scholarly journals Improving palliative and end-of-life care with machine learning and routine data: a rapid review

2019 ◽  
Vol 2 ◽  
pp. 13 ◽  
Author(s):  
Virginia Storick ◽  
Aoife O’Herlihy ◽  
Sarah Abdelhafeez ◽  
Rakesh Ahmed ◽  
Peter May

Introduction: Improving end-of-life (EOL) care is a priority worldwide as this population experiences poor outcomes and accounts disproportionately for costs. In clinical practice, physician judgement is the core method of identifying EOL care needs but has important limitations. Machine learning (ML) is a subset of artificial intelligence advancing capacity to identify patterns and make predictions using large datasets.  ML approaches have the potential to improve clinical decision-making and policy design, but there has been no systematic assembly of current evidence. Methods: We conducted a rapid review, searching systematically seven databases from inception to December 31st, 2018: EMBASE, MEDLINE, Cochrane Library, PsycINFO, WOS, SCOPUS and ECONLIT.  We included peer-reviewed studies that used ML approaches on routine data to improve palliative and EOL care for adults.  Our specified outcomes were survival, quality of life (QoL), place of death, costs, and receipt of high-intensity treatment near end of life.  We did not search grey literature and excluded material that was not a peer-reviewed article. Results: The database search identified 426 citations. We discarded 162 duplicates and screened 264 unique title/abstracts, of which 22 were forwarded for full text review.  Three papers were included, 18 papers were excluded and one full text was sought but unobtainable.  One paper predicted six-month mortality, one paper predicted 12-month mortality and one paper cross-referenced predicted 12-month mortality with healthcare spending.  ML-informed models outperformed logistic regression in predicting mortality but poor prognosis is a weak driver of costs.  Models using only routine administrative data had limited benefit from ML methods. Conclusion: While ML can in principle help to identify those at risk of adverse outcomes and inappropriate treatment near EOL, applications to policy and practice are formative.  Future research must not only expand scope to other outcomes and longer timeframes, but also engage with individual preferences and ethical challenges.

2019 ◽  
Vol 2 ◽  
pp. 13 ◽  
Author(s):  
Virginia Storick ◽  
Aoife O’Herlihy ◽  
Sarah Abdelhafeez ◽  
Rakesh Ahmed ◽  
Peter May

Introduction: Improving palliative care is a priority worldwide as this population experiences poor outcomes and accounts disproportionately for costs. In clinical practice, physician judgement is the core method of identifying palliative care needs but has important limitations. Machine learning (ML) is a subset of artificial intelligence advancing capacity to identify patterns and make predictions using large datasets.  ML has the potential to improve clinical decision-making and policy design, but there has been no systematic assembly of current evidence. Methods: We conducted a rapid review, searching systematically seven databases from inception to December 31st, 2018: EMBASE, MEDLINE, Cochrane Library, PsycINFO, WOS, SCOPUS and ECONLIT.  We included peer-reviewed studies that used ML approaches on routine data to improve palliative care for adults.  Our specified outcomes were survival, quality of life (QoL), place of death, costs, and receipt of high-intensity treatment near end of life.  We did not search grey literature. Results: The database search identified 426 citations. We discarded 162 duplicates and screened 264 unique title/abstracts, of which 22 were forwarded for full text review.  Three papers were included, 18 papers were excluded and one full text was sought but unobtainable.  One paper predicted six-month mortality, one paper predicted 12-month mortality and one paper cross-referenced predicted 12-month mortality with healthcare spending.  ML-informed models outperformed logistic regression in predicting mortality where data inputs were relatively strong, but those using only basic administrative data had limited benefit from ML.  Identifying poor prognosis does not appear effective in tackling high costs associated with serious illness.  Conclusion: While ML can in principle help to identify those at risk of adverse outcomes and inappropriate treatment, applications to policy and practice are formative.  Future research must not only expand scope to other outcomes and longer timeframes, but also engage with individual preferences and ethical challenges.


