Venous thromboembolism prevention program implementation in a community oncology practice: a cohort study.

Background: While national guidelines recommend Venous Thromboembolism (VTE) risk assessment in cancer outpatients and consideration of pharmacologic prophylaxis in high-risk patients, prophylaxis rates are low in community oncology practices. A successful model for guideline implementation (the Vermont Model, VM) is validated in an academic tertiary oncology setting. We undertook an implementation study to determine the success of this model in a multi-site community oncology practice. The study objectives were to: 1) adapt the VM to the community practice setting; 2) implement the adapted VM into practice; and 3) evaluate clinical and implementation outcomes. Methods: The study was carried out in three phases: (1) Pre-implementation, a multidisciplinary team addressed the need to adapt the VM to the local context including electronic medical record (EMR) optimisation and clinician education; (2) implementation of the strategies adapted to the local context, informed by VM and adapted based on stakeholder feedback; (3) prospective evaluation of clinical and implementation outcomes at six months after implementation. Findings: Following creation of a comprehensive initiation roadmap for the adaptation of VM program to the community practice, 302 cancer outpatients initiating new treatment met inclusion criteria over a 6 month implementation period. VTE risk education was provided to 100% of patients, and 98% (296) of patients received a VTE risk assessment. Of 52 patients (18%) who scored as high risk based on a modified Khorana (Protecht) score, 14 (27%) initiated prophylaxis. Barriers to program adaptation included EMR optimization challenges and practice-level responsibility assignment, time constraints, concern about potential drug interactions, and financial & insurance issues. Interpretation: Implementation of a multidisciplinary VTE prevention model in the community-based oncology setting successfully increased VTE education and risk assessment rates. AC prophylaxis rates were modestly increased, highlighting the need to understand and address barriers to anticoagulant prophylaxis prescribing in this setting. Funding: Northern New England Clinical Oncology Society Research Funding Program.

Assessing the Performance of Machine Learning Methods Trained on Public Health Observational Data: A Case Study From COVID-19.

From early in the coronavirus disease 2019 (COVID-19) pandemic, there was interest in using machine learning methods to predict COVID-19 infection status based on vocal audio signals, for example, cough recordings. However, early studies had limitations in terms of data collection and of how the performances of the proposed predictive models were assessed. This article describes how these limitations have been overcome in a study carried out by the Turing-RSS Health Data Laboratory and the UK Health Security Agency. As part of the study, the UK Health Security Agency collected a dataset of acoustic recordings, SARS-CoV-2 infection status and extensive study participant meta-data. This allowed us to rigorously assess state-of-the-art machine learning techniques to predict SARS-CoV-2 infection status based on vocal audio signals. The lessons learned from this project should inform future studies on statistical evaluation methods to assess the performance of machine learning techniques for public health tasks.

Bayesian Lesion Estimation with a Structured Spike-and-Slab Prior.

Neural demyelination and brain damage accumulated in white matter appear as hyperintense areas on T2-weighted MRI scans in the form of lesions. Modeling binary images at the population level, where each voxel represents the existence of a lesion, plays an important role in understanding aging and inflammatory diseases. We propose a scalable hierarchical Bayesian spatial model, called BLESS, capable of handling binary responses by placing continuous spike-and-slab mixture priors on spatially-varying parameters and enforcing spatial dependency on the parameter dictating the amount of sparsity within the probability of inclusion. The use of mean-field variational inference with dynamic posterior exploration, which is an annealing-like strategy that improves optimization, allows our method to scale to large sample sizes. Our method also accounts for underestimation of posterior variance due to variational inference by providing an approximate posterior sampling approach based on Bayesian bootstrap ideas and spike-and-slab priors with random shrinkage targets. Besides accurate uncertainty quantification, this approach is capable of producing novel cluster size based imaging statistics, such as credible intervals of cluster size, and measures of reliability of cluster occurrence. Lastly, we validate our results via simulation studies and an application to the UK Biobank, a large-scale lesion mapping study with a sample size of 40,000 subjects.

Characterising the genetic architecture of changes in adiposity during adulthood using electronic health records.

