Explore the vast range of titles available.

The emergence of large language models (LLMs) opens new horizons to leverage, often unused, information in clinical text. Our study aims to capitalise on this new potential. Specifically, we examine the utility of text embeddings generated by LLMs in predicting postoperative acute kidney injury (AKI) in paediatric cardiopulmonary bypass (CPB) patients using electronic health record (EHR) text, and propose methods for explaining their output. AKI could be a serious complication in paediatric CPB and its accurate prediction can significantly improve patient outcomes by enabling timely interventions. We evaluate various text embedding algorithms such as Doc2Vec, top-performing sentence transformers on Hugging Face, and commercial LLMs from Google and OpenAI. We benchmark the cross-validated performance of these ‘AI models’ against a ‘baseline model’ as well as an established clinically-defined ‘expert model’. The baseline model includes structured features, i.e., patient gender, age, height, body mass index and length of operation. The majority of AI models surpass, not only the baseline model, but also the expert model. An ensemble of AI and clinical-expert models improves discriminative performance by 23% compared to the baseline model. Consistency of patient clusters formed from AI-generated embeddings with clinical-expert clusters—measured via the adjusted rand index and adjusted mutual information metrics—illustrates the medical validity of LLM embeddings. We create a reverse mapping from the numeric embedding space to the natural-language domain via the embedding-based clusters, generating medical labels for the clusters in the process. We also use text-generating LLMs to summarise the differences between AI and expert clusters. Such ‘explainability’ outputs can increase medical practitioners’ trust in the AI applications, and help generate new hypotheses, e.g., by studying the association of cluster memberships and outcomes of interest.

Background For some SARS-CoV-2 survivors, recovery from the acute phase of the infection has been grueling with lingering effects. Many of the symptoms characterized as the post-acute sequelae of COVID-19 (PASC) could have multiple causes or are similarly seen in non-COVID patients. Accurate identification of PASC phenotypes will be important to guide future research and help the healthcare system focus its efforts and resources on adequately controlled age- and gender-specific sequelae of a COVID-19 infection. Methods In this retrospective electronic health record (EHR) cohort study, we applied a computational framework for knowledge discovery from clinical data, MLHO, to identify phenotypes that positively associate with a past positive reverse transcription-polymerase chain reaction (RT-PCR) test for COVID-19. We evaluated the post-test phenotypes in two temporal windows at 3–6 and 6–9 months after the test and by age and gender. Data from longitudinal diagnosis records stored in EHRs from Mass General Brigham in the Boston Metropolitan Area was used for the analyses. Statistical analyses were performed on data from March 2020 to June 2021. Study participants included over 96 thousand patients who had tested positive or negative for COVID-19 and were not hospitalized. Results We identified 33 phenotypes among different age/gender cohorts or time windows that were positively associated with past SARS-CoV-2 infection. All identified phenotypes were newly recorded in patients’ medical records 2 months or longer after a COVID-19 RT-PCR test in non-hospitalized patients regardless of the test result. Among these phenotypes, a new diagnosis record for anosmia and dysgeusia (OR 2.60, 95% CI [1.94–3.46]), alopecia (OR 3.09, 95% CI [2.53–3.76]), chest pain (OR 1.27, 95% CI [1.09–1.48]), chronic fatigue syndrome (OR 2.60, 95% CI [1.22–2.10]), shortness of breath (OR 1.41, 95% CI [1.22–1.64]), pneumonia (OR 1.66, 95% CI [1.28–2.16]), and type 2 diabetes mellitus (OR 1.41, 95% CI [1.22–1.64]) is one of the most significant indicators of a past COVID-19 infection. Additionally, more new phenotypes were found with increased confidence among the cohorts who were younger than 65. Conclusions The findings of this study confirm many of the post-COVID-19 symptoms and suggest that a variety of new diagnoses, including new diabetes mellitus and neurological disorder diagnoses, are more common among those with a history of COVID-19 than those without the infection. Additionally, more than 63% of PASC phenotypes were observed in patients under 65 years of age, pointing out the importance of vaccination to minimize the risk of debilitating post-acute sequelae of COVID-19 among younger adults.

