Model Development Data Research Articles

Groundwaterscapes: A Global Classification and Mapping of Groundwater's Large‐Scale Socioeconomic, Ecological, and Earth System Functions

AbstractGroundwater is a dynamic component of the global water cycle with important social, economic, ecological, and Earth system functions. We present a new global classification and mapping of groundwater systems, which we call groundwaterscapes, that represent predominant configurations of large‐scale groundwater system functions. We identify and map 15 groundwaterscapes which offer a new lens to conceptualize, study, model, and manage groundwater. Groundwaterscapes are derived using a novel application of sequenced self‐organizing maps that capture patterns in groundwater system functions at the grid cell level (∼10 km), including groundwater‐dependent ecosystem type and density, storage capacity, irrigation, safe drinking water access, and national governance. All large aquifer systems of the world are characterized by multiple groundwaterscapes, highlighting the pitfalls of treating these groundwater bodies as lumped systems in global assessments. We evaluate the distribution of Global Groundwater Monitoring Network wells across groundwaterscapes and find that industrial agricultural regions are disproportionately monitored, while several groundwaterscapes have next to no monitoring wells. This disparity undermines the ability to understand system dynamics across the full range of settings that characterize groundwater systems globally. We argue that groundwaterscapes offer a conceptual and spatial tool to guide model development, hypothesis testing, and future data collection initiatives to better understand groundwater's embeddedness within social‐ecological systems at the global scale.

A review of geospatial exposure models and approaches for health data integration

Abstract Background Geospatial methods are common in environmental exposure assessments and increasingly integrated with health data to generate comprehensive models of environmental impacts on public health. Objective Our objective is to review geospatial exposure models and approaches for health data integration in environmental health applications. Methods We conduct a literature review and synthesis. Results First, we discuss key concepts and terminology for geospatial exposure data and models. Second, we provide an overview of workflows in geospatial exposure model development and health data integration. Third, we review modeling approaches, including proximity-based, statistical, and mechanistic approaches, across diverse exposure types, such as air quality, water quality, climate, and socioeconomic factors. For each model type, we provide descriptions, general equations, and example applications for environmental exposure assessment. Fourth, we discuss the approaches used to integrate geospatial exposure data and health data, such as methods to link data sources with disparate spatial and temporal scales. Fifth, we describe the landscape of open-source tools supporting these workflows.

Integrated Multiphase-Flow Modeling Technique Yields Accurate Downhole Pressure Predictions

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 214855, “Integrated Multiphase-Flow Modeling for Downhole Pressure Predictions,” by Abdullah Alkhezzi and Yilin Fan, SPE, Colorado School of Mines. The paper has not been peer reviewed. _ This work presents an integrated multiphase flow model for downhole pressure predictions. The aim of the model is to produce more-accurate downhole pressure predictions under wide flowing conditions while maintaining a simple form. As a component of the integrated model, an improved two-fluid model for segregated flow is proposed. Results of the two-fluid segregated model are compared with five state-of-the-art existing models, while results of the integrated model are compared with three models. Introduction Throughout the life of the well, knowing bottomhole flowing pressure (Pwf) and the pressure profile of the wellbore are of great significance. Unfortunately, deploying downhole pressure gauges to obtain Pwfreadings is often not economical or practical. The common practice is to apply hydraulic models to predict Pwfgiven surface measurements. The prediction of such behavior is simple when dealing with single-phase fluid flow. Unfortunately, this condition is rare in the petroleum industry. The existence of multiple phases introduces multiple complexities hindering the accuracy of downhole pressure predictions. To account for such variations, fluid-property models must be integrated into the calculation procedure. The complexity, coupled with field-data scarcity, results in the deficiency of work that evaluates point models on actual wells. In this work, the authors evaluated the performance of a few widely used multiphase-flow point-based models on actual field data using a marching algorithm and developed a simplified, yet more precise, integrated model. Integrated Model Development Data Set Description. In this study, data points were collected for two main purposes. First, experimental data sets were collected to model and improve the segregated flow model. Second, field data were collected to test the integrated multiphase model. To improve the segregated flow model, 1,478 experimental data points were obtained from various sources in the literature. To evaluate the integrated multiphase flow model, 313 data points from two main sources of data were used (literature and actual field data). In total, four data sets were obtained from the literature and one was obtained from Civitas Resources. Integrated Model Description. The multiphase-flow point model incorporated in the authors’ integrated modeling consists of three main components: critical gas velocity estimation for the onset of liquid loading and hydraulic multiphase flow models before and after the onset of liquid loading. The proposed model characterizes the flow based on whether liquid loading occurs. The onset of liquid loading corresponds with the transition of the flow pattern from segregated to intermittent flow. At points where the superficial gas velocity is estimated to be lower than the critical gas velocity and the flow is considered intermittent or bubbly, the drift-flux model is to be used, which works well in flow patterns where liquid volume is high. Another strength of the model is its ability to capture countercurrent flow. The drift-flux homogeneous-like approach makes the process simple and continuous and simultaneously captures some physics through slippage. For points where the superficial gas velocity is greater than the critical gas velocity, two-fluid modeling is to be used.

