38 research outputs found
Usage of allergy codes in primary care electronic health records: a national evaluation in Scotland
Full text linkBackground: The UK's NHS intends to move from the current Read code system to the international, detailed Systematized Nomenclature of Medicine Clinical Terms (SNOMED-CT) to facilitate more clinically appropriate coding of conditions and associated risk factors and outcomes. Given concerns about coding behaviour of general practitioners, we sought to study the current coding patterns in allergies and identify lessons for the future migration to SNOMED-CT.Methods: Data from 2 014 551 primary care consultations in over 100 000 patients with one or more of 11 potentially allergic diseases (anaphylaxis, angioedema, asthma, conjunctivitis, drug allergies, eczema, food allergy, rhinitis, urticaria, venom allergy and other probable allergic disorders) from the Scottish Primary Care Clinical Informatics Unit Research (PCCIU-R) database were descriptively analysed and visualized to understand Read code usage patterns.Results: We identified 352 Read codes for these allergic diseases, but only 36 codes (10%) were used in 95% of consultations; 73 codes (21%) were never used. Half of all usage was for Quality and Outcomes Framework codes for asthma. Despite 149 detailed codes (42%) being available for allergic triggers, these were infrequently used.Conclusions: This analysis of Read codes use suggests that introduction of the more detailed SNOMED-CT, in isolation, will not improve the quality of allergy coding in Scottish primary care. The introduction of SNOMED-CT should be accompanied by initiatives aimed at improving coding quality, such as the definition of terms/codes, the availability of terminology browsers, a recommended list of codes and mechanisms to incentivize detailed coding of the condition and the underlying allergic trigger
Learning health systems need to bridge the ‘two cultures’ of clinical informatics and data science
Full text linkBackground UK health research policy and plans for population health management are predicated upon transformative knowledge discovery from operational ‘Big Data’. Learning health systems require not only data, but feedback loops of knowledge into changed practice. This depends on knowledge management and application, which in turn depends upon effective system design and implementation. Biomedical informatics is the interdisciplinary field at the intersection of health science, social science and information science and technology that spans this entire scope.Issues In the UK, the separate worlds of health data science (bioinformatics, ‘Big Data’) and effective healthcare system design and implementation (clinical informatics, ‘Digital Health’) have operated as ‘two cultures’. Much National Health Service and social care data is of very poor quality. Substantial research funding is wasted on ‘data cleansing’ or by producing very weak evidence. There is not yet a sufficiently powerful professional community or evidence base of best practice to influence the practitioner community or the digital health industry.Recommendation The UK needs increased clinical informatics research and education capacity and capability at much greater scale and ambition to be able to meet policy expectations, address the fundamental gaps in the discipline’s evidence base and mitigate the absence of regulation. Independent evaluation of digital health interventions should be the norm, not the exception.Conclusions Policy makers and research funders need to acknowledge the existing gap between the ‘two cultures’ and recognise that the full social and economic benefits of digital health and data science can only be realised by accepting the interdisciplinary nature of biomedical informatics and supporting a significant expansion of clinical informatics capacity and capability
Developing learning health system capabilities in the UK National Health Service - using asthma as an exemplar
Full text linkAsthma is a common condition responsible for substantial morbidity and societal impacts, much of which are potentially preventable. This condition, therefore, serve as useful exemplar to investigate the opportunities for developing health infrastructures that allow continuous cycles of improvement. The United Kingdom’s (UK’s) mature electronic health records infrastructure offers considerable opportunity to improve outcomes for people with asthma through the creation of a Learning Health System (LHS). The core idea in an LHS is to use the continuous streams of data emerging as a by-product of clinical care to inform and support policy decisions, organisation and delivery of healthcare and the personalisation of care. This was demonstrated during the recent COVID-19 pandemic when data from across the health ecosystem were harvested and analysed in near real-time to inform decision relating to public policy, public health and clinical care. In this thesis, I reflect on the progress made to advance capabilities to building LHS in the NHS for asthma and summarise outstanding challenges by critically considering eight papers that I first-authored between November 2014 and June 2024.
