The creation of nurses' schedules is a critical task that directly impacts the quality and safety of patient care as well as the quality of life for nurses. In most hospitals in Japan, this responsibility falls to the head nurse of each ward. The physical and mental burden of this task is considerable, and recent challenges such as the growing shortage of nurses and increasingly diverse working styles have further complicated the scheduling process. Consequently, there is a growing demand for automated nurse scheduling systems. Technically, modern integer programming solvers can generate feasible schedules within a practical timeframe. However, in many hospitals, schedules are still created manually. This is largely because tacit knowledge, considerations unconsciously applied by head nurses, cannot be fully formalized into explicit constraints, often resulting in automatically generated schedules that are not practically usable. To address this issue, we propose a novel "two-stage scheduling method." This approach divides the scheduling task into night shift and day shift stages, allowing head nurses to make manual adjustments after the first stage. This interactive process makes
Healthcare systems face increasing pressure to allocate limited nursing resources efficiently while accounting for skill heterogeneity, patient acuity, staff fatigue, and continuity of care. Traditional optimization and heuristic scheduling methods struggle to capture these dynamic, multi-constraint environments. I propose NurseSchedRL, a reinforcement learning framework for nurse-patient assignment that integrates structured state encoding, constrained action masking, and attention-based representations of skills, fatigue, and geographical context. NurseSchedRL uses Proximal Policy Optimization (PPO) with feasibility masks to ensure assignments respect real-world constraints, while dynamically adapting to patient arrivals and varying nurse availability. In simulation with realistic nurse and patient data, NurseSchedRL achieves improved scheduling efficiency, better alignment of skills to patient needs, and reduced fatigue compared to baseline heuristic and unconstrained RL approaches. These results highlight the potential of reinforcement learning for decision support in complex, high-stakes healthcare workforce management.
Nurse staffing and scheduling are persistent challenges in healthcare due to demand fluctuations and individual nurse preferences. This study introduces the concept of bounded flexibility, balancing nurse satisfaction with strict rostering rules, particularly a real-world time regularity policy from a major hospital in Singapore. We model the problem as a multi-stage stochastic program to address evolving demand, optimizing both aggregate staffing and detailed scheduling decisions. A reformulation into a two-stage structure using block-separable recourse reduces computational burden without loss of accuracy. To solve the problem efficiently, we develop a Generative AI-guided algorithm. Numerical experiments with real hospital data show substantial cost savings and improved nurse flexibility with minimal compromise to schedule regularity. Numerical experiments based on real-world nurse profiles, nurse preferences, and patient demand data are conducted to evaluate the performance of the proposed methods. Our results demonstrate that the stochastic model achieves significant cost savings compared to the deterministic model. Notably, a slight reduction in the regularity level can remar
Recent advancements in Large Language Models (LLMs) have played a significant role in reducing human workload across various domains, a trend that is increasingly extending into the medical field. In this paper, we propose an automated pipeline designed to alleviate the burden on nurses by automatically extracting clinical observations from nurse dictations. To ensure accurate extraction, we introduce a method based on Retrieval-Augmented Generation (RAG). Our approach demonstrates effective performance, achieving an F1-score of 0.796 on the MEDIQA-SYNUR test dataset.
We present the design principles of a nurse scheduling system built using Answer Set Programming (ASP) and successfully deployed at the University of Yamanashi Hospital. Nurse scheduling is a complex optimization problem requiring the reconciliation of individual nurse preferences with hospital staffing needs across various wards. This involves balancing hard and soft constraints and the flexibility of interactive adjustments. While extensively studied in academia, real-world nurse scheduling presents unique challenges that go beyond typical benchmark problems and competitions. This paper details the practical application of ASP to address these challenges at the University of Yamanashi Hospital, focusing on the insights gained and the advancements in ASP technology necessary to effectively manage the complexities of real-world deployment.