Modeling the transmission of antibiotic-resistant Enterobacterales in the community: A systematic review

BackgroundAntibiotic-resistant Enterobacterales (ARE) are a public health threat worldwide. Dissemination of these opportunistic pathogens has been largely studied in hospitals. Despite high prevalence of asymptomatic colonization in the community in some regions of the world, less is known about ARE acquisition and spread in this setting. As explaining the community ARE dynamics has not been straightforward, mathematical models can be key to explore underlying phenomena and further evaluate the impact of interventions to curb ARE circulation outside of hospitals. MethodsWe conducted a systematic review of mathematical modeling studies focusing on the transmission of AR-E in the community, excluding models only specific to hospitals. We extracted model features (population, setting), formalism (compartmental, individual-based), biological hypotheses (transmission, infection, antibiotic impact, resistant strain specificities) and main findings. We discussed additional mechanisms to be considered, open scientific questions, and most pressing data needs. ResultsWe identified 18 modeling studies focusing on the human transmission of ARE in the community (n=11) or in both community and hospital (n=7). Models aimed at (i) understanding mechanisms driving resistance dynamics; (ii) identifying and quantifying transmission routes; or (iii) evaluating public health interventions to reduce resistance. To overcome the difficulty of reproducing observed ARE dynamics in the community using the classical two-strains competition model, studies proposed to include mechanisms such as within-host strain competition or a strong host population structure. Studies inferring model parameters from longitudinal carriage data were mostly based on models considering the ARE strain only. They showed differences in ARE carriage duration depending on the acquisition mode: returning travelers have a significantly shorter carriage duration than discharged hospitalized patient or healthy individuals. Interestingly, predictions across models regarding the success of public health interventions to reduce ARE rates depended on pathogens, settings, and antibiotic resistance mechanisms. For E. coli, reducing person-to-person transmission in the community had a stronger effect than reducing antibiotic use in the community. For Klebsiella pneumoniae, reducing antibiotic use in hospitals was more efficient than reducing community use. ConclusionsThis study raises the limited number of modeling studies specifically addressing the transmission of ARE in the community. It highlights the need for model development and community-based data collection especially in low- and middle-income countries to better understand acquisition routes and their relative contribution to observed ARE levels. Such modeling will be critical to correctly design and evaluate public health interventions to control ARE transmission in the community and further reduce the associated infection burden.

Improving The Ability of Vocal Group Through POMP2E Model Development for Students of Junior High School

This research aims to develop a POMP2E learning model that is valid/feasible, practical, and effective for use in learning the art of music in junior high schools. The type of research is Research & Development using the research and development procedures of the Gall, Gall & Borg model which was adapted from the Dick, Carey & Carey model. The research sample consisted of class IX students of SMP Negeri 1 Dolok Masihul as a group to test product practicality through one-on-one trials, small group trials (limited) and large group trials (field). Class IX students of SMP Negeri 3 Dolok Masihul tested product effectiveness through small group and field group tests. The data analysis techniques used were qualitative and quantitative descriptive data analysis techniques as well as experimental data analysis. Qualitative and quantitative data analysis is used to analyze model development data, namely testing instrument validity and product validity. Experimental data analysis is used for the validity and reliability of the tests used and the t test to see statistical differences in results between the experimental class and the control class. The results of testing the feasibility of supporting equipment instruments for the POMP2E model obtained a calculated average of 0.853, including the very feasible category. The results of the feasibility test for all POMPO2E model supporting device products obtained a calculated average of 0.874, including the category of very suitable for use. The results of the practicality test of using the POMP2E learning model and all supporting tools developed according to teacher responses obtained an average score of 89.32% in the very practical category, according to practicality according to students the average score was 88.56% in the very practical category. The results of the effectiveness test on the use of all POMP2E learning model products which were developed through three testing aspects, namely the cognitive, apective and psychomotor aspects, showed that the results of the POMP2E learning model's cognitive aspect effectiveness test were obtained N-Gain=0.73, including the high category with the interpretation of the category being quite effective in use. . The results of testing the effectiveness of the affective aspect of the POMP2E learning model obtained N-Gain=0.84, which is in the high category with the interpretation that it is effectively used. The results of testing the effectiveness of the POMP2E learning model for psychomotor aspects obtained N-Gain=0.76, which is in the high category with the interpretation that it is effective to use. Thus, it can be concluded that the POMP2E learning model developed is effective in improving the vocal abilities of groups of junior high school students.

