Browse through all publications from the Institute of Global Health Innovation, which our Patient Safety Translational Research Centre is part of. This feed includes reports and research papers from our Centre.
- Showing results for:
- Reset all filters
Journal articleBai W, Cursi F, Guo X, et al., 2022,
Journal articleLam K, Chen J, Wang Z, et al., 2022,
Accurate and objective performance assessment is essential for both trainees and certified surgeons. However, existing methods can be time consuming, labor intensive and subject to bias. Machine learning (ML) has the potential to provide rapid, automated and reproducible feedback without the need for expert reviewers. We aimed to systematically review the literature and determine the ML techniques used for technical surgical skill assessment and identify challenges and barriers in the field. A systematic literature search, in accordance with the PRISMA statement, was performed to identify studies detailing the use of ML for technical skill assessment in surgery. Of the 1896 studies that were retrieved, 66 studies were included. The most common ML methods used were Hidden Markov Models (HMM, 14/66), Support Vector Machines (SVM, 17/66) and Artificial Neural Networks (ANN, 17/66). 40/66 studies used kinematic data, 19/66 used video or image data, and 7/66 used both. Studies assessed performance of benchtop tasks (48/66), simulator tasks (10/66), and real-life surgery (8/66). Accuracy rates of over 80% were achieved, although tasks and participants varied between studies. Barriers to progress in the field included a focus on basic tasks, lack of standardization between studies, and lack of datasets. ML has the potential to produce accurate and objective surgical skill assessment through the use of methods including HMM, SVM, and ANN. Future ML-based assessment tools should move beyond the assessment ofbasic tasks and towards real-life surgery and provide interpretable feedback with clinical value for the surgeon.
Journal articleDanielli S, Donnelly P, Coffey T, et al., 2022,
It's official: The UK is in a recession. The economy has suffered its biggest slump on record with a drop in gross domestic product (GDP) of 20.4%. 1 This is going to have a significant impact on our health and well-being. It risks creating a spiralling decay as we know good health is not only a consequence, but also a condition for sustained and sustainable economic development. 2 In this way, the health of a nation creates a virtuous circle of improved health and improved economic prosperity. How we measure prosperity is therefore important and needs to be considered.
Journal articleO'Brien N, Shaw A, Flott K, et al., 2022,
Safety in fragile, conflict-affected, and vulnerable settings: An evidence scanning approach for identifying patient safety interventions, Journal of Global Health, Vol: 12, Pages: 1-10, ISSN: 2047-2978
BackgroundThe number of people living in fragile, conflict-affected, and vulnerable (FCV) settings is growing rapidly and attention to achieving universal health coverage must be accompanied by sufficient focus on the safety of care for universal access to be meaningful. Healthcare workers in these settings are working under extreme conditions, often with insufficient contextualized evidence to support decision-making. Recognising the relative paucity of, and methodological issues in gathering evidence from these settings, the evidence scanning described in this paper considered which patient safety interventions might offer the ‘better bet’, e.g., the most effective and appropriate intervention in FCV settings.MethodsAn evidence scanning approach was used to examine the literature. The search was limited to FCV settings and low-income settings as defined by the World Bank, but if a systematic review included a mix of evidence from FCV/low income settings, as well as low-middle income settings, it was included. The search was conducted in English and limited to studies published from 2003 onwards, utilising Google Scholar as a publicly accessible database and further review of the grey literature, with specific attention to the outputs of non-governmental organisations. The search and subsequent analysis were completed between April and June 2020.FindingsThe majority of studies identified related to strengthening infection prevention and control which was also found to be the ‘better bet’ intervention that could generalise to other settings, be most feasible to implement, and most effective for improving patient care and associated outcomes. Other prioritized interventions include risk management, with contributing elements such as reporting, audits, and death review processes.ConclusionsInfection prevention and control interventions dominate in the literature for multiple reasons including strength of evidence, acceptability, feasibility, an
Journal articleO'Brien N, Flott K, Bray O, et al., 2022,
Implementation of initiatives designed to improve healthcare worker health and wellbeing during the COVID-19 pandemic: comparative case studies from 13 healthcare provider organisations globally, Globalization and Health, Vol: 18, ISSN: 1744-8603
Background: Healthcare workers are at a disproportionate risk of contracting COVID-19. The physical and mental repercussions of such risk have an impact on the wellbeing of healthcare workers around the world. Healthcare workers are the foundation of all well-functioning health systems capable of responding to the ongoing pandemic; initiatives to address and reduce such risk are critical. Since the onset of the pandemic healthcare organizations have embarked on the implementation of a range of initiatives designed to improve healthcare worker health and wellbeing. Methods: Through a qualitative collective case study approach where participants responded to a longform survey, the facilitators, and barriers to implementing such initiatives were explored, offering global insights into the challenges faced at the organizational level. 