I begin this thesis with a brief overview of why asthma was used as an exemplar and how LHS has the potential to curb adverse outcomes of asthma and improve health in people with asthma. The concept of Learning Healthcare System had emanated from healthcare. Recognising that health is also shaped by wider determinants such as housing conditions and air pollution, Prof Aziz Sheikh proposed the term Learning Health System to encompass factors beyond healthcare alone. In this thesis, I adopt the definition of LHS as proposed by Prof Aziz Sheikh. Then I proceed to relevant epidemiological and health services research studies and LHS literature that predates and informs my own research and publications. Towards creating an LHS for asthma, I am guided by the four priority areas identified by Health Foundation and Health Data Research UK: i) learning from data, ii) harnessing technology, iii) learning communities and iv) implementing and evaluating improvements to services.
Next, I focus on my research, describing the studies I was involved in. In that chapter I describe three epidemiological and health services research studies and a qualitative study on health information systems I was involved in, which underpinned my submitted publications. For these four studies, I describe my involvement in the study, background to the study, the aims and objectives, design and methods used, implication of the findings and dissemination of findings.
My first paper provided the first evaluation of primary care clinical codes on asthma and allergies as was used in two million GP consultations in Scotland. My second paper is a protocol, which, for the first time, listed the routine and administrative datasets across the four nations of UK, for finding epidemiology and burden of asthma and the methods used to analyse these. In my third paper, I used those datasets to report the first comprehensive asthma burden estimates in the UK. In the absence of linked and longitudinal data, my fourth paper used cross-sectional data to create, for the first time, a population pyramid of asthma morbidity in Scotland. I found that a small proportion of people with asthma make disproportionate use of hospital-based asthma services. The fifth paper described, for the first time, profile of those admitted in paediatric intensive care in England for asthma, with patterns of healthcare utilisation and outcomes.
These exercises involved working with different data custodians across geography, data harmonisation issues and significant time lags between care provision and access to the data. Thus, to explore the barriers and facilitators in utilising electronic health records in near-real time across information systems, my sixth paper was a qualitative study based on interviews of stakeholders and data users in Scotland, which has rich data assets. The next study focused on creating LHS capability and investigating asthma modifiable factors so that targeted interventions could be provided in near-real time. The seventh paper was one of the first publications that analysed asthma modifiable factors that might explain the reduced risk of asthma hospitalisations during the COVID-19 pandemic. This PhD culminated in the development and deployment of a near-real time asthma dashboard designed for use in UK primary care. Using routinely collected data from the Oxford-RCGP RSC, the tool provides weekly feedback on asthma epidemiology, modifiable risk factors, and exacerbations at practice level, benchmarked against network averages. The dashboard operationalises key features of an LHS by enabling a timely, data-informed decision-making tool to support local quality improvement.
This is followed by my reflections in the next chapter, on the findings of my submitted papers, noting how individually and collectively, they contributed to the priority areas for creating an LHS. They have been presented under: i) learning from data: clinical codes, compiling and linking datasets for comprehensive understanding of the asthma burden, focusing on people with high health needs, children admitted to paediatric intensive care, potentially modifiable risk factors for asthma exacerbations, asthma dashboard as a quality improvement tool in asthma care, data fitness for research, data lifecycle approach, accessing data via single trusted research environment with metadata; ii) harnessing technology: overcoming technological roadblocks in real-time data, data integration across systems, modernising infrastructure, call for tech-savvy workforce, data virtualisation, asthma dashboard as an integrated visualisation; iii) learning communities: building collaboration to overcome data challenges, collaboration at national level; and iv) implementing and evaluating improvements to services through real-time monitoring.
After describing my contributions, I attempt an interpretation of my work in the context of the wider literature on asthma and LHS and identify alignments and distinctions. I discuss that by focusing on the role of LHS, my papers and review of the literature offer insights into how LHS capability could be built in the NHS to improve asthma outcomes.
I assess the strengths and limitations of my published work and implication of my findings for the existing literature on LHS. I conclude, that to improve asthma outcomes, an LHS approach is a potential solution. My contribution spans i) ‘practice to data’ cycle of LHS by listing the clinical codes and datasets on asthma in the UK nations, ii) ‘data to knowledge’ cycle by providing a) comprehensive estimates of asthma epidemiology, healthcare utilisation and outcomes at every UK-nation level and UK-wide, which can be used for baseline estimates for future studies, b) identification of potentially modifiable factors for asthma exacerbations, c) knowledge on barriers and facilitators that can enable real-time access to data; and iii) beginning of the ‘knowledge to practice’ cycle by deploying an asthma dashboard in RCGP RSC, which now needs promotion for regular usage and evaluation.
