Introduction: Artificial intelligence (AI) and neuroimaging offer new opportunities for diagnosis and prognosis of dementia.Methods: We systematically reviewed studies reporting AI for neuroimaging in diagnosis and/or prognosis of cognitive neurodegenerative diseases.Results: A total of 255 studies were identified. Most studies relied on the Alzheimer's Disease Neuroimaging Initiative dataset. Algorithmic classifiers were the most commonly used AI method (48%) and discriminative models performed best for differentiating Alzheimer's disease from controls. The accuracy of algorithms varied with the patient cohort, imaging modalities, and stratifiers used. Few studies performed validation in an independent cohort.Discussion: The literature has several methodological limitations including lack of sufficient algorithm development descriptions and standard definitions. We make recommendations to improve model validation including addressing key clinical questions, providing sufficient description of AI methods and validating findings in independent datasets. Collaborative approaches between experts in AI and medicine will help achieve the promising potential of AI tools in practice.Highlights: There has been a rapid expansion in the use of machine learning for diagnosis and prognosis in neurodegenerative disease Most studies (71%) relied on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset with no other individual dataset used more than five times There has been a recent rise in the use of more complex discriminative models (e.g., neural networks) that performed better than other classifiers for classification of AD vs healthy controls We make recommendations to address methodological considerations, addressing key clinical questions, and validation We also make recommendations for the field more broadly to standardize outcome measures, address gaps in the literature, and monitor sources of bias

The need to better understand implementing evidence-informed dementia care has been recognised in multiple priority-setting partnerships. The aim of this scoping review was to give an overview of the state of the evidence on implementation and dissemination of dementia care, and create a systematic evidence map. We sought studies that addressed dissemination and implementation strategies or described barriers and facilitators to implementation across dementia stages and care settings. Twelve databases were searched from inception to October 2015 followed by forward citation and grey literature searches. Quantitative studies with a comparative research design and qualitative studies with recognised methods of data collection were included. Titles, abstracts and full texts were screened independently by two reviewers with discrepancies resolved by a third where necessary. Data extraction was performed by one reviewer and checked by a second. Strategies were mapped according to the ERIC compilation. Eighty-eight studies were included (30 quantitative, 34 qualitative and 24 mixed-methods studies). Approximately 60% of studies reported implementation strategies to improve practice: training and education of professionals (94%), promotion of stakeholder interrelationships (69%) and evaluative strategies (46%) were common; financial strategies were rare (15%). Nearly 70% of studies reported barriers or facilitators of care practices primarily within residential care settings. Organisational factors, including time constraints and increased workload, were recurrent barriers, whereas leadership and managerial support were often reported to promote implementation. Less is known about implementation activities in primary care and hospital settings, or the views and experiences of people with dementia and their family caregivers. This scoping review and mapping of the evidence reveals a paucity of robust evidence to inform the successful dissemination and implementation of evidence-based dementia care. Further exploration of the most appropriate methods to evaluate and report initiatives to bring about change and of the effectiveness of implementation strategies is necessary if we are to make changes in practice that improve dementia care.

Aims and objectives: To systematically review and synthesise qualitative data from studies exploring the experiences of hospital staff who care for people living with dementia (Plwd).Background: In hospital, the number of Plwd continues to rise; however, their experiences of care remain problematic. Negative experiences of care are likely to contribute to poorer mental and physical health outcomes for Plwd while in hospital and after discharge. Experiences of the hospital staff who care for Plwd can also be poor or unrewarding. It is important to understand the experiences of staff in order to improve staff well‐being and ultimately the experience of care for Plwd while in hospital.Design: Systematic review and evidence synthesis of qualitative research.Data sources: We searched 16 electronic databases in March 2018 and completed forward and backward citation chasing.Methods: Eligible studies explored the experiences of paid and unpaid staff providing care in hospital for Plwd. Study selection was undertaken independently by two reviewers, and quality appraisal was conducted. We prioritised included studies according to richness of text, methodological rigour and conceptual contribution. We adopted approaches of meta‐ethnography to analyse study findings, creating a conceptual model to represent the line of argument.Findings: Forty‐five studies reported in 58 papers met the inclusion criteria, and of these, we prioritised 19 studies reported in 24 papers. The line of argument was that Institutions can improve staff experiences of care for Plwd by fostering person‐centred care (PCC). PCC aligned with staff perceptions of ‘good care’; however, staff often felt prevented from providing PCC because of care cultures that prioritised tasks, routines and physical health. Staff experienced conflict over the care they wanted to give versus the care they were able to give, and this caused moral distress. When staff were able to provide PCC, this increased experiences of job satisfaction and emotional well‐being.Conclusions: Person‐centred care not only has the potential to improve the experience of care for Plwd and their carers, but can also improve the experiences of hospital staff caring for Plwd. However, without institutional‐level changes, hospital staff are often unable to provide PCC even when they have the experience and knowledge to do so.Implications for practice: Institutional‐level areas for change include the following: training; performance indicators and ward cultures that prioritise psychological needs alongside physical needs; adequate staffing levels; inclusive approaches to carers; physical environments that promote familiarisation, social interaction and occupation; systems of documentation about individual needs of Plwd; and cultures of sharing knowledge across hierarchies.

