Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information.

AIMS: Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints. METHODS: Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable. RESULTS: Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance. CONCLUSIONS: This study developed a series of ML models of accuracy ranging from 71.9-99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.

A Machine Learning Approach to Predict Weight Change in ART-Experienced People Living With HIV.

INTRODUCTION: The objective of the study was to develop machine learning (ML) models that predict the percentage weight change in each interval of time in antiretroviral therapy-experienced people living with HIV. METHODS: This was an observational study that comprised consecutive people living with HIV attending Modena HIV Metabolic Clinic with at least 2 visits. Data were partitioned in an 80/20 training/test set to generate 10 progressively parsimonious predictive ML models. Weight gain was defined as any weight change >5%, at the next visit. SHapley Additive exPlanations values were used to quantify the positive or negative impact of any single variable included in each model on the predicted weight changes. RESULTS: A total of 3,321 patients generated 18,322 observations. At the last observation, the median age was 50 years and 69% patients were male. Model 1 (the only 1 including body composition assessed with dual-energy x-ray absorptiometry) had an accuracy greater than 90%. This model could predict weight at the next visit with an error of <5%. CONCLUSIONS: ML models with the inclusion of body composition and metabolic and endocrinological variables had an excellent performance. The parsimonious models available in standard clinical evaluation are insufficient to obtain reliable prediction, but are good enough to predict who will not experience weight gain.

Mapping inpatient care pathways for patients with COPD: an observational study using routinely collected electronic hospital record data.

Introduction: Respiratory specialist ward care is associated with better outcomes for patients with COPD exacerbations. We assessed patient pathways and associated factors for people admitted to hospital with COPD exacerbations. Methods: We analysed routinely collected electronic health data for patients admitted with COPD exacerbation in 2018 to Queen Elizabeth Hospital, Birmingham, UK. We extracted data on demographics, deprivation index, Elixhauser comorbidities, ward moves, length of stay, and in-hospital and 1-year mortality. We compared care pathways with recommended care pathways (transition from initial assessment area to respiratory wards or discharge). We used Markov state transition models to derive probabilities of following recommended pathways for patient subgroups. Results: Of 42 555 patients with unplanned admissions during 2018, 571 patients were admitted at least once with an exacerbation of COPD. The mean±sd age was 51±11 years; 313 (55%) were women, 337 (59%) lived in the most deprived neighbourhoods and 45 (9%) were from non-white ethnic backgrounds. 428 (75.0%) had ≥4 comorbidities. Age >70 years was associated with higher in-hospital and 1-year mortality, more places of care (wards) and longer length of stay; having ≥4 comorbidities was associated with higher mortality and longer length of stay. Older age was associated with a significantly lower probability of following a recommended pathway (>70 years: 0.514, 95% CI 0.458-0.571; ≤70 years: 0.636, 95% CI 0.572-0.696; p=0.004). Conclusions: Only older age was associated with a lower chance of following recommended hospital pathways of care. Such analyses could help refine appropriate care pathways for patients with COPD exacerbations.

Ethnic differences in early onset multimorbidity and associations with health service use, long-term prescribing, years of life lost, and mortality: A cross-sectional study using clustering in the UK Clinical Practice Research Datalink.

