Search

An examinition of area under the curve (AUC) values from PubMed abtracts, aimed at examining AUC-hacking.

Data obtained through systematic review for the ADNEX model external validations and code to perform meta-analysis and figures in the paper with the same name.

A systematic review of existing maternal early warning scores (MOEWS/MEWS) that identify maternal mortality, ICU admission or a combination of maternal morbidities.

Supplemental material, sj-docx-1-smm-10.1177_09622802231151220 for Minimum sample size for developing a multivariable prediction model using multinomial logistic regression by Alexander Pate, Richard D Riley, Gary S Collins, Maarten van Smeden, Ben Van Calster, Joie Ensor and Glen P Martin in Statistical Methods in Medical Research

Supplemental material, sj-docx-1-smm-10.1177_09622802231151220 for Minimum sample size for developing a multivariable prediction model using multinomial logistic regression by Alexander Pate, Richard D Riley, Gary S Collins, Maarten van Smeden, Ben Van Calster, Joie Ensor and Glen P Martin in Statistical Methods in Medical Research

The swift progress and ubiquitous adoption of Generative AI (GAI), Generative Pre-trained Transformers (GPTs), and large language models (LLMs) like ChatGPT, have spurred queries about their ethical application, use, and disclosure in scholarly research and scientific productions. A few publishers and journals have recently created their own sets of rules; however, the absence of a unified approach may lead to a 'Babel Tower Effect,' potentially resulting in confusion rather than desired standardization. In response to this, we present the ChatGPT, Generative Artificial Intelligence, and Natural Large Language Models for Accountable Reporting and Use Guidelines (CANGARU) initiative, with the aim of fostering a cross-disciplinary global inclusive consensus on the ethical use, disclosure, and proper reporting of GAI/GPT/LLM technologies in academia. The present protocol consists of four distinct parts: a) an ongoing systematic review of GAI/GPT/LLM applications to understand the linked ideas, findings, and reporting standards in scholarly research, and to formulate guidelines for its use and disclosure, b) a bibliometric analysis of existing author guidelines in journals that mention GAI/GPT/LLM, with the goal of evaluating existing guidelines, analyzing the disparity in their recommendations, and identifying common rules that can be brought into the Delphi consensus process, c) a Delphi survey to establish agreement on the items for the guidelines, ensuring principled GAI/GPT/LLM use, disclosure, and reporting in academia, and d) the subsequent development and dissemination of the finalized guidelines and their supplementary explanation and elaboration documents., Comment: 20 pages, 1 figure, protocol

List of not-for-profit organisations that provide financial support to health researchers working in the United Kingdom

Information about what open research practices are suggested, incentivised or required from health researchers by the UK funders listed

A study on how funders of health research in the UK practice and incentivise open research

Here we present three approaches to identifying possible barriers and facilitators that researchers encounter when using reporting guidelines: 1. A thematic synthesis of qualitative data 2. A description of quantitative questions asked in studies that gather feedback on guidelines 3. A description of Google analytics data from the EQUATOR Network website. The themes we identify will be useful to guideline developers who want to make sure their resources are easy to use, journal editors who want to encourage guideline adherence, and will inform the features of a new website being developed by the EQUATOR Network which will help authors find, understand and apply reporting guidelines.

This project is an attempt to harmonize the available data on psychological outcome measures following ACL injury from various cohorts across the world. We will attempt to perform an individual patient data (IPD) meta-analysis to explore psychological outcomes following ACL injury and how they may be impacted by modifiable treatment strategy.

Data used to inform analysis evaluating the risk of bias of clinical prediction models developed using machine learning methods in the field of Oncology

There is evidence that, although most reputable medical journals endorse the use of reporting guidelines, authors still find it difficult to identify the most appropriate one and use it effectively to improve the completeness of their article. We have developed an online tool called GoodReports (www.goodreports.org) to help researchers find and use reporting guidelines. The tool currently helps researchers identify the most appropriate single reporting guideline (e.g., CONSORT, STROBE, or PRISMA) and delivers an online, editable checklist that can also be downloaded. The checklist can be annotated to indicate where in the manuscript each item has been reported, then submitted to a journal alongside an article manuscript. However, pilot data collected as part of a collaboration with a medical journal indicated that when a checklist was delivered immediately before submission, it did not lead to authors making significant additions to their manuscript. Therefore, we plan to 1. Develop the functionality of the GoodReports tool to deliver an article template to be used during writing. 2. Combine items from more than one reporting guideline into a single article template, where appropriate. 3. Conduct a randomized trial to test whether article templates delivered early in the writing process result in more complete reporting of health research articles.