13 healthcare organizations were surveyed across 13 countries. Of these 13 participants, 5 subsequently provided missing information through longform interviews or written clarifications.Results: 13 case studies were received from healthcare provider organizations. Mental health initiatives were the most commonly described health and wellbeing initiatives among respondents. Physical health and health and safety focused initiatives, such as the adaption of workspaces, were also described. Strong institutional level direction, including engaged leadership, and the input, feedback, and engagement of frontline staff were the two main facilitators in implementing initiatives. The most common barrier to implementation, noted largely by organizations who discussed infection prevention and control initiatives, was inadequate personal protective equipment and supply chain disruption. Conclusions: Common themes emerge globally in exploring the enablers and barriers to implementing initiatives to improve healthcare workers health and wellbeing through the COVID-19 pandemic. Consideration of the themes outlined in the paper by healthcare organizations
Journal articleElliott P, Bodinier B, Eales O, et al., 2022,
The unprecedented rise in SARS-CoV-2 infections during December 2021 was concurrent with rapid spread of the Omicron variant in England and globally. We analyzed prevalence of SARS-CoV-2 and its dynamics in England from end November to mid-December 2021 among almost 100,000 participants from the REACT-1 study. Prevalence was high with rapid growth nationally and particularly in London during December 2021, and an increasing proportion of infections due to Omicron. We observed large falls in swab positivity among mostly vaccinated older children (12-17 years) compared with unvaccinated younger children (5-11 years), and in adults who received a third (booster) vaccine dose vs. two doses. Our results reinforce the importance of vaccination and booster campaigns, although additional measures have been needed to control the rapid growth of the Omicron variant.
Journal articleKhanbhai M, Symons J, Flott K, et al., 2022,
Enriching the value of patient experience feedback: interactive dashboard development using co-design and heuristic evaluation, JMIR Human Factors, Vol: 9, Pages: 1-14, ISSN: 2292-9495
Background:There is an abundance of patient experience data held within healthcare organisations but stakeholders and staff are often unable to use the output in a meaningful and timely way to improve care delivery. Dashboards, which use visualised data to summarise key patient experience feedback, have the potential to address these issues.Objective:The aim of this study was to develop a patient experience dashboard with an emphasis on FFT reporting as per the national policy drive. An iterative process involving co-design involving key stakeholders was used to develop the dashboard, followed by heuristic usability testing.Methods:A two staged approach was employed; participatory co-design involving 20 co-designers to develop a dashboard prototype followed by iterative dashboard testing. Language analysis was performed on free-text patient experience data from the Friends and Family Test (FFT) and the themes and sentiment generated was used to populate the dashboard with associated FFT metrics. Heuristic evaluation and usability testing were conducted to refine the dashboard and assess user satisfaction using the system usability score (SUS).Results:Qualitative analysis from the co-design process informed development of the dashboard prototype with key dashboard requirements and a significant preference for bubble chart display. Heuristic evaluation revelated the majority of cumulative scores had no usability problem (n=18), cosmetic problem only (n=7), or minor usability problem (n= 5). Mean SUS was 89.7 (SD 7.9) suggesting an excellent rating.Conclusions:The growing capacity to collect and process patient experience data suggests that data visualisation will be increasingly important in turning the feedback into improvements to care. Through heuristic usability we demonstrated that very large FFT data can be presented into a thematically driven, simple visual display without loss of the nuances and still allow for exploration of the original free-text comments. T
Journal articleSounderajah V, 2022,
Quality assessment standards in artificial intelligence diagnostic accuracy systematic reviews: a meta-research study, npj Digital Medicine, Vol: 5, Pages: 1-13, ISSN: 2398-6352
Artificial intelligence (AI) centred diagnostic systems are increasingly recognized as robust solutions in healthcare delivery pathways. In turn, there has been a concurrent rise in secondary research studies regarding these technologies in order to influence key clinical and policymaking decisions. It is therefore essential that these studies accurately appraise methodological quality and risk of bias within shortlisted trials and reports. In order to assess whether this critical step is performed, we undertook a meta-research study evaluating adherence to the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool within AI diagnostic accuracy systematic reviews. A literature search was conducted on all studies published from 2000 to December 2020. Of 50 included reviews, 36 performed quality assessment, of which 27 utilised the QUADAS-2 tool. Bias was reported across all four domains of QUADAS-2. 243 of 423 studies (57.5%) across all systematic reviews utilising QUADAS-2 reported a high or unclear risk of bias in the patient selection domain, 110 (26%) reported a high or unclear risk of bias in the index test domain, 121 (28.6%) in the reference standard domain and 157 (37.1%) in the flow and timing domain. This study demonstrates incomplete uptake of quality assessment tools in reviews of AI-based diagnostic accuracy studies and highlights inconsistent reporting across all domains of quality assessment. Poor standards of reporting act as barriers to clinical implementation. The creation of an AI specific extension for quality assessment tools of diagnostic accuracy AI studies may facilitate the safe translation of AI tools into clinical practice.