Margin quality analysis for wedge resection of lung cancer and construction of a predictive model.

Insufficient pulmonary wedge resection margin is associated with malignant positive margins and high local recurrence risk for lung cancer. This study aimed to identify the risk factors of insufficient or guideline discordant resection margin distance and establish a predictive model to preoperatively estimate the risk of discordant margin for individual patient. Guideline discordant resection margin was defined as ratio of resection margin distance to tumor size less than one. Patients who had pulmonary malignancies and underwent wedge resection between April 2014 and February 2023 were enrolled and stratified by quality of resection margin. Multivariable logistic regression analysis was employed to identify risk factors of guideline discordant margin and a predictive model was developed. Data from March 2023 to January 2024 were collected for internal validation. A total of 530 patients were included. The incidence of guideline discordant wedge resection margin was 37.2%. Longer tumor's max distance to pleura and larger tumor size were variables associated with increased risk and included in the final model. Preoperative localization and right-side surgery were protective variables in the predictive model. A nomogram was built based on the predictive model. The model showed satisfying predictive performance with a concordance index of 0.720 for the predictive model, and 0.761 for internal validation. The goodness-if-fit tests were non-significant for both model development and internal validation data set. The preoperative predictive model and nomogram show good predictive performance to estimate the risk of guideline discordant wedge resection margin. Individualized surgical plans or preoperative nodule localization can be made for high-risk patients.

Decision region analysis for generalizability of artificial intelligence models: estimating model generalizability in the case of cross-reactivity and population shift.

Understanding an artificial intelligence (AI) model's ability to generalize to its target population is critical to ensuring the safe and effective usage of AI in medical devices. A traditional generalizability assessment relies on the availability of large, diverse datasets, which are difficult to obtain in many medical imaging applications. We present an approach for enhanced generalizability assessment by examining the decision space beyond the available testing data distribution. Vicinal distributions of virtual samples are generated by interpolating between triplets of test images. The generated virtual samples leverage the characteristics already in the test set, increasing the sample diversity while remaining close to the AI model's data manifold. We demonstrate the generalizability assessment approach on the non-clinical tasks of classifying patient sex, race, COVID status, and age group from chest x-rays. Decision region composition analysis for generalizability indicated that a disproportionately large portion of the decision space belonged to a single "preferred" class for each task, despite comparable performance on the evaluation dataset. Evaluation using cross-reactivity and population shift strategies indicated a tendency to overpredict samples as belonging to the preferred class (e.g., COVID negative) for patients whose subgroup was not represented in the model development data. An analysis of an AI model's decision space has the potential to provide insight into model generalizability. Our approach uses the analysis of composition of the decision space to obtain an improved assessment of model generalizability in the case of limited test data.

Development and External Validation of Individualized Prediction Models for Pain Intensity Outcomes in Patients With Neck Pain, Low Back Pain, or Both in Primary Care Settings.

