共找到 20 条结果
暂无摘要（点击查看详情）
暂无摘要（点击查看详情）
暂无摘要（点击查看详情）
暂无摘要（点击查看详情）
INTRODUCTION: Health care systems around the world are struggling with limited resources, in relation to the prevailing health care need. An accessible primary care is an important part of the solution for how to provide affordable care for the population and reduce pressure on the overall health care system such as unnecessary hospital stays and associated costs. As primary care constitutes an important first line of healthcare, the task of prioritising and deciding what to do and for whom lies in practice, primarily with the primary care professionals. Thus, the decisions and behaviour of primary care professionals have a central role in achieving good and equal health in the population. The aim of this study is to explore how primary health care professionals handle situations with limited resources and enhance our knowledge of priorities in practice. METHODS: Semi-structured interviews with 14 health care professionals (7 nurses, 7 physicians) working in Swedish primary care were interviewed. Data were analysed inductively with content analysis. FINDINGS: Three main categories were found: Influx of patients; Structural conditions; and Actions. Each category illustrates an important aspect for what primary care professionals do to achieve good and equal care. The influx of patients concerned what the professionals handled in terms of patients' healthcare needs and patient behaviour. Structural conditions consisted of policies and goals set for primary care, competence availability, technical systems, and organisational culture. To handle situations due to limited resources, professionals performed different actions: matching health care needs with professionals' competency, defining care needs to suit booking systems appointments, giving care at the inappropriate health care level, rearranging workhours, and passing on the decision making. CONCLUSION: Priorities in primary care are not, "one fits all" solution. Our study shows that priorities in primary care comprise of ongoing daily processes that are adapted to the situation, context of patient influx, and structural conditions. Healthcare professional's actions for how influx of patients' is handled in relation to limited resources, are created, and shaped within this context which also sets the boundaries for their actions.
Relationship-centred care (RCC) recognises that healthcare quality depends not only on outcomes, but on how voice, responsibility, and emotional labour are negotiated among patients, caregivers, and providers. As AI systems enter sensitive care contexts, they introduce a new participant into these negotiations. Drawing on empirical work in Advance Care Planning (ACP) and peer support, we argue that AI's primary impact in high-subjectivity domains is not optimisation but redistribution: it reorganises who speaks, who decides, and who bears moral responsibility. Across both settings, participants were less concerned with technical accuracy than with relational consequences: whether AI would appropriately represent their decision, reduce burden, or blur accountability, scaffold connection, or subtly displace it. We identify three relational dimensions: authority, temporality, and visibility, through which AI reshapes care relationships, and propose design provocations centred on relational legibility, bounded agency, responsibility traceability, and non-substitutive scaffolding.
BACKGROUND: We aim to describe the health-related quality of life of informal carers and their experiences of primary care. METHODS: Responses from the 2011-12 English General Practice Patient Survey, including 195,364 informal carers, were analysed using mixed effect logistic regressions controlling for age, gender, ethnicity and social deprivation to describe carer health-related quality of life (mobility, self-care, usual activities, pain, and anxiety/depression, measured using EQ-5D) and primary care experience (access, continuity and communication). RESULTS: Informal carers reported poorer health-related quality of life than non-carers of similar age, gender, ethnicity and social deprivation. Increasing caring commitment was associated with worse EQ-5D scores, with carers of 50+ hours a week scoring 0.05 points lower than non-carers (95 % CI 0.05 to 0.04), equivalent to 18 fewer days of full health annually. Considering each domain of EQ-5D separately, carers of 50+ hours/week were more likely to report pain OR = 1.53 (1.50-1.57), p < 0.0001, and anxiety/depression OR = 1.69 (1.66-1.73), p < 0.0001, than non-carers. Younger carers scored lower on EQ-5D than non-carer peers but the converse was true among over-85s. In the most deprived areas carers reported the equivalent of 37 fewer days of full health annually than carers in the most affluent areas. On average, carers reported poorer patient experiences in all areas of primary care than non-carers (odds ratios 0.84-0.97), with this difference being most marked in the domain of access. CONCLUSIONS: Informal carers experience a double disadvantage of poorer health-related quality of life and poorer patient experience in primary care. We find no evidence for health benefits of caregiving. We recommend physicians identify and treat carer health problems, including pain and anxiety/depression, particularly among young, deprived and high time-commitment carers. Improving patient experience for carers, including access to primary care, should be a priority.