In modern healthcare, the demand for autonomous robotic assistants has grown significantly, particularly in the operating room, where surgical tasks require precision and reliability. Robotic scrub nurses have emerged as a promising solution to improve efficiency and reduce human error during surgery. However, challenges remain in terms of accurately grasping and handing over surgical instruments, especially when dealing with complex or difficult objects in dynamic environments. In this work, we introduce a novel robotic scrub nurse system, RoboNurse-VLA, built on a Vision-Language-Action (VLA) model by integrating the Segment Anything Model 2 (SAM 2) and the Llama 2 language model. The proposed RoboNurse-VLA system enables highly precise grasping and handover of surgical instruments in real-time based on voice commands from the surgeon. Leveraging state-of-the-art vision and language models, the system can address key challenges for object detection, pose optimization, and the handling of complex and difficult-to-grasp instruments. Through extensive evaluations, RoboNurse-VLA demonstrates superior performance compared to existing models, achieving high success rates in surgical in
Using a systematic review and meta-analysis, this study investigates the impact of the COVID-19 pandemic on job burnout among nurses. We review healthcare articles following the PRISMA 2020 guidelines and identify the main aspects and factors of burnout among nurses during the pandemic. Using the Maslach Burnout questionnaire, we searched PubMed, ScienceDirect, and Google Scholar, three open-access databases, for relevant sources measuring emotional burnout, personal failure, and nurse depersonalization. Two reviewers extract and screen data from the sources and evaluate the risk of bias. The analysis reveals that 2.75% of nurses experienced job burnout during the pandemic, with a 95% confidence interval and rates varying from 1.87% to 7.75%. These findings emphasize the need for interventions to address the pandemic's effect on job burnout among nurses and enhance their well-being and healthcare quality. We recommend considering individual, organizational, and contextual factors influencing healthcare workers' burnout. Future research should focus on identifying effective interventions to lower burnout in nurses and other healthcare professionals during pandemics and high-stress s
The utilization of robotic technology has gained traction in healthcare facilities due to progress in the field that enables time and cost savings, minimizes waste, and improves patient care. Digital healthcare technologies that leverage automation, such as robotics and artificial intelligence, have the potential to enhance the sustainability and profitability of healthcare systems in the long run. However, the recent COVID-19 pandemic has amplified the need for cyber-physical robots to automate check-ups and medication administration. A robot nurse is controlled by the Internet of Things (IoT) and can serve as an automated medical assistant while also allowing supervisory control based on custom commands. This system helps reduce infection risk and improves outcomes in pandemic settings. This research presents a test case with a nurse robot that can assess a patient's health status and take action accordingly. We also evaluate the system's performance in medication administration, health-status monitoring, and life-cycle considerations.
For patients experiencing cancer, nurse navigation can ease the burden of complex care by enhancing coordination of health services and patient outcomes. However, in under-resourced areas, trained nurse navigators may be limited or non-existent. In the United States, artificial intelligence (AI)-enabled digital health tools are increasingly available and may help address gaps in care coordination; however, most are not designed to specifically support nursing. This perspective piece discusses a human-centered AI framework that integrates empathic and agentic approaches grounded in the American Nurses Association's code of ethics to support nurses in the United States in cancer care navigation. The framework could augment, not replace, human empathy and agency while improving nurse workflow, patient-clinician relationships, and care coordination services in under-resourced areas.