2020 ◽  
Vol 9 (1) ◽  
Author(s):  
Patricia Rios ◽  
Amruta Radhakrishnan ◽  
Chantal Williams ◽  
Naveeta Ramkissoon ◽  
Ba’ Pham ◽  
...  

Abstract Background The objective of this review was to examine the current guidelines for infection prevention and control (IPAC) of coronavirus disease-19 (COVID-19) or other coronaviruses in adults 60 years or older living in long-term care facilities (LTCF). Methods EMBASE, MEDLINE, Cochrane library, pre-print servers, clinical trial registries, and relevant grey literature sources were searched until July 31, 2020, using database searching and an automated method called Continuous Active Learning® (CAL®). All search results were processed using CAL® to identify the most likely relevant citations that were then screened by a single human reviewer. Full-text screening, data abstraction, and quality appraisal were completed by a single reviewer and verified by a second. Results Nine clinical practice guidelines (CPGs) were included. The most common recommendation in the CPGs was establishing surveillance and monitoring systems followed by mandating the use of PPE; physically distancing or cohorting residents; environmental cleaning and disinfection; promoting hand and respiratory hygiene among residents, staff, and visitors; and providing sick leave compensation for staff. Conclusions Current evidence suggests robust surveillance and monitoring along with support for IPAC initiatives are key to preventing the spread of COVID-19 in LTCF. However, there are significant gaps in the current recommendations especially with regard to the movement of staff between LTCF and their role as possible transmission vectors. Systematic review registration PROSPERO CRD42020181993


2021 ◽  
pp. 1-13
Author(s):  
Shih-Chun Lin ◽  
Mei-Chih Huang ◽  
Deni Yasmara ◽  
Huey-Lan Wuu

Abstract Objective To determine the impact of palliative care (PC) on end-of-life (EoL) care and the place of death (PoD) in children, adolescents, and young adults with life-limiting conditions. Method Eight online databases (PubMed, Medline, EMBASE, Cochrane Library, CINAHL, Airiti, GARUDA Garba Rujukan Digital, and OpenGrey) from 2010 to February 5, 2020 were searched for studies investigating EoL care and the PoD for pediatric patients receiving and not receiving PC. Results Of the 6,468 citations identified, 14 cohort studies and one case series were included. An evidence base of mainly adequate- and strong-quality studies shows that inpatient hospital PC, either with or without the provision of home and community PC, was found to be associated with a decrease in intensive care use and high-intensity EoL care. Conflicting evidence was found for the association between PC and hospital admissions, length of stay in hospital, resuscitation at the time of death, and the proportion of hospital and home deaths. Significance of results Current evidence suggests that specialist, multidisciplinary involvement, and continuity of PC are required to reduce the intensity of EoL care. Careful attention should be paid to the need for a longer length of stay in a medical setting late in life, and earlier EoL care discussion should take place with patients/caregivers, especially in regard to attempting resuscitation in toddlers, adolescents, and the young adult population. A lack of robust evidence has identified a gap in rigorous multisite prospective studies utilizing data collection.


BMJ Open ◽  
2019 ◽  
Vol 9 (11) ◽  
pp. e032070
Author(s):  
Garrett Scott Bullock ◽  
Nirmala K Panagodage-Perera ◽  
Andrew Murray ◽  
Nigel K Arden ◽  
Stephanie R Filbay

