Foresight-a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study.

BACKGROUND: An electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments). METHODS: Foresight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital [KCH], South London and Maudsley [SLaM], and the US Medical Information Mart for Intensive Care III [MIMIC-III]), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall. FINDINGS: Foresight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% [95% CI 91-100]) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required. INTERPRETATION: Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes. FUNDING: National Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.

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.

Diagnostic yield and limitations of in-hospital documentation in patients with epilepsy.

OBJECTIVE: To determine the diagnostic yield of in-hospital video-electroencephalography (EEG) monitoring to document seizures in patients with epilepsy. METHODS: Retrospective analysis of electronic seizure documentation at the University Hospital Freiburg (UKF) and at King's College London (KCL). Statistical assessment of the role of the duration of monitoring, and subanalyses on presurgical patient groups and patients undergoing reduction of antiseizure medication. RESULTS: Of more than 4800 patients with epilepsy undergoing in-hospital recordings at the two institutions since 2005, seizures with documented for 43% (KCL) and 73% (UKF).. Duration of monitoring was highly significantly associated with seizure recordings (p < .0001), and presurgical patients as well as patients with drug reduction had a significantly higher diagnostic yield (p < .0001). Recordings with a duration of >5 days lead to additional new seizure documentation in only less than 10% of patients. SIGNIFICANCE: There is a need for the development of new ambulatory monitoring strategies to document seizures for diagnostic and monitoring purposes for a relevant subgroup of patients with epilepsy in whom in-hospital monitoring fails to document seizures.

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.

Machine learning-enabled multitrust audit of stroke comorbidities using natural language processing.

BACKGROUND AND PURPOSE: With the increasing adoption of electronic records in the health system, machine learning-enabled techniques offer the opportunity for greater computer-assisted curation of these data for audit and research purposes. In this project, we evaluate the consistency of traditional curation methods used in routine clinical practice against a new machine learning-enabled tool, MedCAT, for the extraction of the stroke comorbidities recorded within the UK's Sentinel Stroke National Audit Programme (SSNAP) initiative. METHODS: A total of 2327 stroke admission episodes from three different National Health Service (NHS) hospitals, between January 2019 and April 2020, were included in this evaluation. In addition, current clinical curation methods (SSNAP) and the machine learning-enabled method (MedCAT) were compared against a subsample of 200 admission episodes manually reviewed by our study team. Performance metrics of sensitivity, specificity, precision, negative predictive value, and F1 scores are reported. RESULTS: The reporting of stroke comorbidities with current clinical curation methods is good for atrial fibrillation, hypertension, and diabetes mellitus, but poor for congestive cardiac failure. The machine learning-enabled method, MedCAT, achieved better performances across all four assessed comorbidities compared with current clinical methods, predominantly driven by higher sensitivity and F1 scores. CONCLUSIONS: We have shown machine learning-enabled data collection can support existing clinical and service initiatives, with the potential to improve the quality and speed of data extraction from existing clinical repositories. The scalability and flexibility of these new machine-learning tools, therefore, present an opportunity to revolutionize audit and research methods.

Regional performance variation in external validation of four prediction models for severity of COVID-19 at hospital admission: An observational multi-centre cohort study.

BACKGROUND: Prediction models should be externally validated to assess their performance before implementation. Several prediction models for coronavirus disease-19 (COVID-19) have been published. This observational cohort study aimed to validate published models of severity for hospitalized patients with COVID-19 using clinical and laboratory predictors. METHODS: Prediction models fitting relevant inclusion criteria were chosen for validation. The outcome was either mortality or a composite outcome of mortality and ICU admission (severe disease). 1295 patients admitted with symptoms of COVID-19 at Kings Cross Hospital (KCH) in London, United Kingdom, and 307 patients at Oslo University Hospital (OUH) in Oslo, Norway were included. The performance of the models was assessed in terms of discrimination and calibration. RESULTS: We identified two models for prediction of mortality (referred to as Xie and Zhang1) and two models for prediction of severe disease (Allenbach and Zhang2). The performance of the models was variable. For prediction of mortality Xie had good discrimination at OUH with an area under the receiver-operating characteristic (AUROC) 0.87 [95% confidence interval (CI) 0.79-0.95] and acceptable discrimination at KCH, AUROC 0.79 [0.76-0.82]. In prediction of severe disease, Allenbach had acceptable discrimination (OUH AUROC 0.81 [0.74-0.88] and KCH AUROC 0.72 [0.68-0.75]). The Zhang models had moderate to poor discrimination. Initial calibration was poor for all models but improved with recalibration. CONCLUSIONS: The performance of the four prediction models was variable. The Xie model had the best discrimination for mortality, while the Allenbach model had acceptable results for prediction of severe disease.

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.

Multi-domain clinical natural language processing with MedCAT: The Medical Concept Annotation Toolkit.

