Implementation of the trial emulation approach in medical research: a scoping review.

BACKGROUND: When conducting randomised controlled trials is impractical, an alternative is to carry out an observational study. However, making valid causal inferences from observational data is challenging because of the risk of several statistical biases. In 2016 Hernán and Robins put forward the 'target trial framework' as a guide to best design and analyse observational studies whilst preventing the most common biases. This framework consists of (1) clearly defining a causal question about an intervention, (2) specifying the protocol of the hypothetical trial, and (3) explaining how the observational data will be used to emulate it. METHODS: The aim of this scoping review was to identify and review all explicit attempts of trial emulation studies across all medical fields. Embase, Medline and Web of Science were searched for trial emulation studies published in English from database inception to February 25, 2021. The following information was extracted from studies that were deemed eligible for review: the subject area, the type of observational data that they leveraged, and the statistical methods they used to address the following biases: (A) confounding bias, (B) immortal time bias, and (C) selection bias. RESULTS: The search resulted in 617 studies, 38 of which we deemed eligible for review. Of those 38 studies, most focused on cardiology, infectious diseases or oncology and the majority used electronic health records/electronic medical records data and cohort studies data. Different statistical methods were used to address confounding at baseline and selection bias, predominantly conditioning on the confounders (N = 18/49, 37%) and inverse probability of censoring weighting (N = 7/20, 35%) respectively. Different approaches were used to address immortal time bias, assigning individuals to treatment strategies at start of follow-up based on their data available at that specific time (N = 21, 55%), using the sequential trial emulations approach (N = 11, 29%) or the cloning approach (N = 6, 16%). CONCLUSION: Different methods can be leveraged to address (A) confounding bias, (B) immortal time bias, and (C) selection bias. When working with observational data, and if possible, the 'target trial' framework should be used as it provides a structured conceptual approach to observational research.

DGLinker: flexible knowledge-graph prediction of disease-gene associations.

As a result of the advent of high-throughput technologies, there has been rapid progress in our understanding of the genetics underlying biological processes. However, despite such advances, the genetic landscape of human diseases has only marginally been disclosed. Exploiting the present availability of large amounts of biological and phenotypic data, we can use our current understanding of disease genetics to train machine learning models to predict novel genetic factors associated with the disease. To this end, we developed DGLinker, a webserver for the prediction of novel candidate genes for human diseases given a set of known disease genes. DGLinker has a user-friendly interface that allows non-expert users to exploit biomedical information from a wide range of biological and phenotypic databases, and/or to upload their own data, to generate a knowledge-graph and use machine learning to predict new disease-associated genes. The webserver includes tools to explore and interpret the results and generates publication-ready figures. DGLinker is available at https://dglinker.rosalind.kcl.ac.uk. The webserver is free and open to all users without the need for registration.

A novel algorithmic approach to generate consensus treatment guidelines in adult acute myeloid leukaemia.

Induction therapy for acute myeloid leukaemia (AML) has changed with the approval of a number of new agents. Clinical guidelines can struggle to keep pace with an evolving treatment and evidence landscape and therefore identifying the most appropriate front-line treatment is challenging for clinicians. Here, we combined drug eligibility criteria and genetic risk stratification into a digital format, allowing the full range of possible treatment eligibility scenarios to be defined. Using exemplar cases representing each of the 22 identified scenarios, we sought to generate consensus on treatment choice from a panel of nine aUK AML experts. We then analysed >2500 real-world cases using the same algorithm, confirming the existence of 21/22 of these scenarios and demonstrating that our novel approach could generate a consensus AML induction treatment in 98% of cases. Our approach, driven by the use of decision trees, is an efficient way to develop consensus guidance rapidly and could be applied to other disease areas. It has the potential to be updated frequently to capture changes in eligibility criteria, novel therapies and emerging trial data. An interactive digital version of the consensus guideline is available.

Diagnostic signature for heart failure with preserved ejection fraction (HFpEF): a machine learning approach using multi-modality electronic health record data.