Machine learning encompasses statistical approaches such as logistic regression (LR) through to more computationally complex models such as neural networks (NN). The aim of this study is to review current published evidence for performance from studies directly comparing logistic regression, and neural network classification approaches in medicine. A literature review was carried out to identify primary research studies which provided information regarding comparative area under the curve (AUC) values for the overall performance of both LR and NN for a defined clinical healthcare-related problem. Following an initial search, articles were reviewed to remove those that did not meet the criteria and performance metrics were extracted from the included articles. Teh initial search revealed 114 articles; 21 studies were included in the study. In 13/21 (62%) of cases, NN had a greater AUC compared to LR, but in most the difference was small and unlikely to be of clinical significance; (unweighted mean difference in AUC 0.03 (95% CI 0-0.06) in favour of NN versus LR. In the majority of cases examined across a range of clinical settings, LR models provide reasonable performance that is only marginally improved using more complex methods such as NN. In many circumstances, the use of a relatively simple LR model is likely to be adequate for real-world needs but in specific circumstances in which large amounts of data are available, and where even small increases in performance would provide significant management value, the application of advanced analytic tools such as NNs may be indicated.

ObjectivesIn the ever-evolving landscape of healthcare, the integration of digital systems and medical devices is increasingly important for modernising healthcare delivery. However, the acceptance and adoption of emerging technologies by healthcare staff present challenges. The purpose of this research was to apply relevant knowledge to inform and improve a conceptual framework (ARC): early exploration and agile adoption of emerging healthcare technology. We report on an expert-led Delphi study to evaluate consensus regarding the framework.MethodThe ARC conceptual framework, presented as four successive phases: imagine, educate, validate and score, was evaluated by 23 experts over two rounds. Experts first agreed/disagreed with 31 enabling statements relating to the early exploration and evaluation of new technology. The expert panel made recommendations (n=20), which were incorporated into round 2 with a checklist to evaluate the potential of a new technology.ResultsAll participating experts completed round 1, and 13 completed round 2. Consensus (defined as >75% agreement) was achieved for 93.4% (n=57) of statements, with consensus without exception achieved for 34.4% (n=21) items and 16 new items added to the improved ARC framework, including on the appropriate use of simulation studies.DiscussionThe main findings highlight the importance of demonstration spaces, time in clinical environments with clinical teams, data-driven benefits and structured debriefs with staff.ConclusionA Delphi approach achieved expert consensus regarding the ARC framework for engaging with new technology and preparing the healthcare workforce for its use. Further advocacy is required to negotiate stakeholder involvement and interdisciplinary cooperation.

