The following lists palliative care research primarily conducted by Australian research groups. The list is based on application of the CareSearch search filter for palliative care to identify articles held within the PubMed database and corresponding to the strongest evidence. Articles have been selected based on relevance and new articles are added on a weekly basis.
Whilst not an exhaustive list, the aim is to keep the community informed by providing a snapshot of recent research findings and planned studies in the Australian setting.
Bakhtary M, Sharma P, Raspin S, Vemuri S, McCarthy M.
Abstract: Children with non-curative brain tumors have a predictable and burdensome neurological decline. Care provision for these children falls in the gap where the acute inpatient services intersect with community-based providers. These children commonly receive care in the community; however, their neurological decline often outpaces engagement with community-based providers. Children with non-curative brain tumors are commonly referred to specialist palliative care services and need timely availability and access to this support. The purpose of this scoping review was to explore the evidence related to standards, guidelines, and models of palliative care provision for children with non-curative brain tumors, and to examine the facilitators and barriers to the implementation of, and access to, these services. Using a narrative synthesis method, a scoping review was conducted according to the Joanna Briggs Institute methodology using six electronic databases (Medline, Embase, Web of Science, Pubmed, CINAHL, and Cochrane Database of Systematic Reviews) from January 2013 to May 2023. A total of 2404 studies were screened for eligibility and 31 were selected for data extraction. There are no international models or standards of care for providing palliative care for children with non-curative brain tumors. Instead, palliative care is delivered at an institutional level, potentially leading to variability in the care that is provided. This variability can threaten the quality of life of these children and their families. Variability in care provision could be minimized by development of standardized palliative care provision. Any proposed standard for palliative care provision for children with non-curative brain tumors should include early integration of palliative care, and allocation of resources to enable training to operationalize referrals to palliative care teams and multidisciplinary care provision across settings, especially home-based care.
Migiddorj B, Batterham M, Win KT.
Background: As machine learning models become increasingly prevalent in palliative care, explainability has become a critical factor in their successful deployment in this sensitive field, where decisions can profoundly impact patient health and quality of life. To address these concerns, Explainable AI (XAI) aims to make complex AI models more understandable and trustworthy.
Objective: This study aims to assess the current state of machine learning models in palliative care, specifically focusing on their compliance with the principles of XAI.
Methods: A comprehensive literature search in four databases was conducted to identify articles on machine learning in palliative care studies published until May 2024, followed by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guideline. The Checklist for Assessment of Medical Artificial Intelligence was used to evaluate the quality of the studies.
Results: Mortality and survival prediction were the primary focus areas in 15 (54%) of the included 28 studies. Regarding data explainability, 20 studies (71%) documented their data preprocessing methods. However, a notable concern is that 45% of the studies did not address handling missing data. Across these studies, 74 machine learning algorithms were employed. Complex models, including Random Forest, Support Vector Machines, Gradient Boosting Machines, and Deep Neural Networks, were predominantly used (64%) due to their high predictive power, achieving AUC values between 0.82 and 0.96. Post-hoc explanation techniques were applied in only 11 studies, using seven different XAI techniques, focusing on global explanations to enhance understanding of model behavior.
Conclusion: Given the critical role of AI-driven decisions in patient care, adopting XAI techniques is essential for fostering trust and usability. Although progress has been made, significant gaps persist. A main challenge remains the trade-off between model performance and interpretability, as highly accurate models often lack the transparency required to build trust in clinical settings. Additionally, complex models frequently provide inadequate explanations for their outputs, lack consistent documentation, and have limited XAI applications, reducing the interpretability of machine learning studies for clinicians and decision-makers.
Sivanathan V, Smallwood N, Zentner D.
Background: Women with chronic heart failure (CHF) experience an increased symptom burden, activity impairment and frailty. Although receiving palliative care services has been shown to improve the quality of life of people with CHF, few patients access this in a timely manner.
Aim: Explore whether there were differences in either referral to specialist palliative care or provision of elements of palliative care to women and men with CHF during their terminal admission in Australia.