BACKGROUND: The population prevalence of multimorbidity (the existence of at least 2 or more long-term conditions [LTCs] in an individual) is increasing among young adults, particularly in minority ethnic groups and individuals living in socioeconomically deprived areas. In this study, we applied a data-driven approach to identify clusters of individuals who had an early onset multimorbidity in an ethnically and socioeconomically diverse population. We identified associations between clusters and a range of health outcomes. METHODS AND FINDINGS: Using linked primary and secondary care data from the Clinical Practice Research Datalink GOLD (CPRD GOLD), we conducted a cross-sectional study of 837,869 individuals with early onset multimorbidity (aged between 16 and 39 years old when the second LTC was recorded) registered with an English general practice between 2010 and 2020. The study population included 777,906 people of White ethnicity (93%), 33,915 people of South Asian ethnicity (4%), and 26,048 people of Black African/Caribbean ethnicity (3%). A total of 204 LTCs were considered. Latent class analysis stratified by ethnicity identified 4 clusters of multimorbidity in White groups and 3 clusters in South Asian and Black groups. We found that early onset multimorbidity was more common among South Asian (59%, 33,915) and Black (56% 26,048) groups compared to the White population (42%, 777,906). Latent class analysis revealed physical and mental health conditions that were common across all ethnic groups (i.e., hypertension, depression, and painful conditions). However, each ethnic group also presented exclusive LTCs and different sociodemographic profiles: In White groups, the cluster with the highest rates/odds of the outcomes was predominantly male (54%, 44,150) and more socioeconomically deprived than the cluster with the lowest rates/odds of the outcomes. On the other hand, South Asian and Black groups were more socioeconomically deprived than White groups, with a consistent deprivation gradient across all multimorbidity clusters. At the end of the study, 4% (34,922) of the White early onset multimorbidity population had died compared to 2% of the South Asian and Black early onset multimorbidity populations (535 and 570, respectively); however, the latter groups died younger and lost more years of life. The 3 ethnic groups each displayed a cluster of individuals with increased rates of primary care consultations, hospitalisations, long-term prescribing, and odds of mortality. Study limitations include the exclusion of individuals with missing ethnicity information, the age of diagnosis not reflecting the actual age of onset, and the exclusion of people from Mixed, Chinese, and other ethnic groups due to insufficient power to investigate associations between multimorbidity and health-related outcomes in these groups. CONCLUSIONS: These findings emphasise the need to identify, prevent, and manage multimorbidity early in the life course. Our work provides additional insights into the excess burden of early onset multimorbidity in those from socioeconomically deprived and diverse groups who are disproportionately and more severely affected by multimorbidity and highlights the need to ensure healthcare improvements are equitable.

Real-world data mining meets clinical practice: Research challenges and perspective.

As Big Data Analysis meets healthcare applications, domain-specific challenges and opportunities materialize in all aspects of data science. Advanced statistical methods and Artificial Intelligence (AI) on Electronic Health Records (EHRs) are used both for knowledge discovery purposes and clinical decision support. Such techniques enable the emerging Predictive, Preventative, Personalized, and Participatory Medicine (P4M) paradigm. Working with the Infectious Disease Clinic of the University Hospital of Modena, Italy, we have developed a range of Data-Driven (DD) approaches to solve critical clinical applications using statistics, Machine Learning (ML) and Big Data Analytics on real-world EHR. Here, we describe our perspective on the challenges we encountered. Some are connected to medical data and their sparse, scarce, and unbalanced nature. Others are bound to the application environment, as medical AI tools can affect people's health and life. For each of these problems, we report some available techniques to tackle them, present examples drawn from our experience, and propose which approaches, in our opinion, could lead to successful real-world, end-to-end implementations. DESY report number: DESY-22-153.

The interplay of post-acute COVID-19 syndrome and aging: a biological, clinical and public health approach.

The post-acute COVID-19 syndrome (PACS) is characterized by the persistence of fluctuating symptoms over three months from the onset of the possible or confirmed COVID-19 acute phase. Current data suggests that at least 10% of people with previously documented infection may develop PACS, and up to 50-80% of prevalence is reported among survivors after hospital discharge. This viewpoint will discuss various aspects of PACS, particularly in older adults, with a specific hypothesis to describe PACS as the expression of a modified aging trajectory induced by SARS CoV-2. This hypothesis will be argued from biological, clinical and public health view, addressing three main questions: (i) does SARS-CoV-2-induced alterations in aging trajectories play a role in PACS?; (ii) do people with PACS face immuno-metabolic derangements that lead to increased susceptibility to age-related diseases?; (iii) is it possible to restore the healthy aging trajectory followed by the individual before pre-COVID?. A particular focus will be given to the well-being of people with PACS that could be assessed by the intrinsic capacity model and support the definition of the healthy aging trajectory.