BACKGROUND: Heart failure with preserved ejection fraction (HFpEF) is thought to be highly prevalent yet remains underdiagnosed. Evidence-based treatments are available that increase quality of life and decrease hospitalization. We sought to develop a data-driven diagnostic model to predict from electronic health records (EHR) the likelihood of HFpEF among patients with unexplained dyspnea and preserved left ventricular EF. METHODS AND RESULTS: The derivation cohort comprised patients with dyspnea and echocardiography results. Structured and unstructured data were extracted using an automated informatics pipeline. Patients were retrospectively diagnosed as HFpEF (cases), non-HF (control cohort I), or HF with reduced EF (HFrEF; control cohort II). The ability of clinical parameters and investigations to discriminate cases from controls was evaluated by extreme gradient boosting. A likelihood scoring system was developed and validated in a separate test cohort. The derivation cohort included 1585 consecutive patients: 133 cases of HFpEF (9%), 194 non-HF cases (Control cohort I) and 1258 HFrEF cases (Control cohort II). Two HFpEF diagnostic signatures were derived, comprising symptoms, diagnoses and investigation results. A final prediction model was generated based on the averaged likelihood scores from these two models. In a validation cohort consisting of 269 consecutive patients [with 66 HFpEF cases (24.5%)], the diagnostic power of detecting HFpEF had an AUROC of 90% (P < 0.001) and average precision of 74%. CONCLUSION: This diagnostic signature enables discrimination of HFpEF from non-cardiac dyspnea or HFrEF from EHR and can assist in the diagnostic evaluation in patients with unexplained dyspnea. This approach will enable identification of HFpEF patients who may then benefit from new evidence-based therapies.

Evaluation and improvement of the National Early Warning Score (NEWS2) for COVID-19: a multi-hospital study.

BACKGROUND: The National Early Warning Score (NEWS2) is currently recommended in the UK for the risk stratification of COVID-19 patients, but little is known about its ability to detect severe cases. We aimed to evaluate NEWS2 for the prediction of severe COVID-19 outcome and identify and validate a set of blood and physiological parameters routinely collected at hospital admission to improve upon the use of NEWS2 alone for medium-term risk stratification. METHODS: Training cohorts comprised 1276 patients admitted to King's College Hospital National Health Service (NHS) Foundation Trust with COVID-19 disease from 1 March to 30 April 2020. External validation cohorts included 6237 patients from five UK NHS Trusts (Guy's and St Thomas' Hospitals, University Hospitals Southampton, University Hospitals Bristol and Weston NHS Foundation Trust, University College London Hospitals, University Hospitals Birmingham), one hospital in Norway (Oslo University Hospital), and two hospitals in Wuhan, China (Wuhan Sixth Hospital and Taikang Tongji Hospital). The outcome was severe COVID-19 disease (transfer to intensive care unit (ICU) or death) at 14 days after hospital admission. Age, physiological measures, blood biomarkers, sex, ethnicity, and comorbidities (hypertension, diabetes, cardiovascular, respiratory and kidney diseases) measured at hospital admission were considered in the models. RESULTS: A baseline model of 'NEWS2 + age' had poor-to-moderate discrimination for severe COVID-19 infection at 14 days (area under receiver operating characteristic curve (AUC) in training cohort = 0.700, 95% confidence interval (CI) 0.680, 0.722; Brier score = 0.192, 95% CI 0.186, 0.197). A supplemented model adding eight routinely collected blood and physiological parameters (supplemental oxygen flow rate, urea, age, oxygen saturation, C-reactive protein, estimated glomerular filtration rate, neutrophil count, neutrophil/lymphocyte ratio) improved discrimination (AUC = 0.735; 95% CI 0.715, 0.757), and these improvements were replicated across seven UK and non-UK sites. However, there was evidence of miscalibration with the model tending to underestimate risks in most sites. CONCLUSIONS: NEWS2 score had poor-to-moderate discrimination for medium-term COVID-19 outcome which raises questions about its use as a screening tool at hospital admission. Risk stratification was improved by including readily available blood and physiological parameters measured at hospital admission, but there was evidence of miscalibration in external sites. This highlights the need for a better understanding of the use of early warning scores for COVID.

Pre-existing cardiovascular disease rather than cardiovascular risk factors drives mortality in COVID-19.