The purpose of this study was to develop and externally validate multivariable prediction models for future pain intensity outcomes to inform targeted interventions for patients with neck or low back pain in primary care settings. Model development data were obtained from a group of 679 adults with neck or low back pain who consulted a participating United Kingdom general practice. Predictors included self-report items regarding pain severity and impact from the STarT MSK Tool. Pain intensity at 2 and 6months was modeled separately for continuous and dichotomized outcomes using linear and logistic regression, respectively. External validation of all models was conducted in a separate group of 586 patients recruited from a similar population with patients' predictor information collected both at point of consultation and 2 to 4weeks later using self-report questionnaires. Calibration and discrimination of the models were assessed separately using STarT MSK Tool data from both time points to assess differences in predictive performance. Pain intensity and patients reporting their condition would last a long time contributed most to predictions of future pain intensity conditional on other variables. On external validation, models were reasonably well calibrated on average when using tool measurements taken 2 to 4weeks after consultation (calibration slope = 0.848 [95% CI = 0.767 to 0.928] for 2-month pain intensity score), but performance was poor using point-of-consultation tool data (calibration slope for 2-month pain intensity score of 0.650 [95% CI = 0.549 to 0.750]). Model predictive accuracy was good when predictors were measured 2 to 4weeks after primary care consultation, but poor when measured at the point of consultation. Future research will explore whether additional, nonmodifiable predictors improve point-of-consultation predictive performance. External validation demonstrated that these individualized prediction models were not sufficiently accurate to recommend their use in clinical practice. Further research is required to improve performance through inclusion of additional nonmodifiable risk factors.

COMO: a pipeline for multi-omics data integration in metabolic modeling and drug discovery.

Identifying potential drug targets using metabolic modeling requires integrating multiple modeling methods and heterogeneous biological datasets, which can be challenging without efficient tools. We developed Constraint-based Optimization of Metabolic Objectives (COMO), a user-friendly pipeline that integrates multi-omics data processing, context-specific metabolic model development, simulations, drug databases and disease data to aid drug discovery. COMO can be installed as a Docker Image or with Conda and includes intuitive instructions within a Jupyter Lab environment. It provides a comprehensive solution for the integration of bulk and single-cell RNA-seq, microarrays and proteomics outputs to develop context-specific metabolic models. Using public databases, open-source solutions for model construction and a streamlined approach for predicting repurposable drugs, COMO enables researchers to investigate low-cost alternatives and novel disease treatments. As a case study, we used the pipeline to construct metabolic models of B cells, which simulate and analyze them to predict metabolic drug targets for rheumatoid arthritis and systemic lupus erythematosus, respectively. COMO can be used to construct models for any cell or tissue type and identify drugs for any human disease where metabolic inhibition is relevant. The pipeline has the potential to improve the health of the global community cost-effectively by providing high-confidence targets to pursue in preclinical and clinical studies. The source code of the COMO pipeline is available at https://github.com/HelikarLab/COMO. The Docker image can be pulled at https://github.com/HelikarLab/COMO/pkgs/container/como.

Machine learning models for efficient characterization of Schottky barrier photodiode internal parameters

We propose ANN-based models to analyze and extract the internal parameters of a Schottky photodiode (SPD) without presenting them with any knowledge of the highly nonlinear thermionic emission (TE) expression of the device current. We train, evaluate and demonstrate the ML models on thirty-six private datasets from three previously published devices, which denote current responses under illumination and ambient temperature of graphene oxide (GO) doped p-Si Schottky barrier diodes (SBDs). The GO doping levels are 0%, 1%, 3%, 5%, and 10%. The illumination ranged from dark (0 mW/cm2) to 30 mW/cm2. The predictions are then made completely at the intensity of 60 mW/cm2. For each diode, some values of the barrier height (phi ), ideality factor (n), and series resistance (R_s) independently calculated using the Cheung–Cheung method were included in the training dataset. The predictions are done at unspecified intensities on the model development data at 80 and 100 mW/cm2, and on external data at 5% and 20% GO doping which were not part of the development dataset. The ANN achieved a mean square error and mean absolute error score below 0.003 across all datasets. This demonstrates the effective learning capabilities of the ANN models in accurately capturing the photo responses of the photodiodes and accurately predicting the internal parameters of the Schottky Barrier Diodes (SBDs), all without relying on an inherent understanding of the thermionic emission (TE) equation for SBDs. The ANN models achieved high accuracy in this process. The proposed ML models can significantly reduce analysis time in device development cycles and can be applied to other datasets in various fields.