My reflections on my research journey involved navigating complex health data ecosystems to investigate how routine data can inform better asthma care. My early studies revealed limitations in coding and data quality, while later work identified modifiable risks and inequalities in asthma outcomes. The development of the asthma dashboard marked a turning point, shifting from knowledge generation to deployment in practice. Key lessons included the importance of data curation, stakeholder co-design, and the structural challenges of sustaining learning systems in real-world practice.
My call to action is to realise the potential of a national LHS for asthma - the NHS must move from data collection to action. This involves embedding real-time feedback tools like the Oxford-RCGP RSC asthma dashboard into clinical workflows, improving coding for treatable traits, investing in local quality improvement, and fostering collaborative learning communities. The UK's world-class data infrastructure can, and should, be harnessed to reduce variation and improve outcomes in asthma care
MoME: Mixture of Multimodal Experts for Cancer Survival Prediction
No full textSurvival prediction requires integrating Whole Slide Images (WSIs) and genomics, a task complicated by significant heterogeneity and complex inter- and intra-modal interactions between modalities. Previous methods used co-attention, fusing features only once after separate encoding, which is insufficient to model such a complex task due to modality heterogeneity. To this end, we propose a Biased Progressive Encoding (BPE) paradigm, performing encoding and fusion simultaneously. This paradigm uses one modality as a reference when encoding the other, fostering deep fusion of the modalities through multiple iterations, progressively reducing the cross-modal disparities and facilitating complementary interactions. Besides, survival prediction involves biomarkers from WSIs, genomics, and their integrative analysis. Key biomarkers may exist in different modalities under individual variations, necessitating the model flexibility. Hence, we further propose a Mixture of Multimodal Experts layer to dynamically select tailored experts in each stage of the BPE paradigm. Experts incorporate reference information from another modality to varying degrees, enabling a balanced or biased focus on different modalities during the encoding process. The experimental results demonstrate the superior performance of our method on various datasets, including TCGA-BLCA, TCGA-UCEC and TCGA-LUAD. Codes are available at https://github.com/BearCleverProud/MoME. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024
The Morality Menu Project
No full textThe discipline of machine ethics examines, designs and produces moral machines. The artificial morality is usually pre-programmed by a manufacturer or developer. However, another approach is the more flexible morality menu (MOME). With this, owners or users replicate their own moral preferences onto a machine. A team at the FHNW implemented a MOME for MOBO (a chatbot) in 2019/2020. In this article, the author introduces the idea of the MOME, presents the MOBO-MOME project and discusses advantages and disadvantages of such an approach. It turns out that a morality menu could be a valuable extension for certain moral machines
We need a robust evidence base to unravel the relationship between sex hormones and asthma
Full text linkThere has long been interest in whether sex hormones play a role in the development of asthma and influence its natural history, but much of this evidence base is of poor quality and hence difficult to interpret. This interest stems from clinical experiences, and findings from a substantial body of epidemiological investigations, and a smaller body of mechanistic and experimental studies. These have mainly focused on oestrogen and progesterone in females with inconsistent results. The focus on testosterone in both males and females in the linked study by Han et al is therefore welcome but other than these strengths,1 it suffers from many of the same limitations as much of the previous body of epidemiological work. In this editorial, we seek to contextualise the findings from Han et al and offer suggestions on how to strengthen the evidence base for understanding the relationship between sex hormones and asthma
Ten years of asthma admissions to adult critical care units in England and Wales
Full text linkOBJECTIVES: To describe the patient demographics, outcomes and trends of admissions with acute severe asthma admitted to adult critical care units in England and Wales. DESIGN: 10-year, retrospective analysis of a national audit database.SETTING: Secondary care: adult, general critical care units in the UK. PARTICIPANTS: 830 808 admissions to adult, general critical care units.PRIMARY AND SECONDARY OUTCOME MEASURES: Demographic data including age and sex, whether the patient was invasively ventilated or not, length of stay (LOS; both in the critical care unit and acute hospital), survival (both critical care unit and acute hospital) and time trends across the 10-year period.RESULTS: Over the 10-year period, there were 11 948 (1.4% of total) admissions with asthma to adult critical care units in England and Wales. Among them 67.5% were female and 32.5% were male (RR F:M 2.1; 95% CI 2.0 to 2.1). Median LOS in the critical care unit was 1.8 days (IQR 0.9-3.8). Median LOS in the acute hospital was 7 days (IQR 4-14). Critical care unit survival rate was 95.5%. Survival at discharge from hospital was 93.3%. There was an increase in admissions to adult critical care units by an average of 4.7% (95% CI 2.8 to 6.7)/year. CONCLUSIONS: Acute asthma represents a modest burden of work for adult critical care units in England and Wales. Demographic patterns for admission to critical care unit mirror those of severe asthma in the general adult community. The number of critical care admissions with asthma are rising, although we were unable to discern whether this represents a true increase in the incidence of acute asthma or asthma severity
