancy societies, campaigns are ineffective. In such cases, efforts should focus on reducing vaccine risk perceptions. This research advances the understanding of dynamic behavioral responses to vaccination campaigns through evolutionary game theory, moving beyond models that assume static vaccination behavior. By employing a demographic-based networked compartmental model, it derives actionable and interpretable campaign strategies, providing valuable guidance for real-world implementation.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"84-98"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143382295","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":"Inter-organizational pooling of NICU nurses in the Dutch neonatal network: a simulation-optimization study.","authors":"Gréanne Leeftink, Kimberley Morris, Tim Antonius, Willem de Vries, Erwin Hans","doi":"10.1007/s10729-025-09697-8","DOIUrl":"10.1007/s10729-025-09697-8","url":null,"abstract":"<p><p>Neonatology care, the care for premature and severely ill babies, is increasingly confronted with capacity challenges. The entire perinatal care chain, including the Neonatal Intensive Care Unit (NICU), operates at high occupation levels. This results in refusals, leading to undesirable transports to other centers or even abroad, which affects quality of care, length of stay, and safety of these babies, and places a heavy burden on patients, their families, and involved caregivers. In this work we assess the improvement potential of network collaboration strategies that focus on reducing the number of patient transports, by allowing flexible deployment of nurses over the existing NICUs to match short-term changes in patient demand. We develop a discrete event simulation with an integrated optimization module for shift allocation and transfer optimization. A case study for the Dutch national NICU network, involving 9 NICU locations and current transport of 15% of all NICU patients in case of no flexible deployment, shows the potential of transporting staff instead of patients: About 70% of patient transports can be eliminated in case of 15-50% capacity sharing, and about 35% of nationwide transports is eliminated with up to 15% capacity sharing in the Dutch's main conurbation area only.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"64-83"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143255508","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":"Mechanistic modeling of social conditions in disease-prediction simulations via copulas and probabilistic graphical models: HIV case study.","authors":"Amir Khosheghbal, Peter J Haas, Chaitra Gopalappa","doi":"10.1007/s10729-024-09694-3","DOIUrl":"10.1007/s10729-024-09694-3","url":null,"abstract":"<p><p>As social and economic conditions are key determinants of HIV, the United States 'National HIV/AIDS Strategy (NHAS)', in addition to care and treatment, aims to address mental health, unemployment, food insecurity, and housing instability, as part of its strategic plan for the 'Ending the HIV Epidemic' initiative. Although mechanistic models of HIV play a key role in evaluating intervention strategies, social conditions are typically not part of the modeling framework. Challenges include the unavailability of coherent statistical data for social conditions and behaviors. We developed a method, combining undirected graphical modeling with copula methods, to integrate disparate data sources, to estimate joint probability distributions for social conditions and behaviors. We incorporated these in a national-level network model, Progression and Transmission of HIV (PATH 4.0), to simulate behaviors as functions of social conditions and HIV transmissions as a function of behaviors. As a demonstration for the potential applications of such a model, we conducted two hypothetical what-if intervention analyses to estimate the impact of an ideal 100% efficacious intervention strategy. The first analysis modeled care behavior (using viral suppression as proxy) as a function of depression, neighborhood, housing, poverty, education, insurance, and employment status. The second modeled sexual behaviors (number of partners and condom-use) as functions of employment, housing, poverty, and education status, among persons who exchange sex. HIV transmissions and disease progression were then simulated as functions of behaviors to estimate incidence reductions. Social determinants are key drivers of many infectious and non-infectious diseases. Our work enables the development of decision support tools to holistically evaluate the syndemics of health and social inequity.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"28-49"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142768193","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":"Road coverage as demand metric for ambulance allocation.","authors":"Martin van Buuren","doi":"10.1007/s10729-024-09695-2","DOIUrl":"10.1007/s10729-024-09695-2","url":null,"abstract":"<p><p>Ambulances must be strategically placed to ensure timely patient care and save lives. The allocation problem considered in the current paper optimally distributes a fixed number of ambulances over predetermined bases with limited capacity. Ambulance allocation problems are usually solved through historical demand. In such cases, researchers process call record data that is shared by ambulance service providers. This paper proposes an alternative demand metric, namely the meters of covered road. Road network information is widely and publicly available, making it easily accessible. We demonstrate for a real ambulance region that the road coverage demand metric performs similarly to the historical call record metric in the case of static allocation, and that it outperforms when dynamic ambulance management is used.