Development and Validation of an Automated Image-Based Deep Learning Platform for Sarcopenia Assessment in Head and Neck Cancer

Sarcopenia is an established prognostic factor in patients with head and neck squamous cell carcinoma (HNSCC); the quantification of sarcopenia assessed by imaging is typically achieved through the skeletal muscle index (SMI), which can be derived from cervical skeletal muscle segmentation and cross-sectional area. However, manual muscle segmentation is labor intensive, prone to interobserver variability, and impractical for large-scale clinical use. To develop and externally validate a fully automated image-based deep learning platform for cervical vertebral muscle segmentation and SMI calculation and evaluate associations with survival and treatment toxicity outcomes. For this prognostic study, a model development data set was curated from publicly available and deidentified data from patients with HNSCC treated at MD Anderson Cancer Center between January 1, 2003, and December 31, 2013. A total of 899 patients undergoing primary radiation for HNSCC with abdominal computed tomography scans and complete clinical information were selected. An external validation data set was retrospectively collected from patients undergoing primary radiation therapy between January 1, 1996, and December 31, 2013, at Brigham and Women's Hospital. The data analysis was performed between May 1, 2022, and March 31, 2023. C3 vertebral skeletal muscle segmentation during radiation therapy for HNSCC. Overall survival and treatment toxicity outcomes of HNSCC. The total patient cohort comprised 899 patients with HNSCC (median [range] age, 58 [24-90] years; 140 female [15.6%] and 755 male [84.0%]). Dice similarity coefficients for the validation set (n = 96) and internal test set (n = 48) were 0.90 (95% CI, 0.90-0.91) and 0.90 (95% CI, 0.89-0.91), respectively, with a mean 96.2% acceptable rate between 2 reviewers on external clinical testing (n = 377). Estimated cross-sectional area and SMI values were associated with manually annotated values (Pearson r = 0.99; P < .001) across data sets. On multivariable Cox proportional hazards regression, SMI-derived sarcopenia was associated with worse overall survival (hazard ratio, 2.05; 95% CI, 1.04-4.04; P = .04) and longer feeding tube duration (median [range], 162 [6-1477] vs 134 [15-1255] days; hazard ratio, 0.66; 95% CI, 0.48-0.89; P = .006) than no sarcopenia. This prognostic study's findings show external validation of a fully automated deep learning pipeline to accurately measure sarcopenia in HNSCC and an association with important disease outcomes. The pipeline could enable the integration of sarcopenia assessment into clinical decision making for individuals with HNSCC.

Identification and validation of the model consisting of DDX49, EGFR, and T-stage as a possible risk factor for lymph node metastasis in patients with lung cancer.

The lymph node metastasis stage of lung cancer is an important decisive factor in the need for postoperative adjuvant treatment and the difference between stage IIIa and stage IIIB that is the necessary information to distinguish whether surgery can be performed or not. The specificity of the clinical diagnosis of lung cancer with lymph node metastasis cannot meet the requirements of preoperative evaluation of surgical indications and prediction of surgical removal range in lung cancer. This was an early experimental laboratory trial. The model identification data included the RNA sequence data of 10 patients from our clinical data and 188 patients with lung cancer from The Cancer Genome Atlas dataset. The model development and validation data consisted of RNA sequence data for 537 cases from the Gene Expression Omnibus dataset. We explore the predictive value of the model on two independent clinical data. A higher specificity of diagnostic model for patients with lung cancer with lymph node metastases consisted of DDX49, EGFR, and tumor stage (T-stage), which were the independent predictive factors. The area under the curve value, specificity, and sensitivity for predicting lymph node metastases were 0.835, 70.4%, and 78.9% at RNA expression level in the training group, and 0.681, 73.2%, and 75.7% at RNA expression level in the validation group as shown as in result part. To verify the predictive performance of the combined model for lymph node metastases, we downloaded the GSE30219 data set (n = 291) and the GSE31210 data set (n = 246) from the Gene Expression Omnibus (GEO) database as the training group and validation group, respectively. In addition, the model had a higher specificity for predicting lymph node metastases in independent tissue samples. Determination of DDX49, EGFR, and T-stage could form a novel prediction model to improve the diagnostic efficacy of lymph node metastasis in clinical application.