Bias and inequity in palliative care disproportionately affect marginalised groups. Large language models (LLMs), such as GPT-4o, hold potential to enhance care but risk perpetuating biases present in their training data. This study aimed to systematically evaluate whether GPT-4o propagates biases in palliative care responses using adversarially designed datasets. In July 2024, GPT-4o was probed using the Palliative Care Adversarial Dataset (PCAD), and responses were evaluated by three palliative care experts in Canada and the United Kingdom using validated bias rubrics. The PCAD comprised PCAD-Direct (100 adversarial questions) and PCAD-Counterfactual (84 paired scenarios). These datasets targeted four care dimensions (access to care, pain management, advance care planning, and place of death preferences) and three identity axes (ethnicity, age, and diagnosis). Bias was detected in a substantial proportion of responses. For adversarial questions, the pooled bias rate was 0.33 (95% confidence interval [CI]: 0.28, 0.38); "allows biased premise" was the most frequently identified source of bias (0.47; 95% CI: 0.39, 0.55), such as failing to challenge stereotypes. For counterfactual s
Long-term care service for old people is in great demand in most of the aging societies. The number of nursing homes residents is increasing while the number of care providers is limited. Due to the care worker shortage, care to vulnerable older residents cannot be fully tailored to the unique needs and preference of each individual. This may bring negative impacts on health outcomes and quality of life among institutionalized older people. To improve care quality through personalized care planning and delivery with limited care workforce, we propose a new care planning model assisted by artificial intelligence. We apply bandit algorithms which optimize the clinical decision for care planning by adapting to the sequential feedback from the past decisions. We evaluate the proposed model on empirical data acquired from the Systems for Person-centered Elder Care (SPEC) study, a ICT-enhanced care management program.
Digital Twin (DT) technology has emerged as a transformative approach in healthcare, but its application in personalized patient care remains limited. This paper aims to present a practical implementation of DT in the management of chronic diseases. We introduce a general DT framework for personalized care planning (DT4PCP), with the core components being a real-time virtual representation of a patient's health and emerging predictive models to enable adaptive, personalized care. We implemented the DT4PCP framework for managing Type 2 Diabetes (DT4PCP-T2D), enabling real-time collection of behavioral data from patients with T2D, predicting emergency department (ED) risks, simulating the effects of different interventions, and personalizing care strategies to reduce ED visits. The DT4PCP-T2D also integrates social determinants of health (SDoH) and other contextual data, offering a comprehensive view of the patient's health to ensure that care recommendations are tailored to individual needs. Through retrospective simulations, we demonstrate that integrating DTs in T2D management can lead to significant advancements in personalized medicine. This study underscores the potential of DT
CARE-link is an open-source, web-based clinical support platform designed to improve the management of gestational diabetes by linking clinicians and patients through an LLM-mediated workflow. The system aggregates patient-generated data outside the hospital, summarizes relevant clinical information, and delivers context-aware decision support to clinicians. For patients, CARE-link provides clear explanations of management plans and delivers timely lifestyle guidance through a WhatsApp interface. The integrated dual-facing design aims to promote continuous monitoring, support individualized care, and reduce the burden of in-clinic follow-ups. Built with a modular architecture, the platform can be adapted to other chronic conditions requiring longitudinal tracking and behavioral support. CARE-link has the potential to enhance clinical oversight, promote patient compliance, and strengthen continuity of care particularly in resource-constrained settings.
Electronic health records (EHRs) provide comprehensive patient data which could be better used to enhance informed decision-making, resource allocation, and coordinated care, thereby optimising healthcare delivery. However, in mental healthcare, critical information, such as on risk factors, precipitants, and treatment responses, is often embedded in unstructured text, limiting the ability to automate at scale measures to identify and prioritise local populations and patients, which potentially hinders timely prevention and intervention. We describe the development and proof-of-concept implementation of VIEWER, a clinical informatics platform designed to enhance direct patient care and population health management by improving the accessibility and usability of EHR data. We further outline strategies that were employed in this work to foster informatics innovation through interdisciplinary and cross-organisational collaboration to support integrated, personalised care, and detail how these advancements were piloted and implemented within a large UK mental health National Health Service Foundation Trust to improve patient outcomes at an individual patient, clinician, clinical team,
As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Rank Adaptation (LoRA), currently one of the most widely adopted parameter-efficient fine-tuning (PEFT) methods, mitigates this challenge by optimizing only low-rank adaptation matrices, thereby greatly reducing the number of trainable parameters. With the parameter overhead substantially reduced, the activations retained for backpropagation have emerged as the primary remaining memory bottleneck during LoRA fine-tuning. To address this, we propose CARE-LoRA, a data-aware Compressed Activation REconstruction framework. By exploiting the inherent projection structure of LoRA, CARE-LoRA replaces the full input activation with the low-rank compressed activation naturally produced by the LoRA branch. It further computes a lightweight reconstruction matrix during the forward pass with negligible additional computation cost, which is used during backpropagation to reconstruct the gradient signal, thereby keeping LoRA matrices fully trainable. Extensive experiments across diverse models and downstream tasks demonstrate that, while substantially
BACKGROUND: Different models for care pathways involving both specialist and primary care have been developed to ensure adequate follow-up after discharge. These care pathways have mainly been developed and run by specialist care and have been disease-based. In this study, primary care providers took the initiative to develop a model for integrated care pathways across care levels for older patients in need of home care services after discharge. Initially, the objective was to develop pathways for patients diagnosed with heart failure, COPD and stroke. The aim of this paper is to investigate the process and the experiences of the participants in this developmental work. The participants were drawn from three hospitals, six municipalities and patient organizations in Central Norway. METHODS: This qualitative study used focus group interviews, written material and observations. Representatives from the hospitals, municipalities and patient organizations taking part in the development process were chosen as informants. RESULTS: The development process was very challenging because of the differing perspectives on care and different organizational structures in specialist care and primary care. In this study, the disease perspective, being dominant in specialist care, was not found to be suitable for use in primary health care because of the need to cover a broader perspective including the patient's functioning, social situation and his or her preferences. Furthermore, managing several different disease-based care pathways was found to be unsuitable in home care services, as well as unsuitable for a population characterized by a substantial degree of comorbidity. The outcome of the development process was a consensus that outlined a single, common patient-centred care pathway for transition from hospital to follow-up in primary care. The pathway was suitable for most common diseases and included functional and social aspects as well as disease follow-up, thus merging the differing perspectives. The disease-based care pathways were kept for use within the hospitals. CONCLUSIONS: Disease-based care pathways for older patients were found to be neither feasible nor sustainable in primary care. A common patient-centred care pathway that could meet the needs of multi- morbid patients was recommended.