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"50-63"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143004534","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":"DEA-based centralized resource allocation with a balance between efficiency and equity: evidence from healthcare services across 31 provinces in China.","authors":"Tao Du, Jinyu Li, Yan Qiao","doi":"10.1007/s10729-025-09698-7","DOIUrl":"10.1007/s10729-025-09698-7","url":null,"abstract":"<p><p>In the context of increasing investment in healthcare, the key issue of China's healthcare system reform is how to maximize output and ensure the equity of resource allocation. The generalized DEA-based resource allocation model (Model 1) pursues the maximization of DMU efficiency in resource allocation without considering equity, and it could yield a multi-solution problem by considering only the outputs instead of the inputs in the objective function. Thus, a DEA-based centralized resource allocation model with a balance between efficiency and equity (Model 2) is proposed, in which efficiency and equity are measured by output and input indicators in the objective function simultaneously, this could be more consistent with the essence of the DEA method. Model 2 effectively prevents the multi-solution problem by introducing both outputs and inputs into the objective function, and its Pareto-efficiency is proven. The main advantage of the proposed Model 2 is that efficiency and equity can be optimized in resource allocation; in particular, it can ensure equity for all DMUs in both absolute and relative terms. Furthermore, we illustrate and examine the application of Model 2 with centralized healthcare service resource allocation across 31 provinces in mainland China. We investigate the properties and effectiveness of Model 2 by comparison with Model 1 in terms of both efficiency and equity. Efficiency and equity are measured from three perspectives: efficiency values and slacks, input and output indicators, and allocation deviation. The results prove that Model 2 is superior to Model 1 in terms of both efficiency and equity.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"119-141"},"PeriodicalIF":2.3,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143673460","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":"Optimization of testing protocols to screen for COVID-19: a multi-objective model.","authors":"Hadi Moheb-Alizadeh, Donald P Warsing, Richard E Kouri, Sajjad Taghiyeh, Robert B Handfield","doi":"10.1007/s10729-024-09688-1","DOIUrl":"10.1007/s10729-024-09688-1","url":null,"abstract":"<p><p>In this paper we develop a new multi-objective simulated annealing (MOSA) algorithm to generate optimal testing protocols for infectious diseases, using the COVID-19 pandemic as our context. A SEIR (susceptible-exposed-infected-recovered) epidemiological model is embedded as the computational platform for our MOSA algorithm to optimize testing protocols for screening across three joint objectives: minimum cost of test materials, minimum total infections over the testing horizon, and minimum number of false negatives over the horizon. We demonstrate the application of this optimization tool to recommend screening protocols for K-12 school districts in the U.S. State of North Carolina. Our approach is scalable by population coverage and can be employed at the level of individual school districts or regional collections of districts, individual schools or collections of schools across a district, business sites, or nursing homes, among other congregate settings where individuals may be screened prior to gaining entry to the site. The algorithm can be solved two ways, generating either independent optimal protocols across individual testing locations, or a common protocol covering all locations in the collection of testing sites. Our findings can be used to inform policy decisions to guide the development of effective testing strategies for controlling the spread of COVID-19 or other pandemic diseases in a wide range of congregate settings across various geographic regions.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"580-603"},"PeriodicalIF":2.3,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142400160","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":"Forecasting to support EMS tactical planning: what is important and what is not.","authors":"Mostafa Rezaei, Armann Ingolfsson","doi":"10.1007/s10729-024-09690-7","DOIUrl":"10.1007/s10729-024-09690-7","url":null,"abstract":"<p><p>Forecasting emergency medical service (EMS) call volumes is critical for resource allocation and planning. The development of many commercial and free software packages has made a variety of forecasting methods accessible. Practitioners, however, are left with little guidance on selecting the most appropriate method for their needs. Using 5 years of data from 3 cities in Alberta, we compute exponential smoothing and benchmark forecasts for 8-hour periods for each ambulance station catchment area and with a forecast horizon of two weeks-a spatio-temporal resolution appropriate for tactical planning. The methods that we consider differ on three spectra: the number and type of time-series components, whether forecasts are computed individually or jointly, and the way in which forecasts at a specific resolution are converted to forecasts at the resolution of interest. We find that it is important to include a weekly seasonal component when forecasting EMS demand. Multiplicative seasonality, however, shows no benefit over additive seasonality. Adding other time-series components (e.g., trend, ARMA errors, Box-Cox transformation) does not improve performance. Spatial resolutions of station catchment area and lower, and temporal resolution of 4-24 hours perform similarly. We adapt an existing hierarchical forecasting framework to a two-dimensional spatio-temporal hierarchy, but find that hierarchical reconciliation of forecasts does not improve performance at the forecast resolution of interest for tactical planning. Neither does jointly forecasting time series. We show that added complexity does not materially improve forecasting performance. The simple methods that we find perform well are easy to implement and interpret, making implementation in practice more likely. In a simulation study we alter the empirical weekly patterns and demonstrate how extreme differences between the weekly seasonality patterns of different regions cause hierarchically-reconciled bottom-up approaches to outperform top-down approaches.</p>","PeriodicalId":12903,"journal":{"name":"Health Care Management Science","volume":" ","pages":"604-630"},"PeriodicalIF":2.3,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142463887","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}