Validated Model for Prediction of Adverse Cardiac Outcome in Patients With Fabry Disease

BackgroundThe cardiac manifestations of Fabry disease are the leading cause of death, but risk stratification remains inadequate. Identifying patients who are at risk of adverse cardiac outcome may facilitate more evidence-based treatment guidance. Contemporary cardiovascular cardiac magnetic resonance biomarkers have become widely adopted, but their prognostic value remains unclear. ObjectivesThe objective of this study was to develop, internally validate, and evaluate the performance of, a prognostic model, including contemporary deep phenotyping, which can be used to generate individual risk estimates for adverse cardiac outcome in patients with Fabry disease. MethodsThis longitudinal prospective cohort study consisted of 200 consecutive patients with Fabry disease undergoing clinical cardiac magnetic resonance. Median follow-up was 4.5 years (IQR: 2.7-6.3 years). Prognostic models were developed using Cox proportional hazards modeling. Outcome was a composite of adverse cardiac events. Model performance was evaluated. A risk calculator, which provides 5-year estimated risk of adverse cardiac outcome for individual patients, including men and women, was generated. ResultsThe highest performing, internally validated, parsimonious multivariable model included age, native myocardial T1 dispersion (SD of per voxel myocardial T1 relaxation times), and indexed left ventricular mass. Median optimism-adjusted c-statistic across 5 imputed model development data sets was 0.77 (95% CI: 0.70-0.84). Model calibration was excellent across the full risk profile. ConclusionsThis study developed and internally validated a risk prediction model that accurately predicts 5-year risk of adverse cardiac outcome for individual patients with Fabry disease, including men and women, which could easily be integrated into clinical care. External validation is warranted.

Application of machine learning algorithms in predicting HIV infection among men who have sex with men: Model development and validation.

BackgroundContinuously growing of HIV incidence among men who have sex with men (MSM), as well as the low rate of HIV testing of MSM in China, demonstrates a need for innovative strategies to improve the implementation of HIV prevention. The use of machine learning algorithms is an increasing tendency in disease diagnosis prediction. We aimed to develop and validate machine learning models in predicting HIV infection among MSM that can identify individuals at increased risk of HIV acquisition for transmission-reduction interventions.MethodsWe extracted data from MSM sentinel surveillance in Zhejiang province from 2018 to 2020. Univariate logistic regression was used to select significant variables in 2018–2019 data (P < 0.05). After data processing and feature selection, we divided the model development data into two groups by stratified random sampling: training data (70%) and testing data (30%). The Synthetic Minority Oversampling Technique (SMOTE) was applied to solve the problem of unbalanced data. The evaluation metrics of model performance were comprised of accuracy, precision, recall, F-measure, and the area under the receiver operating characteristic curve (AUC). Then, we explored three commonly-used machine learning algorithms to compare with logistic regression (LR), including decision tree (DT), support vector machines (SVM), and random forest (RF). Finally, the four models were validated prospectively with 2020 data from Zhejiang province.ResultsA total of 6,346 MSM were included in model development data, 372 of whom were diagnosed with HIV. In feature selection, 12 variables were selected as model predicting indicators. Compared with LR, the algorithms of DT, SVM, and RF improved the classification prediction performance in SMOTE-processed data, with the AUC of 0.778, 0.856, 0.887, and 0.942, respectively. RF was the best-performing algorithm (accuracy = 0.871, precision = 0.960, recall = 0.775, F-measure = 0.858, and AUC = 0.942). And the RF model still performed well on prospective validation (AUC = 0.846).ConclusionMachine learning models are substantially better than conventional LR model and RF should be considered in prediction tools of HIV infection in Chinese MSM. Further studies are needed to optimize and promote these algorithms and evaluate their impact on HIV prevention of MSM.

Development and validation of automated computer-aided risk scores to predict in-hospital mortality for emergency medical admissions with COVID-19: a retrospective cohort development and validation study

ObjectivesThere are no established mortality risk equations specifically for unplanned emergency medical admissions which include patients with SARS-19 (COVID-19). We aim to develop and validate a computer-aided risk score (CARMc19)...

Performance of an electronic health record-based predictive model to identify patients with atrial fibrillation across countries.