IntroductionCricket is a popular sport played by 2.5 billion people of all ages and abilities. However, cricket participation is decreasing in the UK, despite an increased focus of governments on increasing sport participation to enhance public health. Understanding the health benefits and mitigating the health risks of cricket participation may help cricket organisations promote cricket participation while optimising the long-term health of cricket participants. Currently, there is no literature review on the relationship between cricket participation, health and well-being; thus, this relationship remains unclear. Therefore, the aims of this scoping review were (1) to investigate the relationship between cricket participation, health and well-being and (ii) to identify the research gaps related to cricket, health and well-being.Methods and analysisDue to the broad nature of our research question and the large number of health outcomes assessed within the cricket literature and to facilitate identification of research gaps, a scoping review methodology was used. The methodology of this paper was informed by previous scoping review protocols and best practice methodological frameworks. MEDLINE, CINAHL, Embase, Scopus, PsycINFO, SPORTDiscus, Cochrane Library, EBSCO, Web of Science and PEDro and grey literature sources (Google Scholar, ClinicalTrials.gov, ISRCTN Registry and ProQuest) will be systematically searched. Studies that assess a construct related to health and/or well-being in current and/or former cricketers from all ages and standards of play will be eligible. Two reviewers will independently screen full texts of identified studies for eligibility and will perform data extraction. Results will be presented in tabular and graphical forms and will be reported descriptively.Ethics and disseminationThis research is exempt from ethics approval due to the data being available through published and public available resources. Results will be published in a peer-reviewed sports and exercise medicine journal regardless of positive or negative findings. In addition, results will be disseminated through multiple platforms, including conference presentations and social media using multimedia resources (eg, infographics, animations, videos, podcasts and blogs), to engage stakeholder groups, including cricketers, cricket coaches, sporting bodies, sports medicine professionals and policy makers. There findings will inform clinical decision making, policy changes and future research agendas.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Aimee O'Farrell ◽  
Geoff McCombe ◽  
John Broughan ◽  
Áine Carroll ◽  
Mary Casey ◽  
...  

PurposeIn many healthcare systems, health policy has committed to delivering an integrated model of care to address the increasing burden of disease. The interface between primary and secondary care has been identified as a problem area. This paper aims to undertake a scoping review to gain a deeper understanding of the markers of integration across the primary–secondary interface.Design/methodology/approachA search was conducted of PubMed, SCOPUS, Cochrane Library and the grey literature for papers published in English using the framework described by Arksey and O'Malley. The search process was guided by the “Preferred Reporting Items for Systematic Reviews and Meta-Analyses” (PRISMA).FindingsThe initial database search identified 112 articles, which were screened by title and abstract. A total of 26 articles were selected for full-text review, after which nine articles were excluded as they were not relevant to the research question or the full text was not available. In total, 17 studies were included in the review. A range of study designs were identified including a systematic review (n = 3), mixed methods study (n = 5), qualitative (n = 6) and quantitative (n = 3). The included studies documented integration across the primary–secondary interface; integration measurement and factors affecting care coordination.Originality/valueMany studies examine individual aspects of integration. However, this study is unique as it provides a comprehensive overview of the many perspectives and methodological approaches involved with evaluating integration within the primary–secondary care interface and primary care itself. Further research is required to establish valid reliable tools for measurement and implementation.


Hypertension ◽  
2020 ◽  
Vol 76 (Suppl_1) ◽  
Author(s):  
Irina Benenson ◽  
Frederick Waldron