Obesity is a heritable disease, characterised by excess adiposity that is measured by body mass index (BMI). While over 1,000 genetic loci are associated with BMI, less is known about the genetic contribution to adiposity trajectories over adulthood. We derive adiposity-change phenotypes from 24.5 million primary-care health records in over 740,000 individuals in the UK Biobank, Million Veteran Program USA, and Estonian Biobank, to discover and validate the genetic architecture of adiposity trajectories. Using multiple BMI measurements over time increases power to identify genetic factors affecting baseline BMI by 14%. In the largest reported genome-wide study of adiposity-change in adulthood, we identify novel associations with BMI-change at six independent loci, including rs429358 (APOE missense variant). The SNP-based heritability of BMI-change (1.98%) is 9-fold lower than that of BMI. The modest genetic correlation between BMI-change and BMI (45.2%) indicates that genetic studies of longitudinal trajectories could uncover novel biology of quantitative traits in adulthood.

A large-scale and PCR-referenced vocal audio dataset for COVID-19.

The UK COVID-19 Vocal Audio Dataset is designed for the training and evaluation of machine learning models that classify SARS-CoV-2 infection status or associated respiratory symptoms using vocal audio. The UK Health Security Agency recruited voluntary participants through the national Test and Trace programme and the REACT-1 survey in England from March 2021 to March 2022, during dominant transmission of the Alpha and Delta SARS-CoV-2 variants and some Omicron variant sublineages. Audio recordings of volitional coughs, exhalations, and speech were collected in the 'Speak up and help beat coronavirus' digital survey alongside demographic, symptom and self-reported respiratory condition data. Digital survey submissions were linked to SARS-CoV-2 test results. The UK COVID-19 Vocal Audio Dataset represents the largest collection of SARS-CoV-2 PCR-referenced audio recordings to date. PCR results were linked to 70,565 of 72,999 participants and 24,105 of 25,706 positive cases. Respiratory symptoms were reported by 45.6% of participants. This dataset has additional potential uses for bioacoustics research, with 11.3% participants self-reporting asthma, and 27.2% with linked influenza PCR test results.

Development and validation of a risk model for hospital-acquired venous thrombosis: the Medical Inpatients Thrombosis and Hemostasis study.

BACKGROUND: Regulatory organizations recommend assessing hospital-acquired (HA) venous thromboembolism (VTE) risk for medical inpatients. OBJECTIVES: To develop and validate a risk assessment model (RAM) for HA-VTE in medical inpatients using objective and assessable risk factors knowable at admission. METHODS: The development cohort included people admitted to medical services at the University of Vermont Medical Center (Burlington, Vermont) between 2010 and 2019, and the validation cohorts included people admitted to Hennepin County Medical Center (Minneapolis, Minnesota), University of Michigan Medical Center (Ann Arbor, Michigan), and Harris Health Systems (Houston, Texas). Individuals with VTE at admission, aged <18 years, and admitted for <1 midnight were excluded. We used a Bayesian penalized regression technique to select candidate HA-VTE risk factors for final inclusion in the RAM. RESULTS: The development cohort included 60 633 admissions and 227 HA-VTE, and the validation cohorts included 111 269 admissions and 651 HA-VTE. Seven HA-VTE risk factors with t statistics ≥1.5 were included in the RAM: history of VTE, low hemoglobin level, elevated creatinine level, active cancer, hyponatremia, increased red cell distribution width, and malnutrition. The areas under the receiver operating characteristic curve and calibration slope were 0.72 and 1.10, respectively. The areas under the receiver operating characteristic curve and calibration slope were 0.70 and 0.93 at Hennepin County Medical Center, 0.70 and 0.87 at the University of Michigan Medical Center, and 0.71 and 1.00 at Harris Health Systems, respectively. The RAM performed well stratified by age, sex, and race. CONCLUSION: We developed and validated a RAM for HA-VTE in medical inpatients. By quantifying risk, clinicians can determine the potential benefits of measures to reduce HA-VTE.

Age-dependent topic modeling of comorbidities in UK Biobank identifies disease subtypes with differential genetic risk.

The analysis of longitudinal data from electronic health records (EHRs) has the potential to improve clinical diagnoses and enable personalized medicine, motivating efforts to identify disease subtypes from patient comorbidity information. Here we introduce an age-dependent topic modeling (ATM) method that provides a low-rank representation of longitudinal records of hundreds of distinct diseases in large EHR datasets. We applied ATM to 282,957 UK Biobank samples, identifying 52 diseases with heterogeneous comorbidity profiles; analyses of 211,908 All of Us samples produced concordant results. We defined subtypes of the 52 heterogeneous diseases based on their comorbidity profiles and compared genetic risk across disease subtypes using polygenic risk scores (PRSs), identifying 18 disease subtypes whose PRS differed significantly from other subtypes of the same disease. We further identified specific genetic variants with subtype-dependent effects on disease risk. In conclusion, ATM identifies disease subtypes with differential genome-wide and locus-specific genetic risk profiles.