BACKGROUND: The relative association between cardiovascular (CV) risk factors, such as diabetes and hypertension, established CV disease (CVD), and susceptibility to CV complications or mortality in COVID-19 remains unclear. METHODS: We conducted a cohort study of consecutive adults hospitalised for severe COVID-19 between 1st March and 30th June 2020. Pre-existing CVD, CV risk factors and associations with mortality and CV complications were ascertained. RESULTS: Among 1721 patients (median age 71 years, 57% male), 349 (20.3%) had pre-existing CVD (CVD), 888 (51.6%) had CV risk factors without CVD (RF-CVD), 484 (28.1%) had neither. Patients with CVD were older with a higher burden of non-CV comorbidities. During follow-up, 438 (25.5%) patients died: 37% with CVD, 25.7% with RF-CVD and 16.5% with neither. CVD was independently associated with in-hospital mortality among patients < 70 years of age (adjusted HR 2.43 [95% CI 1.16-5.07]), but not in those ≥ 70 years (aHR 1.14 [95% CI 0.77-1.69]). RF-CVD were not independently associated with mortality in either age group (< 70 y aHR 1.21 [95% CI 0.72-2.01], ≥ 70 y aHR 1.07 [95% CI 0.76-1.52]). Most CV complications occurred in patients with CVD (66%) versus RF-CVD (17%) or neither (11%; p < 0.001). 213 [12.4%] patients developed venous thromboembolism (VTE). CVD was not an independent predictor of VTE. CONCLUSIONS: In patients hospitalised with COVID-19, pre-existing established CVD appears to be a more important contributor to mortality than CV risk factors in the absence of CVD. CVD-related hazard may be mediated, in part, by new CV complications. Optimal care and vigilance for destabilised CVD are essential in this patient group. Trial registration n/a.

Establishing Diorhabda carinulata: Impact of Release Disturbances on Pheromone Emission and Influence of Pheromone Lures on Establishment.

Before weed biocontrol insects are transported and released in a new area, they are commonly collected into small paper containers, chilled, and kept under dark conditions. This process can be termed a pre-release protocol. The influence of a pre-release protocol on establishment success of a gregarious biological control agent was assessed using the northern tamarisk beetle, Diorhabda carinulata (Desbrochers), and its exotic, invasive host plant saltcedar (Tamarix spp.). Pre-release protocol impacts on aggregation pheromone production by D. carinulata were characterized under controlled conditions. Additional experiments were undertaken to determine if deployment of aggregation pheromone lures might enhance the agent's persistence at release sites. Adults that experienced the pre-release protocol produced less aggregation pheromone compared to undisturbed adults. Olfactometer bioassays indicated that a cohort of adults subjected to the pre-release protocol were less attractive to other adults than a control cohort. Efficacy of aggregation pheromone-based lures to retain adults at release sites was evaluated by comparing capture numbers of adult beetles at paired treatment and control release sites, 10-14 days after the release of 300, 500, or 1000 individuals. A greater number of adult D. carinulata were captured where the pheromone lures had been deployed compared to control release sites. Application of aggregation pheromone when a new release of D. carinulata is planned should allow biological control practitioners to increase retention of beetles at a release site.

Spinal motor neuron protein supersaturation patterns are associated with inclusion body formation in ALS.

Amyotrophic lateral sclerosis (ALS) is a heterogeneous degenerative motor neuron disease linked to numerous genetic mutations in apparently unrelated proteins. These proteins, including SOD1, TDP-43, and FUS, are highly aggregation-prone and form a variety of intracellular inclusion bodies that are characteristic of different neuropathological subtypes of the disease. Contained within these inclusions are a variety of proteins that do not share obvious characteristics other than coaggregation. However, recent evidence from other neurodegenerative disorders suggests that disease-affected biochemical pathways can be characterized by the presence of proteins that are supersaturated, with cellular concentrations significantly greater than their solubilities. Here, we show that the proteins that form inclusions of mutant SOD1, TDP-43, and FUS are not merely a subset of the native interaction partners of these three proteins, which are themselves supersaturated. To explain the presence of coaggregating proteins in inclusions in the brain and spinal cord, we observe that they have an average supersaturation even greater than the average supersaturation of the native interaction partners in motor neurons, but not when scores are generated from an average of other human tissues. These results suggest that inclusion bodies in various forms of ALS result from a set of proteins that are metastable in motor neurons, and thus prone to aggregation upon a disease-related progressive collapse of protein homeostasis in this specific setting.