BackgroundAtrial fibrillation (AF) burden on patients and healthcare systems warrants innovative strategies for screening asymptomatic individuals.ObjectiveWe sought to externally validate a predictive model originally developed in a German population to detect unidentified incident AF utilising real-world primary healthcare databases from countries in Europe and Australia.MethodsThis retrospective cohort study used anonymized, longitudinal patient data from 5 country-level primary care databases, including Australia, Belgium, France, Germany, and the UK. The study eligibility included adult patients (≥45 years) with either an AF diagnosis (cases) or no diagnosis (controls) who had continuous enrolment in the respective database prior to the study period. Logistic regression was fitted to a binary response (yes/no) for AF diagnosis using pre-determined risk factors.ResultsAF patients were from Germany (n = 63,562), the UK (n = 42,652), France (n = 7,213), Australia (n = 2,753), and Belgium (n = 1,371). Cases were more likely to have hypertension or other cardiac conditions than controls in all validation datasets compared to the model development data. The area under the receiver operating characteristic (ROC) curve in the validation datasets ranged from 0.79 (Belgium) to 0.84 (Germany), comparable to the German study model, which had an area under the curve of 0.83. Most validation sets reported similar specificity at approximately 80% sensitivity, ranging from 67% (France) to 71% (United Kingdom). The positive predictive value (PPV) ranged from 2% (Belgium) to 16% (Germany), and the number needed to be screened was 50 in Belgium and 6 in Germany. The prevalence of AF varied widely between these datasets, which may be related to different coding practices. Low prevalence affected PPV, but not sensitivity, specificity, and ROC curves.ConclusionsAF risk prediction algorithms offer targeted ways to identify patients using electronic health records, which could improve screening number and the cost-effectiveness of AF screening if implemented in clinical practice.

Combining Machine Learning with a Rule-Based Algorithm to Detect and Identify Related Entities of Documented Adverse Drug Reactions on Hospital Discharge Summaries.

Discharge summaries contain valuable information about adverse drug reactions, but their unstructured nature makes them challenging to analyse and use as a signal source for pharmacovigilance. Machine learning has shown promise in identifying discharge summaries that contain related drug-adverse event pairs but has fared relatively poorer in entity extraction. A hybrid model is developed combining rule-based and machine learning algorithms using discharge summaries with the aim of maximising capture of related drug-adverse event pairs. The rule first identifies segments containing adverse event entities within a 100-character distance from a drug term; machine learning subsequently estimates the relatedness of the drug and adverse event entities contained. The approach is validated on four independent datasets that are temporally and geographically separated from model development data. The impact of restricted drug-adverse event pair detection on recall is evaluated by using two of the four validation datasets that do not impose rule-based restrictions to annotations. The hybrid model achieves a recall of 0.80 (fivefold cross validation), 0.80 (temporal) and 0.76 (geographical) on validation using datasets containing only pre-identified target text segments that fulfil the rule-based algorithm criteria. When tested on datasets that additionally contained drug-adverse event pairs not restricted by the rule-based criteria, recall of the model declines to 0.68 and 0.62 on temporally and geographically separated datasets, respectively. The proposed hybrid model demonstrates reasonable generalisability on external validation. Rule-based restriction of the detection space results in an approximately 12-14% reduction in recall but improves identification of the related drug and adverse event terms.

Establishment of CORONET, COVID-19 Risk in Oncology Evaluation Tool, to Identify Patients With Cancer at Low Versus High Risk of Severe Complications of COVID-19 Disease On Presentation to Hospital.

PURPOSEPatients with cancer are at increased risk of severe COVID-19 disease, but have heterogeneous presentations and outcomes. Decision-making tools for hospital admission, severity prediction, and increased monitoring for early intervention are critical. We sought to identify features of COVID-19 disease in patients with cancer predicting severe disease and build a decision support online tool, COVID-19 Risk in Oncology Evaluation Tool (CORONET).METHODSPatients with active cancer (stage I-IV) and laboratory-confirmed COVID-19 disease presenting to hospitals worldwide were included. Discharge (within 24 hours), admission (≥ 24 hours inpatient), oxygen (O2) requirement, and death were combined in a 0-3 point severity scale. Association of features with outcomes were investigated using Lasso regression and Random Forest combined with Shapley Additive Explanations. The CORONET model was then examined in the entire cohort to build an online CORONET decision support tool. Admission and severe disease thresholds were established through pragmatically defined cost functions. Finally, the CORONET model was validated on an external cohort.RESULTSThe model development data set comprised 920 patients, with median age 70 (range 5-99) years, 56% males, 44% females, and 81% solid versus 19% hematologic cancers. In derivation, Random Forest demonstrated superior performance over Lasso with lower mean squared error (0.801 v 0.807) and was selected for development. During validation (n = 282 patients), the performance of CORONET varied depending on the country cohort. CORONET cutoffs for admission and mortality of 1.0 and 2.3 were established. The CORONET decision support tool recommended admission for 95% of patients eventually requiring oxygen and 97% of those who died (94% and 98% in validation, respectively). The specificity for mortality prediction was 92% and 83% in derivation and validation, respectively. Shapley Additive Explanations revealed that National Early Warning Score 2, C-reactive protein, and albumin were the most important features contributing to COVID-19 severity prediction in patients with cancer at time of hospital presentation.CONCLUSIONCORONET, a decision support tool validated in health care systems worldwide, can aid admission decisions and predict COVID-19 severity in patients with cancer.