Optimal strategies for learning multi-ancestry polygenic scores vary across traits.

Polygenic scores (PGSs) are individual-level measures that aggregate the genome-wide genetic predisposition to a given trait. As PGS have predominantly been developed using European-ancestry samples, trait prediction using such European ancestry-derived PGS is less accurate in non-European ancestry individuals. Although there has been recent progress in combining multiple PGS trained on distinct populations, the problem of how to maximize performance given a multiple-ancestry cohort is largely unexplored. Here, we investigate the effect of sample size and ancestry composition on PGS performance for fifteen traits in UK Biobank. For some traits, PGS estimated using a relatively small African-ancestry training set outperformed, on an African-ancestry test set, PGS estimated using a much larger European-ancestry only training set. We observe similar, but not identical, results when considering other minority-ancestry groups within UK Biobank. Our results emphasise the importance of targeted data collection from underrepresented groups in order to address existing disparities in PGS performance.

Development of a computable phenotype using electronic health records for venous thromboembolism in medical inpatients: the Medical Inpatient Thrombosis and Hemostasis study.

Background: Accurate and efficient methods to identify venous thromboembolism (VTE) events in hospitalized people are needed to support large-scale studies. Validated computable phenotypes using a specific combination of discrete, searchable elements in electronic health records to identify VTE and distinguish between hospital-acquired (HA)-VTE and present-on-admission (POA)-VTE would greatly facilitate the study of VTE, obviating the need for chart review. Objectives: To develop and validate computable phenotypes for POA- and HA-VTE in adults hospitalized for medical reasons. Methods: The population included admissions to medical services from 2010 to 2019 at an academic medical center. POA-VTE was defined as VTE diagnosed within 24 hours of admission, and HA-VTE as VTE identified more than 24 hours after admission. Using discharge diagnosis codes, present-on-admission flags, imaging procedures, and medication administration records, we iteratively developed computable phenotypes for POA-VTE and HA-VTE. We assessed the performance of the phenotypes using manual chart review and survey methodology. Results: Among 62,468 admissions, 2693 had any VTE diagnosis code. Using survey methodology, 230 records were reviewed to validate the computable phenotypes. Based on the computable phenotypes, the incidence of POA-VTE was 29.4 per 1000 admissions and that of HA-VTE was 3.6 per 1000 admissions. The POA-VTE computable phenotype had positive predictive value and sensitivity of 88.8% (95% CI, 79.8%-94.0%) and 99.1% (95% CI, 94.0%- 99.8%), respectively. Corresponding values for the HA-VTE computable phenotype were 84.2% (95% CI, 60.8%-94.8%) and 72.3% (95% CI, 40.9%-90.8%). Conclusion: We developed computable phenotypes for HA-VTE and POA-VTE with adequate positive predictive value and sensitivity. This phenotype can be used in electronic health record data-based research.

Direct Oral Anticoagulants vs Low-Molecular-Weight Heparin and Recurrent VTE in Patients With Cancer: A Randomized Clinical Trial.