Background: Hypertensive emergency (HTNE) is a subtype of hypertensive crisis. In contrast to hypertensive urgency (HTNU), which is a severely elevated BP without acute target organ damage (TOD), HTNE presents with the equally high BP in the presence of potentially life-threatening acute TOD such as myocardial infarction, stroke, pulmonary edema and acute kidney injury. Knowledge on risk factors of HTNE may be used in clinical decision-making to differentiate between HTNE and HTNU in patients presenting with markedly high BP. Method: A search of 4 databases (MEDLINE, Cochrane Database of Systematic Reviews, Web of Science, and CINAHL), 7 grey literature sites and relevant organizational websites revealed 11,387 titles. After duplicates were removed, 9,183 studies were screened by the title and abstract for eligibility. Forty full-text articles were retrieved, and each was assessed for eligibility. Fourteen full-text studies that included 10,376 participants were critically appraised and included in this review. The extracted data were pooled to meta-analysis, where HTNU patients (BP ≥180/110 mmHg without acute TOD) were compared to HTNE patients (BP ≥180/110 mmHg with acute TOD) based on several modifiable and non-modifiable risk factors. Results: Patients with HTNE had higher mean systolic (MD 2.413, 95% CI 0.477,4.350) and diastolic BP (MD 2.043, 95% CI 0.624,3.461) compared to patients with HTNU. HTNE were more common in men (OR 1.390, 95% CI 1.207,1.601), older patients (mean diff 5.282, 95% CI 3.229, 7.335). Diabetes (OR 1.723, 95% CI 1.485, 2.000), hyperlipidemia (OR 2.028, 95% CI 1.642, 2.505), and chronic kidney disease (OR 2.448, 95% CI 1.169, 5.124) increased the risk of HTNE. Non-adherence to antihypertensives (OR 0.939, 95% CI 0.647,1.363) and HTN diagnosis unawareness (OR 0.807, 95% CI 0.564, 1.154) did not change the odds of HTNE. Conclusion: Systolic and diastolic BP are marginally higher in patients with HTNE compared to patients with HTNU. Since these differences are small and not clinically significant, clinicians should rely on other symptoms and signs to differentiate between HTNU and HTNE. Measures to prevent and treat cardiometabolic comorbidities should be implemented in order to mitigate the risk of HTNE.


2015 ◽  
Vol 2 (2) ◽  
pp. 119-129 ◽  
Author(s):  
Jennifer Anette Apolinario-Hagen ◽  
Siegfried Tasseit

Abstract Background: Currently, the debate on regional and socio-structurally related treatment gaps in psychotherapeutic care increases the interest in e-mental health interventions such as the Internet-based psychotherapy, online self-help and new approaches for self-empowerment. Thus, health professionals could support informed decision-making by knowing the latest developments. However, if the ‘digital revolution’ fails to reach patients not familiar with Web 2.0, access to psychotherapies is unlikely to improve. Therefore, the objective of this review is to clarify whether online therapies should be recommended as an effective alternative to conventional psychotherapy in primary care.Methods: To investigate the research evidence of online therapies in adults within the last decade (2004-2014), a rapid review of literature was conducted by using electronic databases (i.e. Medline/PubMed, PubMed Central, Cochrane Library) to find systematic reviews, meta-analysis and clinical trials. Furthermore, a hand search in journals and grey literature was undertaken.Results: A search in PubMed for clinical trials on ‘online psychotherapy’ resulted in a total number of 245 publications. So, eight reviews and several clinical trials were chosen. Overall, mostly positive findings on the effectiveness and acceptance of online psychotherapy, primarily in the treatment of depression and anxiety disorders, were identified.Discussion: In sum, Internet-based psychotherapies have been effective in reducing symptoms of mood and anxiety disorders in clinical trials. However, due to the limited range of treatable disorders and non-representative samples (young female college graduates), external validity remains insufficient. Thus, further research is needed to determine if online therapies will be capable of improving access to psychotherapy.


2020 ◽  
Vol 5 (2) ◽  
pp. 26-33
Author(s):  
Alison Rae ◽  
Simon Robinson

Introduction: The development of safe, competent and capable paramedics is one of the key concerns of education providers or Higher Education Institutions (HEIs). To achieve this, paramedic programmes need to focus on teaching leadership to students. The aim of this literature review was to identify the current leadership development opportunities for paramedic students during their undergraduate training across the United Kingdom, in order to identify current gaps and make suggestions on how HEIs could increase leadership opportunities for student paramedics.Methods: During August 2018, the Scopus, Medline, CINAHL and Academic Search Premier databases were searched (the last three accessed via EBSCOhost). Grey literature was also manually reviewed. Both authors screened the title and abstract and agreed on final papers eligible for full-text review. CASP and COREQ checklists were used to assist in critically appraising the quality of the research and to help decide on the papers chosen for inclusion.Results: The search yielded 511 results (455 after duplicates were removed). The grey literature search also yielded one additional document that incorporated a framework based on primary research integrated within the paper itself. After title and abstract review, seven papers were included for full text critical review. Two papers were then excluded, resulting in a total of five papers being included in the review.Conclusion: Current evidence, although limited, demonstrates the benefit of educational programmes in developing educational and non-educational leadership opportunities for paramedic students. Moreover, there is value to individuals being provided or seeking extra-curricular activities, and students should be encouraged to engage in societies, the College of Paramedics, events and conferences, and to work or volunteer in healthcare or emergency service-related sectors to further enhance their leadership potential and skills.