Additional sources of pediatric epidemiological and clinical data are needed to efficiently study COVID-19 in children and youth and inform infection prevention and clinical treatment of pediatric patients. To describe international hospitalization trends and key epidemiological and clinical features of children and youth with COVID-19. This retrospective cohort study included pediatric patients hospitalized between February 2 and October 10, 2020. Patient-level electronic health record (EHR) data were collected across 27 hospitals in France, Germany, Spain, Singapore, the UK, and the US. Patients younger than 21 years who tested positive for COVID-19 and were hospitalized at an institution participating in the Consortium for Clinical Characterization of COVID-19 by EHR were included in the study. Patient characteristics, clinical features, and medication use. There were 347 males (52%; 95% CI, 48.5-55.3) and 324 females (48%; 95% CI, 44.4-51.3) in this study's cohort. There was a bimodal age distribution, with the greatest proportion of patients in the 0- to 2-year (199 patients [30%]) and 12- to 17-year (170 patients [25%]) age range. Trends in hospitalizations for 671 children and youth found discrete surges with variable timing across 6 countries. Data from this cohort mirrored national-level pediatric hospitalization trends for most countries with available data, with peaks in hospitalizations during the initial spring surge occurring within 23 days in the national-level and 4CE data. A total of 27 364 laboratory values for 16 laboratory tests were analyzed, with mean values indicating elevations in markers of inflammation (C-reactive protein, 83 mg/L; 95% CI, 53-112 mg/L; ferritin, 417 ng/mL; 95% CI, 228-607 ng/mL; and procalcitonin, 1.45 ng/mL; 95% CI, 0.13-2.77 ng/mL). Abnormalities in coagulation were also evident (D-dimer, 0.78 ug/mL; 95% CI, 0.35-1.21 ug/mL; and fibrinogen, 477 mg/dL; 95% CI, 385-569 mg/dL). Cardiac troponin, when checked (n = 59), was elevated (0.032 ng/mL; 95% CI, 0.000-0.080 ng/mL). Common complications included cardiac arrhythmias (15.0%; 95% CI, 8.1%-21.7%), viral pneumonia (13.3%; 95% CI, 6.5%-20.1%), and respiratory failure (10.5%; 95% CI, 5.8%-15.3%). Few children were treated with COVID-19-directed medications. This study of EHRs of children and youth hospitalized for COVID-19 in 6 countries demonstrated variability in hospitalization trends across countries and identified common complications and laboratory abnormalities in children and youth with COVID-19 infection. Large-scale informatics-based approaches to integrate and analyze data across health care systems complement methods of disease surveillance and advance understanding of epidemiological and clinical features associated with COVID-19 in children and youth.

Surgical repair of cardiac defects using cardiopulmonary bypass (CPB) in patients with vein of Galen malformation (VGM), presents a serious challenge to the extent that it has been reported only once before. Multiple case reports describe poor outcome, or the use of hybrid procedures avoiding CPB and recommend conservative management until the VGM has been eradicated. Of particular concern is the high blood flow shunting through the VGM which may be so significant that it might reduce cerebral and somatic perfusion to the extent that hypoxic ischaemic injury is induced.Using a combination of high cardiac index and pH-stat blood gas management maximises cerebral protection whilst cooling the patient to 18°C allows Deep Hypothermic Circulatory Arrest (DHCA) facilitated repair of the cardiac lesion to be undertaken safely. By applying resistance to the venous drainage, a positive central venous pressure (CVP) can be maintained avoiding decompression of the central veins which would otherwise exacerbate the cerebral shunt flow.Using a case study of a 23 day old female neonate with dissection of the patent ductus arteriosus (PDA) and pulmonary artery in combination with VGM, we present the key criteria for successful management and the physiological mechanisms.

Given the emphasis placed on technology by the Department of Health and the recent high profile Topol review, the role of healthcare data is set to become highly prevalent in the coming years. To bridge the gap between the traditional clinical-academic and statistician roles in translational research, the skillsets of interdisciplinary ‘clinical informaticians’ are required. This new role requires staff to be conversant in high level programming languages, such as R, python and SQL (the lingua franca of data science), whilst retaining their domain-specific knowledge and an active academic presence within their clinical specialty.To assess the feasibility of upskilling clinical staff into clinical informatician roles, we present case studies of clinicians with little-to-no formal experience of programming, statistics, and data science, who undertook this transition with the Digital Research Environment (DRE). In particular, this transition required a grounding in database extraction, data manipulation, and statistical modelling, replicating the workflow expected in a data-rich research setting.Each case study suggested that online content (tutorials, articles, open source code) provided a solid background in basic data science and functional programming. The benefits of pursuing open-source languages were most keenly observed in question and answer forums, tutorials, and open sessions, with full-text articles and books freely available. Furthermore, paid online courses were abundant, providing high-quality methodological workflows for all aspects of data science and analysis, including advanced topics such as machine learning and deep learning.We found that within 18 months, the staff were able to integrate typical data science workflows within their research programmes. The combination of clinical knowledge and data science will allow the maximum possible value to be extracted from future clinical studies and databases that host increasingly rich EPR datasets, thus further supporting evidence-based improvements to the standard of care in paediatrics.