Data used to inform analysis evaluating the completeness of reporting of clinical prediction models developed using machine learning methods in the field of Oncology

Methodological conduct of prognostic prediction models developed using machine learning in oncology: a systematic review

To identify true gaps and ensure that reporting guidelines remain a useful tool that is straightforward to use, we are conducting a full audit of the current reporting guidelines’ landscape. We are extracting data on general reporting guidelines characteristics (e.g., scope of guideline, journal and year of publication, length of reporting guideline), methods used to develop the reporting guidelines (e.g., details on any literature review, Delphi survey, consensus process, composition of guideline group, pilot testing), and how they were disseminated (e.g., multiple publications, explanatory document, website). We are using the data collected on development methods to update our taxonomy of reporting guidelines, currently based on their scope (specific to study design, section of the report, clinical area, or a combination of these), and whether the document describes an extension of a previous guideline.

An inventory and critical appraisal of prediction models for COVID-19 triage published in Arxiv, medRxiv, bioRxiv, PubMed, and EMBASE

This webpage consists of details and documentation regarding the forthcoming QUADAS-AI Quality Assessment Tool

Predicting drug approval could be valuable in reducing attrition during drug development. Several attempts have been made to develop prediction models of regulatory approval or clinical development on the basis of a range of predictors. However, these models have not included detailed information related to the physicochemical parameters of the compounds, which could be informative and which have been the basis of many extremely influential attempts to distinguish potential drugs from other chemicals. In this project, we will develop and internally validate a prediction model based on comparison of approved small molecule drugs (‘drugs’) with drugs that entered clinical development but were discontinued. Predictors are physicochemical parameters commonly considered in assessments of ‘drug-likeness’.

Background: Clinical prediction models (CPMs) are used to predict the probability of cancer patients’ current and future health status. They are used widely in healthcare and have potential to reduce disease burden, save money for the NHS, and improve patient care. Advancements in healthcare research, such as the availability of ‘big’ data and increasing computational power, has seen a proliferation of CPM models developed using machine-learning (ML) methods. ML methods offer greater modelling flexibility and the ability to model non-linear data and interactions. Though ML has shown promise in high dimensional settings (e.g., imaging), several systematic reviews have shown ML-based CPMs to be at high risk of bias in low dimensional oncology settings; developed using uninformed, too-small sample sizes, using inefficient data-splitting approaches to develop and internally test the CPM. Evidence-based guidance is needed for developing ML-based CPMs. Aims: The research aims of this study are to define and validate sample size criteria for studies developing and validating ML-based CPMs for binary outcomes in low dimensional oncology settings and to develop an interactive graphical user interface with worked examples. Methods: We will conduct a simulation study to define sample size requirements for five common ML techniques used to develop oncology CPMs: decision trees, random forests, gradient-boosting machines, support vector machines and neural networks. We will simulate data using realistic clinical prediction modelling scenarios. We will conduct resampling studies on lung, breast, and colon cancer to validate findings from the simulation study, using a real-world clinical cancer cohort, the Surveillance, Epidemiology, and End Results (SEER) Program. For both studies we will vary design factors, such as sample size and outcome rates, in a fully factorial method. A CPM will be developed for each scenario and its performance assessed using discrimination and calibration performance measures. We will assess hyperparameter tuning methods using cross-validation using default values, grid search or random search for hyperparameter tuning. We will use findings to develop an R Shiny app to create an interactive graphical user interface. How the results of this research will be used: We will develop formal sample size guidance, complemented with an R Shiny web app, for researchers developing and validating ML-based CPMs in oncology. The results will give model developers evidence-based guidance to better design their prediction modelling development and validation studies in oncology. Funders will benefit from better use of their resources and clear guidance for evaluating proposed studies.