INTRODUCTION: Experimental models are essential tools in neurodegenerative disease research. However, the translation of insights and drugs discovered in model systems has proven immensely challenging, marred by high failure rates in human clinical trials.METHODS: Here we review the application of artificial intelligence (AI) and machine learning (ML) in experimental medicine for dementia research.RESULTS: Considering the specific challenges of reproducibility and translation between other species or model systems and human biology in preclinical dementia research, we highlight best practices and resources that can be leveraged to quantify and evaluate translatability. We then evaluate how AI and ML approaches could be applied to enhance both cross‐model reproducibility and translation to human biology, while sustaining biological interpretability.DISCUSSION: AI and ML approaches in experimental medicine remain in their infancy. However, they have great potential to strengthen preclinical research and translation if based upon adequate, robust, and reproducible experimental data.Highlights: There are increasing applications of AI in experimental medicine. We identified issues in reproducibility, cross‐species translation, and data curation in the field. Our review highlights data resources and AI approaches as solutions. Multi‐omics analysis with AI offers exciting future possibilities in drug discovery.

Approximately two-thirds of hospital admissions are older adults and almost half of these are likely to have some form of dementia. People with dementia are not only at an increased risk of adverse outcomes once admitted, but the unfamiliar environment and routinised practices of the wards and acute care can be particularly challenging for them, heightening their confusion, agitation and distress further impacting the ability to optimise their care. It is well established that a person-centred care approach helps alleviate some of the unfamiliar stress but how to embed this in the acute-care setting remains a challenge. In this article, we highlight the challenges that have been recognised in this area and put forward a set of evidence-based ‘pointers for service change’ to help organisations in the delivery of person-centred care. The DEMENTIA CARE pointers cover areas of: dementia awareness and understanding, education and training, modelling of person-centred care by clinical leaders, adapting the environment, teamwork (not being alone), taking the time to ‘get to know’, information sharing, access to necessary resources, communication, involving family (ask family), raising the profile of dementia care, and engaging volunteers. The pointers extend previous guidance, by recognising the importance of ward cultures that prioritise dementia care and institutional support that actively seeks to raise the profile of dementia care. The pointers provide a range of simple to more complex actions or areas for hospitals to help implement person-centred care approaches; however, embedding them within the organisational cultures of hospitals is the next challenge.

Background: Being in hospital can be particularly confusing and challenging not only for people living with dementia, but also for their carers and the staff who care for them. Improving the experience of care for people living with dementia in hospital has been recognised as a priority. Objectives: To understand the experience of care in hospital for people living with dementia, their carers and the staff who care for them and to assess what we know about improving the experience of care. Review methods: We undertook three systematic reviews: (1) the experience of care in hospital, (2) the experience of interventions to improve care in hospital and (3) the effectiveness and cost-effectiveness of interventions to improve the experience of care. Reviews 1 and 2 sought primary qualitative studies and were analysed using meta-ethnography. Review 3 sought comparative studies and economic evaluations of interventions to improve experience of care. An interweaving approach to overarching synthesis was used to integrate the findings across the reviews. Data sources: Sixteen electronic databases were searched. Forwards and backwards citation chasing, author contact and grey literature searches were undertaken. Screening of title and abstracts and full texts was performed by two reviewers independently. A quality appraisal of all included studies was undertaken. Results: Sixty-three studies (reported in 82 papers) were included in review 1, 14 studies (reported in 16 papers) were included in review 2, and 25 studies (reported in 26 papers) were included in review 3. A synthesis of review 1 studies found that when staff were delivering more person-centred care, people living with dementia, carers and staff all experienced this as better care. The line of argument, which represents the conceptual findings as a whole, was that ‘a change of hospital culture is needed before person-centred care can become routine’. From reviews 2 and 3, there was some evidence of improvements in experience of care from activities, staff training, added capacity and inclusion of carers. In consultation with internal and external stakeholders, the findings from the three reviews and overarching synthesis were developed into 12 DEMENTIA CARE pointers for service change: key institutional and environmental practices and processes that could help improve experience of care for people living with dementia in hospital. Limitations: Few of the studies explored experience from the perspectives of people living with dementia. The measurement of experience of care across the studies was not consistent. Methodological variability and the small number of intervention studies limited the ability to draw conclusions on effectiveness. Conclusions: The evidence suggests that, to improve the experience of care in hospital for people living with dementia, a transformation of organisational and ward cultures is needed that supports person-centred care and values the status of dementia care. Changes need to cut across hierarchies and training systems to facilitate working patterns and interactions that enable both physical and emotional care of people living with dementia in hospital. Future research needs to identify how such changes can be implemented, and how they can be maintained in the long term. To do this, well-designed controlled studies with improved reporting of methods and intervention details to elevate the quality of available evidence and facilitate comparisons across different interventions are required. Study registration: This study is registered as PROSPERO CRD42018086013. Funding: This project was funded by the National Institute for Health Research (NIHR) Health Services and Delivery Research programme and will be published in full in Health Services and Delivery Research; Vol. 8, No. 43. See the NIHR Journals Library website for further project information. Additional funding was provided by the NIHR Collaboration for Leadership in Applied Health Research and Care South West Peninsula.