Bleeding in cardiac patients prescribed antithrombotic drugs: electronic health record phenotyping algorithms, incidence, trends and prognosis.

BACKGROUND: Clinical guidelines and public health authorities lack recommendations on scalable approaches to defining and monitoring the occurrence and severity of bleeding in populations prescribed antithrombotic therapy. METHODS: We examined linked primary care, hospital admission and death registry electronic health records (CALIBER 1998-2010, England) of patients with newly diagnosed atrial fibrillation, acute myocardial infarction, unstable angina or stable angina with the aim to develop algorithms for bleeding events. Using the developed bleeding phenotypes, Kaplan-Meier plots were used to estimate the incidence of bleeding events and we used Cox regression models to assess the prognosis for all-cause mortality, atherothrombotic events and further bleeding. RESULTS: We present electronic health record phenotyping algorithms for bleeding based on bleeding diagnosis in primary or hospital care, symptoms, transfusion, surgical procedures and haemoglobin values. In validation of the phenotype, we estimated a positive predictive value of 0.88 (95% CI 0.64, 0.99) for hospitalised bleeding. Amongst 128,815 patients, 27,259 (21.2%) had at least 1 bleeding event, with 5-year risks of bleeding of 29.1%, 21.9%, 25.3% and 23.4% following diagnoses of atrial fibrillation, acute myocardial infarction, unstable angina and stable angina, respectively. Rates of hospitalised bleeding per 1000 patients more than doubled from 1.02 (95% CI 0.83, 1.22) in January 1998 to 2.68 (95% CI 2.49, 2.88) in December 2009 coinciding with the increased rates of antiplatelet and vitamin K antagonist prescribing. Patients with hospitalised bleeding and primary care bleeding, with or without markers of severity, were at increased risk of all-cause mortality and atherothrombotic events compared to those with no bleeding. For example, the hazard ratio for all-cause mortality was 1.98 (95% CI 1.86, 2.11) for primary care bleeding with markers of severity and 1.99 (95% CI 1.92, 2.05) for hospitalised bleeding without markers of severity, compared to patients with no bleeding. CONCLUSIONS: Electronic health record bleeding phenotyping algorithms offer a scalable approach to monitoring bleeding in the population. Incidence of bleeding has doubled in incidence since 1998, affects one in four cardiovascular disease patients, and is associated with poor prognosis. Efforts are required to tackle this iatrogenic epidemic.

Vegetation response to invasive Tamarix control in southwestern U.S. rivers: a collaborative study including 416 sites.

Most studies assessing vegetation response following control of invasive Tamarix trees along southwestern U.S. rivers have been small in scale (e.g., river reach), or at a regional scale but with poor spatial-temporal replication, and most have not included testing the effects of a now widely used biological control. We monitored plant composition following Tamarix control along hydrologic, soil, and climatic gradients in 244 treated and 172 reference sites across six U.S. states. This represents the largest comprehensive assessment to date on the vegetation response to the four most common Tamarix control treatments. Biocontrol by a defoliating beetle (treatment 1) reduced the abundance of Tamarix less than active removal by mechanically using hand and chain-saws (2), heavy machinery (3) or burning (4). Tamarix abundance also decreased with lower temperatures, higher precipitation, and follow-up treatments for Tamarix resprouting. Native cover generally increased over time in active Tamarix removal sites, however, the increases observed were small and was not consistently increased by active revegetation. Overall, native cover was correlated to permanent stream flow, lower grazing pressure, lower soil salinity and temperatures, and higher precipitation. Species diversity also increased where Tamarix was removed. However, Tamarix treatments, especially those generating the highest disturbance (burning and heavy machinery), also often promoted secondary invasions of exotic forbs. The abundance of hydrophytic species was much lower in treated than in reference sites, suggesting that management of southwestern U.S. rivers has focused too much on weed control, overlooking restoration of fluvial processes that provide habitat for hydrophytic and floodplain vegetation. These results can help inform future management of Tamarix-infested rivers to restore hydrogeomorphic processes, increase native biodiversity and reduce abundance of noxious species.

Predicting Future Disorders via Temporal Knowledge Graphs and Medical Ontologies.