Importance: In patients with cancer who have venous thromboembolism (VTE) events, long-term anticoagulation with low-molecular-weight heparin (LMWH) is recommended to prevent recurrent VTE. The effectiveness of a direct oral anticoagulant (DOAC) compared with LMWH for preventing recurrent VTE in patients with cancer is uncertain. Objective: To evaluate DOACs, compared with LMWH, for preventing recurrent VTE and for rates of bleeding in patients with cancer following an initial VTE event. Design, Setting, and Participants: Unblinded, comparative effectiveness, noninferiority randomized clinical trial conducted at 67 oncology practices in the US that enrolled 671 patients with cancer (any invasive solid tumor, lymphoma, multiple myeloma, or chronic lymphocytic leukemia) who had a new clinical or radiological diagnosis of VTE. Enrollment occurred from December 2016 to April 2020. Final follow-up was in November 2020. Intervention: Participants were randomized in a 1:1 ratio to either a DOAC (n = 335) or LMWH (n = 336) and were followed up for 6 months or until death. Physicians and patients selected any DOAC or any LMWH (or fondaparinux) and physicians selected drug doses. Main Outcomes and Measures: The primary outcome was the recurrent VTE rate at 6 months. Noninferiority of anticoagulation with a DOAC vs LMWH was defined by the upper limit of the 1-sided 95% CI for the difference of a DOAC relative to LMWH of less than 3% in the randomized cohort that received at least 1 dose of assigned treatment. The 6 prespecified secondary outcomes included major bleeding, which was assessed using a 2.5% noninferiority margin. Results: Between December 2016 and April 2020, 671 participants were randomized and 638 (95%) completed the trial (median age, 64 years; 353 women [55%]). Among those randomized to a DOAC, 330 received at least 1 dose. Among those randomized to LMWH, 308 received at least 1 dose. Rates of recurrent VTE were 6.1% in the DOAC group and 8.8% in the LMWH group (difference, -2.7%; 1-sided 95% CI, -100% to 0.7%) consistent with the prespecified noninferiority criterion. Of 6 prespecified secondary outcomes, none were statistically significant. Major bleeding occurred in 5.2% of participants in the DOAC group and 5.6% in the LMWH group (difference, -0.4%; 1-sided 95% CI, -100% to 2.5%) and did not meet the noninferiority criterion. Severe adverse events occurred in 33.8% of participants in the DOAC group and 35.1% in the LMWH group. The most common serious adverse events were anemia and death. Conclusions and Relevance: Among adults with cancer and VTE, DOACs were noninferior to LMWH for preventing recurrent VTE over 6-month follow-up. These findings support use of a DOAC to prevent recurrent VTE in patients with cancer. Trial Registration: ClinicalTrials.gov Identifier: NCT02744092.

Comparison of machine learning techniques in prediction of mortality following cardiac surgery: analysis of over 220 000 patients from a large national database.

OBJECTIVES: To perform a systematic comparison of in-hospital mortality risk prediction post-cardiac surgery, between the predominant scoring system-European System for Cardiac Operative Risk Evaluation (EuroSCORE) II, logistic regression (LR) retrained on the same variables and alternative machine learning techniques (ML)-random forest (RF), neural networks (NN), XGBoost and weighted support vector machine. METHODS: Retrospective analyses of prospectively routinely collected data on adult patients undergoing cardiac surgery in the UK from January 2012 to March 2019. Data were temporally split 70:30 into training and validation subsets. Mortality prediction models were created using the 18 variables of EuroSCORE II. Comparisons of discrimination, calibration and clinical utility were then conducted. Changes in model performance, variable-importance over time and hospital/operation-based model performance were also reviewed. RESULTS: Of the 227 087 adults who underwent cardiac surgery during the study period, there were 6258 deaths (2.76%). In the testing cohort, there was an improvement in discrimination [XGBoost (95% confidence interval (CI) area under the receiver operator curve (AUC), 0.834-0.834, F1 score, 0.276-0.280) and RF (95% CI AUC, 0.833-0.834, F1, 0.277-0.281)] compared with EuroSCORE II (95% CI AUC, 0.817-0.818, F1, 0.243-0.245). There was no significant improvement in calibration with ML and retrained-LR compared to EuroSCORE II. However, EuroSCORE II overestimated risk across all deciles of risk and over time. The calibration drift was lowest in NN, XGBoost and RF compared with EuroSCORE II. Decision curve analysis showed XGBoost and RF to have greater net benefit than EuroSCORE II. CONCLUSIONS: ML techniques showed some statistical improvements over retrained-LR and EuroSCORE II. The clinical impact of this improvement is modest at present. However the incorporation of additional risk factors in future studies may improve upon these findings and warrants further study.

Statistical inference with exchangeability and martingales.

In this paper, we start by reviewing exchangeability and its relevance to the Bayesian approach. We highlight the predictive nature of Bayesian models and the symmetry assumptions implied by beliefs of an underlying exchangeable sequence of observations. By taking a closer look at the Bayesian bootstrap, the parametric bootstrap of Efron and a version of Bayesian thinking about inference uncovered by Doob based on martingales, we introduce a parametric Bayesian bootstrap. Martingales play a fundamental role. Illustrations are presented as is the relevant theory. This article is part of the theme issue 'Bayesian inference: challenges, perspectives, and prospects'.

Generating the Right Evidence at the Right Time: Principles of a New Class of Flexible Augmented Clinical Trial Designs.