Author(s):  
Nan Yang ◽  
Siyi Che ◽  
Jingyi Zhang ◽  
Xia Wang ◽  
Yuyi Tang ◽  
...  

AbstractBackgroundExisting recommendations on whether mothers with COVID-19 should continue breastfeeding are still conflicting. We aimed to conduct a rapid review of mother-to-child transmission of COVID-19 during breastfeeding.MethodsWe systematically searched Medline, Embase, Web of Science, Cochrane library, China Biology Medicine disc, China National Knowledge Infrastructure, Wanfang, and preprint articles up to March 2020. We included studies relevant to transmission through milk and respiratory droplets during breastfeeding of mothers with COVID-19, SARS, MERS and influenza. Two reviewers independently screened studies for eligibility, extracted data, assessed risk of bias and used GRADE to assess certainty of evidence.ResultsA total of 4481 records were identified in our literature search. Six studies (five case reports and one case series) involving 58 mothers (16 mothers with COVID-19, 42 mothers with influenza) and their infants proved eligible. Five case reports showed that the viral nucleic acid tests for all thirteen collected samples of breast milk from mothers with COVID-19 were negative. A case series of 42 influenza infected postpartum mothers taking precautions (hand hygiene and wearing masks) before breastfeeding showed that no neonates were infected with influenza during one-month of follow-up.ConclusionsThe current evidence indicates that SARS-CoV-2 viral nucleic acid has not been detected in breast milk. The benefits of breastfeeding may outweigh the risk of SARS-CoV-2 infection in infants. Mothers with COVID-19 should take appropriate precautions to reduce the risk of transmission via droplets and close contact during breastfeeding.


2021 ◽  
pp. 20210340
Author(s):  
Fernando de Oliveira Andriola ◽  
Orion Luiz Haas Junior ◽  
Raquel Guijarro-Martínez ◽  
Federico Hernández-Alfaro ◽  
Rogério Belle de Oliveira ◽  
...  

Objectives: A systematic review was performed to analyze the current evidence on three-dimensional (3D) computed tomography (CT) superimposition protocols used to assess dentomaxillofacial changes after orthognathic and orthofacial surgery. Accuracy, reproducibility, and efficiency were evaluated. Methods: The search was divided into Main Search (PubMed, EMBASE, Cochrane Library, LILACS, and SciELO), Grey Literature search (Google Scholar and Open Grey), and Manual search. Thirteen studies were included. Of these, 10 reported data on accuracy, 10 on reproducibility and five on efficiency. Seven proposed or evaluated methods of voxel-based superimposition, three focused on the surface-based technique, one compared surface- and voxel-based superimposition protocols, one used the maximum mutual information algorithm, and one described a landmark-based superimposition method. Cone-beam computed tomography (CBCT) was the most common imaging technique, being used in 10 studies. Results: The accuracy of most methods was high, showing mean differences smaller than voxels’ dimensions, ranging between 0.05 and 1.76 mm for translational accuracy, and 0.10–1.09° for rotational accuracy. The overall reproducibility was considered good as demonstrated by the small mean error (range: 0.01–0.26 mm) and high correlation coefficients (range: 0.53–1.00). Timing to complete virtual superimposition techniques ranged between a few seconds up to 40 min. Conclusions: Voxel-based superimposition protocols presented the highest accuracy and reproducibility. Moreover, superimposition protocols that used automated processes and involved only one software were the most efficient.


Sign in / Sign up

Export Citation Format

Share Document