Despite the vast potential for insights and value present in Electronic Health Records (EHRs), it is challenging to fully leverage all the available information, particularly that contained in the free-text data written by clinicians describing the health status of patients. The utilization of Named Entity Recognition and Linking tools allows not only for the structuring of information contained within free-text data, but also for the integration with medical ontologies, which may prove highly beneficial for the analysis of patient medical histories with the aim of forecasting future medical outcomes, such as the diagnosis of a new disorder. In this paper, we propose MedTKG, a Temporal Knowledge Graph (TKG) framework that incorporates both the dynamic information of patient clinical histories and the static information of medical ontologies. The TKG is used to model a medical history as a series of snapshots at different points in time, effectively capturing the dynamic nature of the patient's health status, while a static graph is used to model the hierarchies of concepts extracted from domain ontologies. The proposed method aims to predict future disorders by identifying missing objects in the quadruple 〈s, r, ?, t 〉, where s and r denote the patient and the disorder relation type, respectively, and t is the timestamp of the query. The method is evaluated on clinical notes extracted from MIMIC-III and demonstrates the effectiveness of the TKG framework in predicting future disorders and of medical ontologies in improving its performance.

Isolated catalyst sites on amorphous supports: a systematic algorithm for understanding heterogeneities in structure and reactivity.

Methods for modeling catalytic sites on amorphous supports lag far behind methods for modeling catalytic sites on metal surfaces, zeolites, and other crystalline materials. One typical strategy for amorphous supports uses cluster models with arbitrarily chosen constraints to model the rigid amorphous support, but these constraints arbitrarily influence catalyst site activity. An alternative strategy is to use no constraints, but this results in catalytic sites with unrealistic flexibility. We present a systematic ab initio method to model isolated active sites on insulating amorphous supports using small cluster models. A sequential quadratic programming framework helps us relate chemical properties, such as the activation energy, to active site structure. The algorithm is first illustrated on an empirical valence bond model energy landscape. We then use the algorithm to model an off-pathway kinetic trap in olefin metathesis by isolated Mo sites on amorphous SiO2. The cluster models were terminated with basis set deficient fluorine atoms to mimic the properties of an extended silica framework. We also discuss limitations of the current algorithm formulation and future directions for improvement.

Hospital-wide natural language processing summarising the health data of 1 million patients.

Electronic health records (EHRs) represent a major repository of real world clinical trajectories, interventions and outcomes. While modern enterprise EHR's try to capture data in structured standardised formats, a significant bulk of the available information captured in the EHR is still recorded only in unstructured text format and can only be transformed into structured codes by manual processes. Recently, Natural Language Processing (NLP) algorithms have reached a level of performance suitable for large scale and accurate information extraction from clinical text. Here we describe the application of open-source named-entity-recognition and linkage (NER+L) methods (CogStack, MedCAT) to the entire text content of a large UK hospital trust (King's College Hospital, London). The resulting dataset contains 157M SNOMED concepts generated from 9.5M documents for 1.07M patients over a period of 9 years. We present a summary of prevalence and disease onset as well as a patient embedding that captures major comorbidity patterns at scale. NLP has the potential to transform the health data lifecycle, through large-scale automation of a traditionally manual task.

Evaluating clinical outcomes and prognosis in patients with cirrhosis and portal hypertension: a retrospective observational cohort study.

OBJECTIVE: Cirrhosis describes the end-stage of chronic liver disease. Irreversible changes in the liver cause portal hypertension, which can progress to serious complications and death. Only a few studies with small sample sizes have investigated the prognosis of cirrhosis with portal hypertension. We used electronic healthcare records to examine liver-related outcomes in patients with diagnosed/suspected portal hypertension. DESIGN: This retrospective observational cohort study used secondary health data between 1 January 2017 and 3 December 2020 from the TriNetX Network, a federated electronic healthcare records platform. Three patient groups with cirrhosis and diagnosed/suspected portal hypertension were identified ('most severe', 'moderate severity' and 'least severe'). Outcomes studied individually and as a composite were variceal haemorrhage, hepatic encephalopathy, complications of ascites and recorded mortality up to 24 months. RESULTS: There were 13 444, 23 299, and 23 836 patients in the most severe, moderate severity and least severe groups, respectively. Mean age was similar across groups; most participants were white. The most common individual outcomes at 24 months were variceal haemorrhage in the most severe group, recorded mortality and hepatic encephalopathy in the moderate severity group, and recorded mortality in the least severe group. Recorded mortality rate was similar across groups. For the composite outcome, cumulative incidence was 59% in the most severe group at 6 months. Alcohol-associated liver disease and metabolic-associated steatohepatitis were significantly associated with the composite outcome across groups. CONCLUSION: Our analysis of a large dataset from electronic healthcare records illustrates the poor prognosis of patients with diagnosed/suspected portal hypertension.