A Diagnostic Prediction Model for Separating Juvenile Idiopathic Arthritis and Chronic Musculoskeletal Pain Syndrome

To develop and validate a diagnostic prediction model that can distinguish between juvenile idiopathic arthritis (JIA) and chronic musculoskeletal pain syndrome (CMPS) based on patient-reported outcomes. This retrospective cohort study evaluated whether the Juvenile Arthritis Multidimensional Assessment Report (JAMAR) performs well in distinguishing JIA from CMPS. We analyzed JAMARs completed by 287 patients at their first visit to the pediatric rheumatology department of Wilhelmina Children's Hospital in Utrecht, The Netherlands. Relevant JAMAR items for predicting a diagnosis of JIA were selected in a penalized multivariable model suitable for clinical application. The model was subsequently validated with new data from the same center. A total of 196 JAMARs (97 JIA, 99 CMPS) were collected in the model development data, and 91 JAMARs (48 JIA, 43 CMPS) were collected in the validation data. Variables in the prediction model that were strongest associated with a diagnosis of JIA instead of CMPS were asymmetric pain/swelling in the shoulder (OR, 2.34), difficulty with self-care (OR, 2.41), skin rash (OR, 2.07), and asymmetric/pain swelling in the knee (OR, 2.29). Calibration and discrimination (area under the receiver operating characteristic curve, 0.83; 95% CI, 0.74-0.92) of the model in the validation data were good. Several items from the JAMAR questionnaire can potentially distinguish JIA from CMPS in patients with corresponding symptoms. We present an easy-to-use, adjusted, and validated model to separate these 2 diagnoses early at presentation based on patient-reported outcomes to facilitate proper referral and treatment.

Natural history of disease in cynomolgus monkeys exposed to Ebola virus Kikwit strain demonstrates the reliability of this non-human primate model for Ebola virus disease.

Filoviruses (Family Filoviridae genera Ebolavirus and Marburgvirus) are negative-stranded RNA viruses that cause severe health effects in humans and non-human primates, including death. Except in outbreak settings, vaccines and other medical countermeasures against Ebola virus (EBOV) will require testing under the FDA Animal Rule. Multiple vaccine candidates have been evaluated using cynomolgus monkeys (CM) exposed to EBOV Kikwit strain. To the best of our knowledge, however, animal model development data supporting the use of CM in vaccine research have not been submitted to the FDA. This study describes a large CM database (122 CM, 62 female and 60 male, age 2 to 9 years) and demonstrates the consistency of the CM model through time to death models and descriptive statistics. CMs were exposed to EBOV doses of 0.1 to 100,000 PFU in 33 studies conducted at three Animal Biosafety Level 4 facilities, by three exposure routes. Time to death was modeled using Cox proportional hazards models with a frailty term that incorporated study-to-study variability. Despite significant differences attributed to exposure variables, all CMs exposed to the 100 to 1,000 pfu doses commonly used in vaccine studies died or met euthanasia criteria within 21 days of exposure, median 7 days, 93% between 5 and 12 days of exposure. Moderate clinical signs were observed 4 to 5 days after exposure and preceded death or euthanasia by approximately one day. Viremia was detected within a few days of infection. Hematology indices were indicative of viremia and the propensity for hemorrhage with progression of Ebola viremia. Changes associated with coagulation parameters and platelets were consistent with coagulation disruption. Changes in leukocyte profiles were indicative of an acute inflammatory response. Increased liver enzymes were observed shortly after exposure. Taken together, these factors suggest that the cynomolgus monkey is a reliable animal model for human disease.