To support informed decision making, clear descriptions of the beneficial and harmful effects of a treatment are needed by various stakeholders. The current paradigm is to generate evidence sequentially through different experiments. However, data generated later, perhaps through observational studies, can be difficult to compare with earlier randomized trial data, resulting in confusion in understanding and interpretation of treatment effects. Moreover, the scientific questions these later experiments can serve to answer often remain vague. We propose Flexible Augmented Clinical Trial for Improved eVidence gEneration (FACTIVE), a new class of study designs enabling flexible augmentation of confirmatory randomized controlled trials with concurrent and close-to-real-world elements. Our starting point is to use clearly defined objectives for evidence generation, which are formulated through early discussion with health technology assessment (HTA) bodies and are additional to regulatory requirements for authorization of a new treatment. These enabling designs facilitate estimation of certain well-defined treatment effects in the confirmatory part and other complementary treatment effects in a concurrent real-world part. Each stakeholder should use the evidence that is relevant within their own decision-making framework. High quality data are generated under one single protocol and the use of randomization ensures rigorous statistical inference and interpretation within and between the different parts of the experiment. Evidence for the decision making of HTA bodies could be available earlier than is currently the case.

The relative risk of bleeding after medical hospitalization: the medical inpatient thrombosis and hemorrhage study.

BACKGROUND: Clinically relevant bleeding risk in discharged medical patients is underestimated and leads to rehospitalization, morbidity, and mortality. Studies assessing this risk are lacking. OBJECTIVE: The aim of this study was to develop and validate a computable phenotype for clinically relevant bleeding using electronic health record (EHR) data and quantify the relative and absolute risks of this bleeding after medical hospitalization. METHODS: We conducted an observational cohort study of people receiving their primary care at sites affiliated with an academic medical center in northwest Vermont, United States. We developed a computable phenotype using EHR data (diagnosis codes, procedure codes, laboratory, and transfusion data) and validated it by manual chart review. Cox proportional hazard models with hospitalization modeled as a time-varying covariate were used to estimate clinically relevant bleeding risk. RESULTS: The computable phenotype had a positive predictive value of 80% and a negative predictive value of 99%. The bleeding rate in individuals with no medical hospitalizations in the past 3 months was 2.9 per 1000 person-years versus 98.9 per 1000 person-years in those who were discharged in the past 3 months. This translates into a hazard ratio (95% CI) of clinically relevant bleeding of 22.9 (18.9, 27.7), 13.0 (10.0, 16.9), and 6.8 (4.7, 9.8) over the first, second, and third months after discharge, respectively. CONCLUSION: We developed and validated a computable phenotype for clinically relevant bleeding and determined its relative and absolute risk in the 3 months after medical hospitalization discharge. The high rates of bleeding observed underscore the clinical importance of capturing and further studying bleeding after medical discharge.

A spatio-temporal framework for modelling wastewater concentration during the COVID-19 pandemic.

The potential utility of wastewater-based epidemiology as an early warning tool has been explored widely across the globe during the current COVID-19 pandemic. Methods to detect the presence of SARS-CoV-2 RNA in wastewater were developed early in the pandemic, and extensive work has been conducted to evaluate the relationship between viral concentration and COVID-19 case numbers at the catchment areas of sewage treatment works (STWs) over time. However, no attempt has been made to develop a model that predicts wastewater concentration at fine spatio-temporal resolutions covering an entire country, a necessary step towards using wastewater monitoring for the early detection of local outbreaks. We consider weekly averages of flow-normalised viral concentration, reported as the number of SARS-CoV-2N1 gene copies per litre (gc/L) of wastewater available at 303 STWs over the period between 1 June 2021 and 30 March 2022. We specify a spatially continuous statistical model that quantifies the relationship between weekly viral concentration and a collection of covariates covering socio-demographics, land cover and virus associated genomic characteristics at STW catchment areas while accounting for spatial and temporal correlation. We evaluate the model's predictive performance at the catchment level through 10-fold cross-validation. We predict the weekly viral concentration at the population-weighted centroid of the 32,844 lower super output areas (LSOAs) in England, then aggregate these LSOA predictions to the Lower Tier Local Authority level (LTLA), a geography that is more relevant to public health policy-making. We also use the model outputs to quantify the probability of local changes of direction (increases or decreases) in viral concentration over short periods (e.g. two consecutive weeks). The proposed statistical framework can predict SARS-CoV-2 viral concentration in wastewater at high spatio-temporal resolution across England. Additionally, the probabilistic quantification of local changes can be used as an early warning tool for public health surveillance.