Anticoagulation for atrial fibrillation in people with serious mental illness in the general hospital setting.

OBJECTIVE: People with serious mental illnesses (SMI) have an increased risk of stroke compared to the general population. This study aims to evaluate oral anticoagulation prescription trends in atrial fibrillation (AF) patients with and without a comorbid SMI. METHODS: An open-source retrieval system for clinical data (CogStack) was used to identify a cohort of AF patients with SMI who ever had an inpatient admission to King's College Hospital from 2011 to 2020. A Natural Language Processing pipeline was used to calculate CHA2DS2-VASc and HASBLED risk scores from Electronic Health Records free text. Antithrombotic prescriptions of warfarin and Direct acting oral anti-coagulants (DOACs) (apixaban, rivaroxaban, dabigatran, edoxaban) were extracted from discharge summaries. RESULTS: Among patients included in the study (n = 16 916), 2.7% had a recorded co-morbid SMI diagnosis. Compared to non-SMI patients, those with SMI had significantly higher CHA2DS2-VASc (mean (SD): 5.3 (1.96) vs 4.7 (2.08), p < 0.001) and HASBLED scores (mean (SD): 3.2 (1.27) vs 2.5 (1.29), p < 0.001). Among AF patients having a CHA2DS2-VASc ≥2, those with co-morbid SMI were less likely than non-SMI patients to be prescribed an OAC (44% vs 54%, p < 0.001). However, there was no evidence of a significant difference between the two groups since 2019. CONCLUSION: Over recent years, DOAC prescription rates have increased among AF patients with SMI in acute hospitals. More research is needed to confirm whether the introduction of DOACs has reduced OAC treatment gaps in people with serious mental illness and to assess whether the use of DOACs has improved health outcomes in this population.

Mapping multimorbidity in individuals with schizophrenia and bipolar disorders: evidence from the South London and Maudsley NHS Foundation Trust Biomedical Research Centre (SLAM BRC) case register.

OBJECTIVES: The first aim of this study was to design and develop a valid and replicable strategy to extract physical health conditions from clinical notes which are common in mental health services. Then, we examined the prevalence of these conditions in individuals with severe mental illness (SMI) and compared their individual and combined prevalence in individuals with bipolar (BD) and schizophrenia spectrum disorders (SSD). DESIGN: Observational study. SETTING: Secondary mental healthcare services from South London PARTICIPANTS: Our maximal sample comprised 17 500 individuals aged 15 years or older who had received a primary or secondary SMI diagnosis (International Classification of Diseases, 10th edition, F20-31) between 2007 and 2018. MEASURES: We designed and implemented a data extraction strategy for 21 common physical comorbidities using a natural language processing pipeline, MedCAT. Associations were investigated with sex, age at SMI diagnosis, ethnicity and social deprivation for the whole cohort and the BD and SSD subgroups. Linear regression models were used to examine associations with disability measured by the Health of Nations Outcome Scale. RESULTS: Physical health data were extracted, achieving precision rates (F1) above 0.90 for all conditions. The 10 most prevalent conditions were diabetes, hypertension, asthma, arthritis, epilepsy, cerebrovascular accident, eczema, migraine, ischaemic heart disease and chronic obstructive pulmonary disease. The most prevalent combination in this population included diabetes, hypertension and asthma, regardless of their SMI diagnoses. CONCLUSIONS: Our data extraction strategy was found to be adequate to extract physical health data from clinical notes, which is essential for future multimorbidity research using text records. We found that around 40% of our cohort had multimorbidity from which 20% had complex multimorbidity (two or more physical conditions besides SMI). Sex, age, ethnicity and social deprivation were found to be key to understand their heterogeneity and their differential contribution to disability levels in this population. These outputs have direct implications for researchers and clinicians.