Assigning patients to rooms and nurses to patients are critical tasks within hospitals that directly affect patient and staff satisfaction, quality of care, and hospital efficiency. Both patient-to-room assignments and nurse-to-patient assignments are typically agreed upon at the ward level, and they interact in several ways such as jointly determining the walking distances nurses must cover between different patient rooms. This motivates to consider both problems jointly in an integrated fashion. This paper presents the first optimization models and algorithms for the integrated patient-to-room and nurse-to-patient assignment problem. We provide a mixed integer programming formulation of the integrated problem that considers the typical objectives from the single problems as well as additional objectives that can only be properly evaluated when integrating both problems. Moreover, motivated by the inherent complexity that results from integrating these two NP-hard and already computationally challenging problems, we devise an efficient heuristic for the integrated patient-to-room and nurse-to-patient assignment problem. To evaluate the running time and quality of the solution obta
Effective communication training is essential to preparing nurses for high-quality patient care. While standardized patient (SP) simulations provide valuable experiential learning, they are often costly and inflexible. Virtual patient (VP) systems offer a scalable alternative, but most fail to adapt to the varying communication skills of trainees. In particular, when trainees respond ineffectively, VPs should escalate in hostility or become uncooperative--yet this level of adaptive interaction remains largely unsupported. To address this gap, we introduce Adaptive-VP, a VP dialogue generation framework that leverages large language models (LLMs) to dynamically adapt VP behavior based on trainee input. The framework features a pipeline for constructing clinically grounded yet flexible VP scenarios and a modular system for assessing trainee communication and adjusting VP responses in real time, while ensuring learner safety. We validated Adaptive-VP by simulating challenging patient conversations. Automated evaluation using a corpus from practicing nurses showed that our communication skill evaluation mechanism reflected real-world proficiency levels. Expert nurses further confirmed
Recent advancements in large language models (LLMs) have significantly transformed medical systems. However, their potential within specialized domains such as nursing remains largely underexplored. In this work, we introduce NurseLLM, the first nursing-specialized LLM tailored for multiple choice question-answering (MCQ) tasks. We develop a multi-stage data generation pipeline to build the first large scale nursing MCQ dataset to train LLMs on a broad spectrum of nursing topics. We further introduce multiple nursing benchmarks to enable rigorous evaluation. Our extensive experiments demonstrate that NurseLLM outperforms SoTA general-purpose and medical-specialized LLMs of comparable size on different benchmarks, underscoring the importance of a specialized LLM for the nursing domain. Finally, we explore the role of reasoning and multi-agent collaboration systems in nursing, highlighting their promise for future research and applications.
When managing an organization, planners often encounter numerous challenging scenarios. In such instances, relying solely on intuition or managerial experience may not suffice, necessitating a quantitative approach. This demand is further accentuated in the era of big data, where the sheer scale and complexity of constraints pose significant challenges. Therefore, the aim of this study is to provide a foundational framework for addressing personnel scheduling, a critical issue in organizational management. Specifically, we focus on optimizing shift assignments for staff, a task fraught with complexities due to factors such as contractual obligations and mandated rest periods. Moreover, the current landscape is characterized by frequent employee shortages across various industries, with many organizations lacking efficient and dependable management tools to address them. Therefore, our attention is particularly drawn to the nurse rostering problem, a personnel scheduling challenge prevalent in healthcare settings. These issues are characterized by a multitude of variables, given that a single healthcare facility may employ hundreds of nurses, alongside stringent constraints such as
We study the nurse staffing problem under random nurse demand and absenteeism. While the demand uncertainty is exogenous (stemming from the random patient census), the absenteeism uncertainty is \emph{endogenous}, i.e., the number of nurses who show up for work partially depends on the nurse staffing level. For quality of care, many hospitals have developed float pools, i.e., groups of hospital units, and trained nurses to be able to work in multiple units (termed cross-training) in response to potential nurse shortage. In this paper, we propose a distributionally robust nurse staffing (DRNS) model that considers both exogenous and endogenous uncertainties. We derive a separation algorithm to solve this model under a general structure of float pools. In addition, we identify several pool structures that often arise in practice and recast the corresponding DRNS model as a mixed-integer linear program, which facilitates off-the-shelf commercial solvers. Furthermore, we optimize the float pool design to reduce cross-training while achieving specified target staffing costs. The numerical case studies, based on the data of a collaborating hospital, suggest that the units with high absen
Traditional techniques to detect malware infections were not meant to be used by the end-user and current malware removal tools and security software cannot handle the heterogeneity of IoT devices. In this paper, we design, develop and evaluate a tool, called NURSE, to fill this information gap, i.e., enabling end-users to detect IoT-malware infections in their home networks. NURSE follows a modular approach to analyze IoT traffic as captured by means of an ARP spoofing technique which does not require any network modification or specific hardware. Thus, NURSE provides zero-configuration IoT traffic analysis within everybody's reach. After testing NURSE in 83 different IoT network scenarios with a wide variety of IoT device types, results show that NURSE identifies malware-infected IoT devices with high accuracy (86.7%) using device network behavior and contacted destinations.