The end point of clinical research is often considered to be the publication of peer reviewed data and results. Although an effective method for communication with a technical audience, publications can often appear impenetrable for non-technical audiences and are typically unable to deliver a clear method for implementation of the research output. Web applications provide a potential solution for data-driven research and are able to deliver accessible, interactive interfaces for wide audiences. When considering the wealth of data collected in clinical systems such as Epic, the potential for delivering web-based hospital tools derived from GOSH research output is substantial.EPR data were sourced from legacy hospital systems and integrated with patient-level outcome data, including risk of death, and renal failure outcome measurements in the GOSH Digital Research Environment (DRE). These data were then modelled using logistic regression models written in the open source Bayesian modelling platform, Stan, to predict patient outcome. Finally, the project’s analysis workflow, written in the R language, was ported to a dashboard-style R Shiny web app using the Shiny Dashboard package.The resulting modular web app was capable of delivering each element of the project in an accessible manner, without sacrificing the detail or transparency required for clinical research. Each tab of the web app represented a separate step, presenting a high-level project overview, interactive data visualisations, modelling teaching tools, an interactive, dynamic, and interpretable model estimation module, a patient outcome prediction module, customization options, and a tab that renders the app’s source code, encouraging reproducibility. The app was written to be fully compatible with research data provisioned through the DRE and modular enough to be ported to prospective research projects.This work demonstrates a proof-of-concept open source Shiny web app framework for delivering interactive and predictive analytics from clinical research projects.

IntroductionPrior to the rollout of the GOSH EPR system, multiple hospital databases provided fragmentary data from the clinical record. To support research in GOSH and the ICH, these data will all need to be brought together with data from the EPR to provide a complete uninterrupted clinical research dataset suitable for analysis. This need will be particularly acute for research undertaken on rare diseases where accumulating a sufficient cohort of patients is often challenging. In addition, work to harmonise with external data sources would enable more ambitious multi-site research.MethodThe Digital Research Environment (DRE) Team bring together a core dataset of research–relevant clinical data comprising administrative data (e.g. patient demographics, ward stays) and clinical observations (e.g. lab results, vital signs, diagnoses) onto which we have mapped data from multiple legacy systems and the EPR. We have mapped these Research Data Views (RDVs) onto the FHIR standard for clinical data interoperability to allow harmonisation with data from other sources (such as other hospitals).ResultsWe have complete extractions from multiple legacy systems to produce RDVs with data back to 1st January 2000. We are now actively extracting data from the EPR aligning with these RDVs and thus are providing a continuous clinical research dataset across EPR go-live. We have >102 million events for >400,000 patients at GOSH. These RDVs are now available via the DRE Data Selection Tool, along with complete metadata for all fields, for provision into our Research Platform for analysis.ConclusionWe have implemented a resource to put all research-relevant clinical data right at the fingertips of researchers from GOSH, ICH and beyond. This will feed into research projects big and small, empowering researchers to focus on the science, rather than the manual collection of data.

Coincident with the tsunami of COVID-19–related publications, there has been a surge of studies using real-world data, including those obtained from the electronic health record (EHR). Unfortunately, several of these high-profile publications were retracted because of concerns regarding the soundness and quality of the studies and the EHR data they purported to analyze. These retractions highlight that although a small community of EHR informatics experts can readily identify strengths and flaws in EHR-derived studies, many medical editorial teams and otherwise sophisticated medical readers lack the framework to fully critically appraise these studies. In addition, conventional statistical analyses cannot overcome the need for an understanding of the opportunities and limitations of EHR-derived studies. We distill here from the broader informatics literature six key considerations that are crucial for appraising studies utilizing EHR data: data completeness, data collection and handling (eg, transformation), data type (ie, codified, textual), robustness of methods against EHR variability (within and across institutions, countries, and time), transparency of data and analytic code, and the multidisciplinary approach. These considerations will inform researchers, clinicians, and other stakeholders as to the recommended best practices in reviewing manuscripts, grants, and other outputs from EHR-data derived studies, and thereby promote and foster rigor, quality, and reliability of this rapidly growing field.