Demand for health care is constantly increasing due to the ongoing demographic change, while at the same time health service providers face difficulties in finding skilled personnel. This creates pressure on health care systems around the world, such that the efficient, nationwide provision of primary health care has become one of society's greatest challenges. Due to the complexity of health care systems, unforeseen future events, and a frequent lack of data, analyzing and optimizing the performance of health care systems means tackling a wicked problem. To support this task for primary care, this paper introduces the hybrid agent-based simulation model SiM-Care. SiM-Care models the interactions of patients and primary care physicians on an individual level. By tracking agent interactions, it enables modelers to assess multiple key indicators such as patient waiting times and physician utilization. Based on these indicators, primary care systems can be assessed and compared. Moreover, changes in the infrastructure, patient behavior, and service design can be directly evaluated. To showcase the opportunities offered by SiM-Care and aid model validation, we present a case study for
PURPOSE: Care coordination is increasingly recognized as a necessary element of high-quality, patient-centered care. This study investigated (1) the association between care coordination and continuity of primary care, and (2) differences in this association by level of specialty care use. METHODS: We conducted a cross-sectional study of Medicare enrollees with select chronic conditions in an integrated health care delivery system in Washington State. We collected survey information on patient experiences and automated health care utilization data for 1 year preceding survey completion. Coordination was defined by the coordination measure from the short form of the Ambulatory Care Experiences Survey (ACES). Continuity was measured by primary care visit concentration. Patients who had 10 or more specialty care visits were classified as high users. Linear regression was used to estimate the association between coordination and continuity, controlling for potential confounders and clustering within clinicians. We used a continuity-by-specialty interaction term to determine whether the continuity-coordination association was modified by high specialty care use. RESULTS: Among low specialty care users, an increase of 1 standard deviation (SD) in continuity was associated with an increase of 2.71 in the ACES coordination scale (P <.001). In high specialty care users, we observed no association between continuity and reported coordination (P= .77). CONCLUSIONS: High use of specialty care may strain the ability of primary care clinicians to coordinate care effectively. Future studies should investigate care coordination interventions that allow for appropriate specialty care referrals without diminishing the ability of primary care physicians to manage overall patient care.
We find ourselves on the ever-shifting cusp of an AI revolution -- with potentially metamorphic implications for the future practice of healthcare. For many, such innovations cannot come quickly enough; as healthcare systems worldwide struggle to keep up with the ever-changing needs of our populations. And yet, the potential of AI tools and systems to shape healthcare is as often approached with great trepidation as celebrated by health professionals and patients alike. These fears alight not only in the form of privacy and security concerns but for the potential of AI tools to reduce patients to datapoints and professionals to aggregators -- to make healthcare, in short, less caring. This infixated concern, we - as designers, developers and researchers of AI systems - believe it essential we tackle head on; if we are not only to overcome the AI implementation gap, but realise the potential of AI systems to truly augment human-centred practices of care. This, we argue we might yet achieve by realising newly-accessible practices of AI healthcare innovation, engaging providers, recipients and affected communities of care in the inclusive design of AI tools we may yet enthusiastically
Relationship-centered care relies on trust and meaningful connection. As AI enters clinical settings, we must ask not just what it can do, but how it should be positioned to support these values. We examine a "middle, not top" approach where AI mediates communication without usurping human judgment. Through studies of CLEAR, an asynchronous messaging system, we show how this configuration addresses real-world constraints like time pressure and uneven health literacy. We find that mediator affordances (e.g., availability, neutrality) redistribute interpretive work and reduce relational friction. Ultimately, we frame AI mediation as relational infrastructure, highlighting critical design tensions around framing power and privacy.
Recent reinforcement learning approaches, such as outcome-supervised GRPO, have advanced Chain-of-Thought reasoning in large language models (LLMs), yet their adaptation to multimodal LLMs (MLLMs) is unexplored. To address the lack of rigorous evaluation for MLLM post-training methods, we introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning. It offers a large training set and evaluates generalization across three escalating challenges: in-distribution, cross-environment, and cross-environment-task scenarios. Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate. This stems from reward signals focusing solely on final answers, encouraging shortcuts, and strict KL penalties limiting exploration.To address this, we propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision. GRPO-CARE introduces a two-tiered reward: (1) a base reward for answer correctness, and (2) an adaptive consistency bonus, computed by comparing t