A Knowledge Distillation Ensemble Framework for Predicting Short- and Long-Term Hospitalization Outcomes From Electronic Health Records Data.

The ability to perform accurate prognosis is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission and readmission from time-series of vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked ensemble platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction by incorporating static features. The model is used to assess a patient's risk of adversity and provides visual justifications of its prediction. Results of three case studies show that the model outperforms existing platforms in ICU and general ward settings, achieving average Precision-Recall Areas Under the Curve (PR-AUCs) of 0.891 (95% CI: 0.878-0.939) for mortality and 0.908 (95% CI: 0.870-0.935) in predicting ICU admission and readmission.

Evaluation of antithrombotic use and COVID-19 outcomes in a nationwide atrial fibrillation cohort.

OBJECTIVE: To evaluate antithrombotic (AT) use in individuals with atrial fibrillation (AF) and at high risk of stroke (CHA2DS2-VASc score ≥2) and investigate whether pre-existing AT use may improve COVID-19 outcomes. METHODS: Individuals with AF and CHA2DS2-VASc score ≥2 on 1 January 2020 were identified using electronic health records for 56 million people in England and were followed up until 1 May 2021. Factors associated with pre-existing AT use were analysed using logistic regression. Differences in COVID-19-related hospitalisation and death were analysed using logistic and Cox regression in individuals with pre-existing AT use versus no AT use, anticoagulants (AC) versus antiplatelets (AP), and direct oral anticoagulants (DOACs) versus warfarin. RESULTS: From 972 971 individuals with AF (age 79 (±9.3), female 46.2%) and CHA2DS2-VASc score ≥2, 88.0% (n=856 336) had pre-existing AT use, 3.8% (n=37 418) had a COVID-19 hospitalisation and 2.2% (n=21 116) died, followed up to 1 May 2021. Factors associated with no AT use included comorbidities that may contraindicate AT use (liver disease and history of falls) and demographics (socioeconomic status and ethnicity). Pre-existing AT use was associated with lower odds of death (OR=0.92, 95% CI 0.87 to 0.96), but higher odds of hospitalisation (OR=1.20, 95% CI 1.15 to 1.26). AC versus AP was associated with lower odds of death (OR=0.93, 95% CI 0.87 to 0.98) and higher hospitalisation (OR=1.17, 95% CI 1.11 to 1.24). For DOACs versus warfarin, lower odds were observed for hospitalisation (OR=0.86, 95% CI 0.82 to 0.89) but not for death (OR=1.00, 95% CI 0.95 to 1.05). CONCLUSIONS: Pre-existing AT use may be associated with lower odds of COVID-19 death and, while not evidence of causality, provides further incentive to improve AT coverage for eligible individuals with AF.

Dating of a large tool assemblage at the Cooper's Ferry site (Idaho, USA) to ~15,785 cal yr B.P. extends the age of stemmed points in the Americas.

The timing and character of the Pleistocene peopling of the Americas are measured by the discovery of unequivocal artifacts from well-dated contexts. We report the discovery of a well-dated artifact assemblage containing 14 stemmed projectile points from the Cooper's Ferry site in western North America, dating to ~16,000 years ago. These stemmed points are several thousand years older than Clovis fluted points (~13,000 cal yr B.P.) and are ~2300 years older than stemmed points found previously at the site. These points date to the end of Marine Isotope Stage 2 when glaciers had closed off an interior land route into the Americas. This assemblage includes an array of stemmed projectile points that resemble pre-Jomon Late Upper Paleolithic tools from the northwestern Pacific Rim dating to ~20,000 to 19,000 years ago, leading us to hypothesize that some of the first technological traditions in the Americas may have originated in the region.

An open-source, expert-designed decision tree application to support accurate diagnosis of myeloid malignancies.

Accurate, reproducible diagnoses can be difficult to make in haemato-oncology due to multi-parameter clinical data, complex diagnostic criteria and time-pressured environments. We have designed a decision tree application (DTA) that reflects WHO diagnostic criteria to support accurate diagnoses of myeloid malignancies. The DTA returned the correct diagnoses in 94% of clinical cases tested. The DTA maintained a high level of accuracy in a second validation using artificially generated clinical cases. Optimisations have been made to the DTA based on the validations, and the revised version is now publicly available for use at http://bit.do/ADAtool.