Methods: This is a retrospective review of medical records for all admissions resulting in death from chronic heart failure (July 2011 to December 2019).
Results: The cohort (n = 439) was elderly (median age 83.7 years, IQR = 77.6-88.7) and composed of 199 (45.1%) women. There was no association between sex and receiving an inpatient referral to specialist palliative care (P = 0.80). Women were less likely to receive life-sustaining interventions (intubation, inotropes, resuscitation, ICU stay) (odds ratio [OR] = 1.71, 1.04-2.83; P = 0.04) compared to men. Women were more likely to receive terminal symptom-related management (opioids or benzodiazepines) (OR = 3.19, 1.54-6.63; P = 0.01) or a palliative approach (OR = 1.68, 1.14-2.45; P < 0.01). Women were less likely to present to the emergency department (OR = 0.50, 0.31-0.79; P = 0.04) or be referred to an outpatient chronic disease programme (OR = 0.58, 0.34-0.98; P = 0.04) in the 12 months prior to death compared to men.
Conclusion: Given accepted differences in the timeliness of cardiac care for women, the apparent finding of better end-of-life care for women is intriguing and merits further research.
Gallop M, Ford J, Bowman A, Mullen A, Schwebel D, Johnson A, et al.
Aim: To explore current evidence regarding the provision of palliative care for individuals with very severe to extreme behavioural and psychological symptoms of dementia (BPSD) in a hospital setting.
Design: Scoping review.
Reporting method: The PRISMA-ScR reporting guideline.
Methods: The JBI guidelines for scoping reviews were followed. A data extraction form assisted in the identification of key findings via a process of content analysis.
Data sources: Studies were obtained from bibliographic databases of PubMed, CINAHL, and PsycINFO.
Results: This review included six articles, and nine categories emerged from the findings. Symptom assessment and management, pain assessment challenges, atypical presentation of end-stage dementia, complex prescribing and treatment practices, principles of person-centred care, collaboration; training for health care professionals; emotional impact on staff; and family and caregivers.
Conclusions: This scoping review highlighted a significant gap in the literature regarding palliative care for people living with very severe to extreme BPSD in hospital settings. This review highlighted key differences in the presentation of people with BPSD needing palliative care. There is a need for tailored models of care, specialised training and education for health professionals, families, and carers, and recognition of dementia as a terminal illness.
Gebresillassie BM, Attia J, Cavenagh D, Harris ML.
Background: Accurately estimating one-year mortality risk in older women with dementia can inform clinical decision-making, facilitate timely advanced care planning, and optimise palliative care delivery. This study aimed to develop, validate, and assess the clinical utility of a prediction model for one-year all-cause mortality in this population using a nationally representative Australian cohort.
Methods: This prognostic study utilised data from the 1921-26 cohort of the nationally representative, population-based Australian Longitudinal Study on Women's Health (ALSWH) and linked national and state-based administrative health records. Candidate predictors were identified through a systematic review and expert consultation, then refined using a data-driven statistical approach. A multivariable binary logistic regression model was developed and validated to predict one-year all-cause mortality.
Results: The analysis included 1576 older women with dementia (mean age, 72.6 ± 1.5 years). The model demonstrated good discrimination (AUC: 75.1 %, 95 % CI: 72.7 %-77.5 %) and excellent calibration (slope = 1.00, 95 % CI: 0.87-1.13; intercept = 0.00, 95 % CI: 0.11 - 0.11). Model validation using both 10-fold cross-validation and 1000 bootstrap iterations showed minimal optimism in its predictive performance, with AUC optimism of 0.0047 and 0.0042, respectively. Decision curve analysis indicated a net benefit across probability thresholds from 0.24 to 0.88, supporting the model's clinical utility for guiding palliative care decisions.
Conclusion: This prediction model, incorporating readily available predictors, demonstrated compelling performance and clinical utility for identifying older women with dementia at high risk of one-year mortality. The model has the potential to facilitate timely palliative care interventions and is publicly accessible via a web-based calculator. Further external validation in diverse populations and healthcare settings is warranted to confirm its generalisability.
Last updated 30 April 2024