Competing bimetallic ratios: Amsterdam, London and bullion arbitrage in the 18th century
Full text linkThis article analyses the stability of bimetallism in the mid-18th century for the case of two large centres that had different legal ratios and only one international market ratio. A new theoretical framework is articulated for the situation of international independence to set legal bimetallic ratios by monetary authorities in different countries. Then, using new data handcollected from archival sources and relevant to the two main bullion markets in the 18th century, Amsterdam and London, this theoretical framework is utilised to identify the regimes that actually prevailed during that period, in which Amsterdam was effectively on the bimetallic standard while London was on the gold standard de facto.Bimetallism, Bimetallic stability, Bullion markets, Arbitrage, Specie-point mechanism, Melting-minting points
Estimating the incidence, prevalence and true cost of asthma in the UK: secondary analysis of national stand-alone and linked databases in England, Northern Ireland, Scotland and Wales-a study protocol.
Full text linkINTRODUCTION: Asthma is now one of the most common long-term conditions in the UK. It is therefore important to develop a comprehensive appreciation of the healthcare and societal costs in order to inform decisions on care provision and planning. We plan to build on our earlier estimates of national prevalence and costs from asthma by filling the data gaps previously identified in relation to healthcare and broadening the field of enquiry to include societal costs. This work will provide the first UK-wide estimates of the costs of asthma. In the context of asthma for the UK and its member countries (ie, England, Northern Ireland, Scotland and Wales), we seek to: (1) produce a detailed overview of estimates of incidence, prevalence and healthcare utilisation; (2) estimate health and societal costs; (3) identify any remaining information gaps and explore the feasibility of filling these and (4) provide insights into future research that has the potential to inform changes in policy leading to the provision of more cost-effective care.
METHODS AND ANALYSIS: Secondary analyses of data from national health surveys, primary care, prescribing, emergency care, hospital, mortality and administrative data sources will be undertaken to estimate prevalence, healthcare utilisation and outcomes from asthma. Data linkages and economic modelling will be undertaken in an attempt to populate data gaps and estimate costs. Separate prevalence and cost estimates will be calculated for each of the UK-member countries and these will then be aggregated to generate UK-wide estimates.
ETHICS AND DISSEMINATION: Approvals have been obtained from the NHS Scotland Information Services Division's Privacy Advisory Committee, the Secure Anonymised Information Linkage Collaboration Review System, the NHS South-East Scotland Research Ethics Service and The University of Edinburgh's Centre for Population Health Sciences Research Ethics Committee. We will produce a report for Asthma-UK, submit papers to peer-reviewed journals and construct an interactive map
Predicting the risk of asthma attacks in children, adolescents and adults: protocol for a machine learning algorithm derived from a primary care-based retrospective cohort
No full textIntroduction Most asthma attacks and subsequent deaths are potentially preventable. We aim to develop a prognostic tool for identifying patients at high risk of asthma attacks in primary care by leveraging advances in machine learning.Methods and analysis Current prognostic tools use logistic regression to develop a risk scoring model for asthma attacks. We propose to build on this by systematically applying various well-known machine learning techniques to a large longitudinal deidentified primary care database, the Optimum Patient Care Research Database, and comparatively evaluate their performance with the existing logistic regression model and against each other. Machine learning algorithms vary in their predictive abilities based on the dataset and the approach to analysis employed. We will undertake feature selection, classification (both one-class and two-class classifiers) and performance evaluation. Patients who have had actively treated clinician-diagnosed asthma, aged 8–80 years and with 3 years of continuous data, from 2016 to 2018, will be selected. Risk factors will be obtained from the first year, while the next 2 years will form the outcome period, in which the primary endpoint will be the occurrence of an asthma attack.Ethics and dissemination We have obtained approval from OPCRD’s Anonymous Data Ethics Protocols and Transparency (ADEPT) Committee. We will seek ethics approval from The University of Edinburgh’s Research Ethics Group (UREG). We aim to present our findings at scientific conferences and in peer-reviewed journals