Electronic health records (EHR) contain large volumes of unstructured text, requiring the application of information extraction (IE) technologies to enable clinical analysis. We present the open source Medical Concept Annotation Toolkit (MedCAT) that provides: (a) a novel self-supervised machine learning algorithm for extracting concepts using any concept vocabulary including UMLS/SNOMED-CT; (b) a feature-rich annotation interface for customizing and training IE models; and (c) integrations to the broader CogStack ecosystem for vendor-agnostic health system deployment. We show improved performance in extracting UMLS concepts from open datasets (F1:0.448-0.738 vs 0.429-0.650). Further real-world validation demonstrates SNOMED-CT extraction at 3 large London hospitals with self-supervised training over ∼8.8B words from ∼17M clinical records and further fine-tuning with ∼6K clinician annotated examples. We show strong transferability (F1 > 0.94) between hospitals, datasets and concept types indicating cross-domain EHR-agnostic utility for accelerated clinical and research use cases.

Biological responses to COVID-19: Insights from physiological and blood biomarker profiles.

BACKGROUND: Understanding the spectrum and course of biological responses to coronavirus disease 2019 (COVID-19) may have important therapeutic implications. We sought to characterise biological responses among patients hospitalised with severe COVID-19 based on serial, routinely collected, physiological and blood biomarker values. METHODS AND FINDINGS: We performed a retrospective cohort study of 1335 patients hospitalised with laboratory-confirmed COVID-19 (median age 70 years, 56 % male), between 1st March and 30th April 2020. Latent profile analysis was performed on serial physiological and blood biomarkers. Patient characteristics, comorbidities and rates of death and admission to intensive care, were compared between the latent classes. A five class solution provided the best fit. Class 1 "Typical response" exhibited a moderately elevated and rising C-reactive protein (CRP), stable lymphopaenia, and the lowest rates of 14-day adverse outcomes. Class 2 "Rapid hyperinflammatory response" comprised older patients, with higher admission white cell and neutrophil counts, which declined over time, accompanied by a very high and rising CRP and platelet count, and exibited the highest mortality risk. Class 3 "Progressive inflammatory response" was similar to the typical response except for a higher and rising CRP, though similar mortality rate. Class 4 "Inflammatory response with kidney injury" had prominent lymphopaenia, moderately elevated (and rising) CRP, and severe renal failure. Class 5 "Hyperinflammatory response with kidney injury" comprised older patients, with a very high and rising CRP, and severe renal failure that attenuated over time. Physiological measures did not substantially vary between classes at baseline or early admission. CONCLUSIONS AND RELEVANCE: Our identification of five distinct classes of biomarker profiles provides empirical evidence for heterogeneous biological responses to COVID-19. Early hyperinflammatory responses and kidney injury may signify unique pathophysiology that requires targeted therapy.

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.

Technology-based interventions for mental health support after stroke: A systematic review of their acceptability and feasibility.

Mental health disturbances are common after stroke and linked to a slower recovery. Current face-to-face treatment options are costly and often inaccessible. Technology advances have made it possible to overcome some of these barriers to deliver technology-based mental health interventions remotely, but we do not know how acceptable and feasible they are. This systematic review aims to provide an examination of the acceptability and feasibility of technology-based mental health interventions provided to stroke patients and evaluate any barriers to their adoption. A total of 13 studies were included investigating interventions targeting non-specific mental health, depression or anxiety. The delivery technologies were: video conferencing, computer programmes, telephones, DVDs, CDs, robot-assisted devices, and personal digital assistants. Rates of refusal to participate were low (7.9-25%). Where satisfaction was reported, this was generally high. Many studies achieved high levels of adherence (up to 89.6%). This was lower for some technologies (e.g., robotic assistive devices). Where dropout occurred, this was for reasons including a decline in health as well as technical difficulties. Overall, the literature displays early evidence of using technology to deliver mental health interventions to patients with stroke. This review has identified factors that the design of future studies should take into consideration.

Angiotensin-converting enzyme inhibitors and angiotensin II receptor blockers are not associated with severe COVID-19 infection in a multi-site UK acute hospital trust.

AIMS: The SARS-CoV-2 virus binds to the angiotensin-converting enzyme 2 (ACE2) receptor for cell entry. It has been suggested that angiotensin-converting enzyme inhibitors (ACEi) and angiotensin II receptor blockers (ARB), which are commonly used in patients with hypertension or diabetes and may raise tissue ACE2 levels, could increase the risk of severe COVID-19 infection. METHODS AND RESULTS: We evaluated this hypothesis in a consecutive cohort of 1200 acute inpatients with COVID-19 at two hospitals with a multi-ethnic catchment population in London (UK). The mean age was 68 ± 17 years (57% male) and 74% of patients had at least one comorbidity. Overall, 415 patients (34.6%) reached the primary endpoint of death or transfer to a critical care unit for organ support within 21 days of symptom onset. A total of 399 patients (33.3%) were taking ACEi or ARB. Patients on ACEi/ARB were significantly older and had more comorbidities. The odds ratio for the primary endpoint in patients on ACEi and ARB, after adjustment for age, sex and co-morbidities, was 0.63 (95% confidence interval 0.47-0.84, P < 0.01). CONCLUSIONS: There was no evidence for increased severity of COVID-19 in hospitalised patients on chronic treatment with ACEi or ARB. A trend towards a beneficial effect of ACEi/ARB requires further evaluation in larger meta-analyses and randomised clinical trials.