Curating a longitudinal research resource using linked primary care EHR data-a UK Biobank case study.

Primary care EHR data are often of clinical importance to cohort studies however they require careful handling. Challenges include determining the periods during which EHR data were collected. Participants are typically censored when they deregister from a medical practice, however, cohort studies wish to follow participants longitudinally including those that change practice. Using UK Biobank as an exemplar, we developed methodology to infer continuous periods of data collection and maximize follow-up in longitudinal studies. This resulted in longer follow-up for around 40% of participants with multiple registration records (mean increase of 3.8 years from the first study visit). The approach did not sacrifice phenotyping accuracy when comparing agreement between self-reported and EHR data. A diabetes mellitus case study illustrates how the algorithm supports longitudinal study design and provides further validation. We use UK Biobank data, however, the tools provided can be used for other conditions and studies with minimal alteration.

A customisable pipeline for the semi-automated discovery of online activists and social campaigns on Twitter.

Substantial research is available on detecting influencers on social media platforms. In contrast, comparatively few studies exists on the role of online activists, defined informally as users who actively participate in socially-minded online campaigns. Automatically discovering activists who can potentially be approached by organisations that promote social campaigns is important, but not easy, as they are typically active only locally, and, unlike influencers, they are not central to large social media networks. We make the hypothesis that such interesting users can be found on Twitter within temporally and spatially localised contexts. We define these as small but topical fragments of the network, containing interactions about social events or campaigns with a significant online footprint. To explore this hypothesis, we have designed an iterative discovery pipeline consisting of two alternating phases of user discovery and context discovery. Multiple iterations of the pipeline result in a growing dataset of user profiles for activists, as well as growing set of online social contexts. This mode of exploration differs significantly from prior techniques that focus on influencers, and presents unique challenges because of the weak online signal available to detect activists. The paper describes the design and implementation of the pipeline as a customisable software framework, where user-defined operational definitions of online activism can be explored. We present an empirical evaluation on two extensive case studies, one concerning healthcare-related campaigns in the UK during 2018, the other related to online activism in Italy during the COVID-19 pandemic.

Using Wearable Activity Trackers to Predict Type 2 Diabetes: Machine Learning-Based Cross-sectional Study of the UK Biobank Accelerometer Cohort.

BACKGROUND: Between 2013 and 2015, the UK Biobank collected accelerometer traces from 103,712 volunteers aged between 40 and 69 years using wrist-worn triaxial accelerometers for 1 week. This data set has been used in the past to verify that individuals with chronic diseases exhibit reduced activity levels compared with healthy populations. However, the data set is likely to be noisy, as the devices were allocated to participants without a set of inclusion criteria, and the traces reflect free-living conditions. OBJECTIVE: This study aims to determine the extent to which accelerometer traces can be used to distinguish individuals with type 2 diabetes (T2D) from normoglycemic controls and to quantify their limitations. METHODS: Machine learning classifiers were trained using different feature sets to segregate individuals with T2D from normoglycemic individuals. Multiple criteria, based on a combination of self-assessment UK Biobank variables and primary care health records linked to UK Biobank participants, were used to identify 3103 individuals with T2D in this population. The remaining nondiabetic 19,852 participants were further scored on their physical activity impairment severity based on other conditions found in their primary care data, and those deemed likely physically impaired at the time were excluded. Physical activity features were first extracted from the raw accelerometer traces data set for each participant using an algorithm that extends the previously developed Biobank Accelerometry Analysis toolkit from Oxford University. These features were complemented by a selected collection of sociodemographic and lifestyle features available from UK Biobank. RESULTS: We tested 3 types of classifiers, with an area under the receiver operating characteristic curve (AUC) close to 0.86 (95% CI 0.85-0.87) for all 3 classifiers and F1 scores in the range of 0.80-0.82 for T2D-positive individuals and 0.73-0.74 for T2D-negative controls. Results obtained using nonphysically impaired controls were compared with highly physically impaired controls to test the hypothesis that nondiabetic conditions reduce classifier performance. Models built using a training set that included highly impaired controls with other conditions had worse performance (AUC 0.75-0.77; 95% CI 0.74-0.78; F1 scores in the range of 0.76-0.77 for T2D positives and 0.63-0.65 for controls). CONCLUSIONS: Granular measures of free-living physical activity can be used to successfully train machine learning models that are able to discriminate between individuals with T2D and normoglycemic controls, although with limitations because of the intrinsic noise in the data sets. From a broader clinical perspective, these findings motivate further research into the use of physical activity traces as a means of screening individuals at risk of diabetes and for early detection, in conjunction with routinely used risk scores, provided that appropriate quality control is enforced on the data collection protocol.