In this paper, we study the nurse rostering problem that considers multiple units and many soft time-related constraints. An efficient branch and price solution approach that relies on a fast algorithm to solve the pricing subproblem of the column generation process is presented. For the nurse rostering problem, its pricing subproblem can be formulated as a shortest path problem with resource constraints, which has been the backbone of several solutions for several classical problems like vehicle routing problems. However, approaches that perform well on these problems cannot be used since most constraints in the nurse rostering problem are soft. Based on ideas borrowed from global constraints in constraint programming to model rostering problems, an efficient dynamic programming algorithm with novel label definitions and dominating rules specific to soft time-related constraints is proposed. In addition, several acceleration strategies are employed to improve the branch and price algorithm. Computational results on instances of different sizes indicate that the proposed algorithm is a promising solution for the nurse rostering problem with multiple units.
The nurse scheduling problem is a critical optimization challenge in healthcare management. It aims to balance staffing demands, nurse satisfaction, and patient care quality. Corresponding to the constraints inherent in this scheduling problem, we detail the mathematical formulation step-by-step. We then utilize a quantum-inspired technique, the simulated annealing algorithm, and a quadratic unconstrained binary optimization model to optimize workload and increase nurse preferences. Numerical experiments are implemented to show the capacity of our proposed techniques. Our findings indicate a promising direction for future research, with potential applications extending beyond nurse scheduling to other complex optimization problems.
Suspicions about medical murder sometimes arise due to a surprising or unexpected series of events, such as an apparently unusual number of deaths among patients under the care of a particular nurse. But also a single disturbing event might trigger suspicion about a particular nurse, and this might then lead to investigation of events which happened when she was thought to be present. In either case, there is a statistical challenge of distinguishing event clusters that arise from criminal acts from those that arise coincidentally from other causes. We show that an apparently striking association between a nurse's presence and a high rate of deaths in a hospital ward can easily be completely spurious. In short: in a medium-care hospital ward where many patients are suffering terminal illnesses, and deaths are frequent, most deaths occur in the morning. Most nurses are on duty in the morning, too. There are less deaths in the afternoon, and even less at night; correspondingly, less nurses are on duty in the afternoon, even less during the night. Consequently, a full time nurse works the most hours when the most deaths occur. The death rate is higher when she is present than when she
In recent years genetic algorithms have emerged as a useful tool for the heuristic solution of complex discrete optimisation problems. In particular there has been considerable interest in their use in tackling problems arising in the areas of scheduling and timetabling. However, the classical genetic algorithm paradigm is not well equipped to handle constraints and successful implementations usually require some sort of modification to enable the search to exploit problem specific knowledge in order to overcome this shortcoming. This paper is concerned with the development of a family of genetic algorithms for the solution of a nurse rostering problem at a major UK hospital. The hospital is made up of wards of up to 30 nurses. Each ward has its own group of nurses whose shifts have to be scheduled on a weekly basis. In addition to fulfilling the minimum demand for staff over three daily shifts, nurses' wishes and qualifications have to be taken into account. The schedules must also be seen to be fair, in that unpopular shifts have to be spread evenly amongst all nurses, and other restrictions, such as team nursing and special conditions for senior staff, have to be satisfied. The
This paper proposes a new memetic evolutionary algorithm to achieve explicit learning in rule-based nurse rostering, which involves applying a set of heuristic rules for each nurse's assignment. The main framework of the algorithm is an estimation of distribution algorithm, in which an ant-miner methodology improves the individual solutions produced in each generation. Unlike our previous work (where learning is implicit), the learning in the memetic estimation of distribution algorithm is explicit, i.e. we are able to identify building blocks directly. The overall approach learns by building a probabilistic model, i.e. an estimation of the probability distribution of individual nurse-rule pairs that are used to construct schedules. The local search processor (i.e. the ant-miner) reinforces nurse-rule pairs that receive higher rewards. A challenging real world nurse rostering problem is used as the test problem. Computational results show that the proposed approach outperforms most existing approaches. It is suggested that the learning methodologies suggested in this paper may be applied to other scheduling problems where schedules are built systematically according to specific rul