Journal articlevan Dael J, Smalley K, Gillespie A, et al., 2022,
Objective: It is increasingly recognized that patient safety requires heterogeneous insights from a range of stakeholders, yet incident reporting systems in health care still primarily rely on staff perspectives. This paper examines the potential of combining insights from patient complaints and staff incident reports for a more comprehensive understanding of the causes and severity of harm. Methods: Using five years of patient complaints and staff incident reporting data at a large multi-site hospital in London (in the United Kingdom), this study conducted retrospective patient-level data linkage to identify overlapping reports. Using a combination of quantitative coding and in-depth qualitative analysis, we then compared level of harm reported, identified descriptions of adjacent events missed by the other party and examined combined narratives of mutually identified events. Results: Incidents where complaints and incident reports overlapped (n=446, 8.5% of all complaints and 0.6% of all incident reports) represented a small but critical area of investigation, with significantly higher rates of Serious Incidents and severe harm. Linked complaints described greater harm from safety incidents in 60% of cases, reported many surrounding safety events missed by staff (n=582), and provided contesting stories of why problems occurred in 46% cases, and complementary accounts in 26% cases.Conclusions: This study demonstrates the value of using patient complaints to supplement, test, and challenge staff reports, including to provide greater insight on the many potential factors that may give rise to unsafe care. Accordingly, we propose that a more holistic analysis of critical safety incidents can be achieved through combining heterogeneous data from different viewpoints, such as better integration of patient complaints and staff incident reporting data.
Journal articleKhanbhai M, Warren L, Symons J, et al., 2022,
Using natural language processing to understand, facilitate and maintain continuity in patient experience across transitions of care, International Journal of Medical Informatics, Vol: 157, Pages: 1-7, ISSN: 1386-5056
BackgroundPatient centred care necessitates that healthcare experiences and perceived outcomes be considered across all transitions of care. Information encoded within free-text patient experience comments relating to transitions of care are not captured in a systematic way due to the manual resource required. We demonstrate the use of natural language processing (NLP) to extract meaningful information from the Friends and Family Test (FFT).MethodsFree-text fields identifying favourable service (“What did we do well?”) and areas requiring improvement (“What could we do better?”) were extracted from 69,285 FFT reports across four care settings at a secondary care National Health Service (NHS) hospital. Sentiment and patient experience themes were coded by three independent coders to produce a training dataset. The textual data was standardised with a series of pre-processing techniques and the performance of six machine learning (ML) models was obtained. The best performing ML model was applied to predict the themes and sentiment from the remaining reports. Comments relating to transitions of care were extracted, categorised by sentiment, and care setting to identify the most frequent words/combinations presented as tri-grams and word clouds.ResultsThe support vector machine (SVM) ML model produced the highest accuracy in predicting themes and sentiment. The most frequent single words relating to transition and continuity with a negative sentiment were “discharge” in inpatients and Accident and Emergency, “appointment” in outpatients, and “home’ in maternity. Tri-grams identified from the negative sentiments such as ‘seeing different doctor’, ‘information aftercare lacking’, ‘improve discharge process’ and ‘timing discharge letter’ have highlighted some of the problems with care transitions. None of this information was available from the quantitative data.Conc
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.