Machine learning in predicting respiratory failure in patients with COVID-19 pneumonia-Challenges, strengths, and opportunities in a global health emergency.

AIMS: The aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. METHODS: This was an observational prospective study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients' medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio <150 mmHg in at least one of two consecutive arterial blood gas analyses in the following 48 hours. Shapley Additive exPlanations values were used to quantify the positive or negative impact of each variable included in each model on the predicted outcome. RESULTS: A total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth "boosted mixed model" included 20 variables was selected from the model 3, achieved the best predictive performance (AUC = 0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. CONCLUSION: This study developed a machine model with 84% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.

Increasing phenotypic annotation improves the diagnostic rate of exome sequencing in a rare neuromuscular disorder.

Phenotype-based filtering and prioritization contribute to the interpretation of genetic variants detected in exome sequencing. However, it is currently unclear how extensive this phenotypic annotation should be. In this study, we compare methods for incorporating phenotype into the interpretation process and assess the extent to which phenotypic annotation aids prioritization of the correct variant. Using a cohort of 29 patients with congenital myasthenic syndromes with causative variants in known or newly discovered disease genes, exome data and the Human Phenotype Ontology (HPO)-coded phenotypic profiles, we show that gene-list filters created from phenotypic annotations perform similarly to curated disease-gene virtual panels. We use Exomiser, a prioritization tool incorporating phenotypic comparisons, to rank candidate variants while varying phenotypic annotation. Analyzing 3,712 combinations, we show that increasing phenotypic annotation improved prioritization of the causative variant, from 62% ranked first on variant alone to 90% with seven HPO annotations. We conclude that any HPO-based phenotypic annotation aids variant discovery and that annotation with over five terms is recommended in our context. Although focused on a constrained cohort, this provides real-world validation of the utility of phenotypic annotation for variant prioritization. Further research is needed to extend this concept to other diseases and more diverse cohorts.

Targeted therapies for congenital myasthenic syndromes: systematic review and steps towards a treatabolome.

Despite recent scientific advances, most rare genetic diseases - including most neuro-muscular diseases - do not currently have curative gene-based therapies available. However, in some cases, such as vitamin, cofactor or enzyme deficiencies, channelopathies and disorders of the neuromuscular junction, a confirmed genetic diagnosis provides guidance on treatment, with drugs available that may significantly alter the disease course, improve functional ability and extend life expectancy. Nevertheless, many treatable patients remain undiagnosed or do not receive treatment even after genetic diagnosis. The growth of computer-aided genetic analysis systems that enable clinicians to diagnose their undiagnosed patients has not yet been matched by genetics-based decision-support systems for treatment guidance. Generating a 'treatabolome' of treatable variants and the evidence for the treatment has the potential to increase treatment rates for treatable conditions. Here, we use the congenital myasthenic syndromes (CMS), a group of clinically and genetically heterogeneous but frequently treatable neuromuscular conditions, to illustrate the steps in the creation of a treatabolome for rare inherited diseases. We perform a systematic review of the evidence for pharmacological treatment of each CMS type, gathering evidence from 207 studies of over 1000 patients and stratifying by genetic defect, as treatment varies depending on the underlying cause. We assess the strength and quality of the evidence and create a dataset that provides the foundation for a computer-aided system to enable clinicians to gain easier access to information about treatable variants and the evidence they need to consider.

Distilling structure in Taverna scientific workflows: a refactoring approach.

BACKGROUND: Scientific workflows management systems are increasingly used to specify and manage bioinformatics experiments. Their programming model appeals to bioinformaticians, who can use them to easily specify complex data processing pipelines. Such a model is underpinned by a graph structure, where nodes represent bioinformatics tasks and links represent the dataflow. The complexity of such graph structures is increasing over time, with possible impacts on scientific workflows reuse. In this work, we propose effective methods for workflow design, with a focus on the Taverna model. We argue that one of the contributing factors for the difficulties in reuse is the presence of "anti-patterns", a term broadly used in program design, to indicate the use of idiomatic forms that lead to over-complicated design. The main contribution of this work is a method for automatically detecting such anti-patterns, and replacing them with different patterns which result in a reduction in the workflow's overall structural complexity. Rewriting workflows in this way will be beneficial both in terms of user experience (easier design and maintenance), and in terms of operational efficiency (easier to manage, and sometimes to exploit the latent parallelism amongst the tasks). RESULTS: We have conducted a thorough study of the workflows structures available in Taverna, with the aim of finding out workflow fragments whose structure could be made simpler without altering the workflow semantics. We provide four contributions. Firstly, we identify a set of anti-patterns that contribute to the structural workflow complexity. Secondly, we design a series of refactoring transformations to replace each anti-pattern by a new semantically-equivalent pattern with less redundancy and simplified structure. Thirdly, we introduce a distilling algorithm that takes in a workflow and produces a distilled semantically-equivalent workflow. Lastly, we provide an implementation of our refactoring approach that we evaluate on both the public Taverna workflows and on a private collection of workflows from the BioVel project. CONCLUSION: We have designed and implemented an approach to improving workflow structure by way of rewriting preserving workflow semantics. Future work includes considering our refactoring approach during the phase of workflow design and proposing guidelines for designing distilled workflows.

A Comparison of Using Taverna and BPEL in Building Scientific Workflows: the case of caGrid.

With the emergence of "service oriented science," the need arises to orchestrate multiple services to facilitate scientific investigation-that is, to create "science workflows." We present here our findings in providing a workflow solution for the caGrid service-based grid infrastructure. We choose BPEL and Taverna as candidates, and compare their usability in the lifecycle of a scientific workflow, including workflow composition, execution, and result analysis. Our experience shows that BPEL as an imperative language offers a comprehensive set of modeling primitives for workflows of all flavors; while Taverna offers a dataflow model and a more compact set of primitives that facilitates dataflow modeling and pipelined execution. We hope that this comparison study not only helps researchers select a language or tool that meets their specific needs, but also offers some insight on how a workflow language and tool can fulfill the requirement of the scientific community.

Information quality in proteomics.

Proteomics, the study of the protein complement of a biological system, is generating increasing quantities of data from rapidly developing technologies employed in a variety of different experimental workflows. Experimental processes, e.g. for comparative 2D gel studies or LC-MS/MS analyses of complex protein mixtures, involve a number of steps: from experimental design, through wet and dry lab operations, to publication of data in repositories and finally to data annotation and maintenance. The presence of inaccuracies throughout the processing pipeline, however, results in data that can be untrustworthy, thus offsetting the benefits of high-throughput technology. While researchers and practitioners are generally aware of some of the information quality issues associated with public proteomics data, there are few accepted criteria and guidelines for dealing with them. In this article, we highlight factors that impact on the quality of experimental data and review current approaches to information quality management in proteomics. Data quality issues are considered throughout the lifecycle of a proteomics experiment, from experiment design and technique selection, through data analysis, to archiving and sharing.