Additional file 5: Figure S1. The percentage change in the age-standardised point prevalence of chronic obstructive pulmonary disease in the Middle East and North Africa region from 1990 to 2019, by sex and country (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 4: Table S4. DALYs due to chronic obstructive pulmonary disease in 1990 and 2019 for both sexes and percentage change in age-standardised rates (ASRs) per 100,000 in the Middle East and North Africa region (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 2. Model recalibration approaches evaluated.

Additional file 1: Table S1. Different types and meanings of datasets in predictive modelling. Table S2. Essential treatments prescribed at admission that were included as predictors. Table S3. Symptoms and signs of severe illness considered as candidate predictors. Table S4. Distribution of predictors for patients included in the SENSS model derivation, updating and external validation. Table S5. Distribution of predictors for patients included in the NETS model derivation, updating and external validation. Table S6. Hospital Specific Candidate Predictor Summaries. Table S7. Distribution of predictors and missingness in SENSS external validation dataset by in-hospital mortality. Table S8. Distribution of predictors in NETS external validation dataset by in-hospital mortality.

In the version of this article initially published, a list of the DECIDE-AI expert group members and their affiliations was omitted and has now been included in the HTML and PDF versions of the article. *A list of authors and their affiliations appears online.

Additional file 7: Figure S3. The percentage change in the age-standardised DALYs of chronic obstructive pulmonary disease in the Middle East and North Africa region from 1990 to 2019, by sex and country. DALY = disability-adjusted-life-years (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 1. Supplementary information

Additional file 8: Figure S4. Percentage of DALYs due to chronic obstructive pulmonary disease attributable to risk factors for the Middle East and North Africa countries, by sex, in 2019. DALY = disability-adjusted-life-years (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 6: Figure S2. The percentage change in the age-standardised death of chronic obstructive pulmonary disease in the Middle East and North Africa region from 1990 to 2019, by sex and country (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Clinical prediction models estimate an individual's risk of a particular health outcome, conditional on their values of multiple predictors. A developed model is a consequence of the development dataset and the chosen model building strategy, including the sample size, number of predictors and analysis method (e.g., regression or machine learning). Here, we raise the concern that many models are developed using small datasets that lead to instability in the model and its predictions (estimated risks). We define four levels of model stability in estimated risks moving from the overall mean to the individual level. Then, through simulation and case studies of statistical and machine learning approaches, we show instability in a model's estimated risks is often considerable, and ultimately manifests itself as miscalibration of predictions in new data. Therefore, we recommend researchers should always examine instability at the model development stage and propose instability plots and measures to do so. This entails repeating the model building steps (those used in the development of the original prediction model) in each of multiple (e.g., 1000) bootstrap samples, to produce multiple bootstrap models, and then deriving (i) a prediction instability plot of bootstrap model predictions (y-axis) versus original model predictions (x-axis), (ii) a calibration instability plot showing calibration curves for the bootstrap models in the original sample; and (iii) the instability index, which is the mean absolute difference between individuals' original and bootstrap model predictions. A case study is used to illustrate how these instability assessments help reassure (or not) whether model predictions are likely to be reliable (or not), whilst also informing a model's critical appraisal (risk of bias rating), fairness assessment and further validation requirements., Comment: 30 pages, 7 Figures

Additional file 3: Table S3. Deaths of chronic obstructive pulmonary disease in 1990 and 2019 for both sexes and percentage change in age-standardised rates (ASRs) per 100,000 in the Middle East and North Africa region (generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

The development of a reporting guideline for protocols of diagnostic and prognostic prediction studies (TRIPOD-P) - a systematic review and Delphi survey

Additional file 1: Table S1. Health states for chronic obstructive pulmonary disease and the associated disability weights from the Global Burden of Disease 2019 Study.

BackgroundOsteoarthritis (OA) is a chronic joint disease, with increasing global burden of disability and healthcare utilisation. Recent meta-analyses have shown a range of effects of OA on mortality, reflecting different OA definitions and study methods. We seek to overcome limitations introduced when using aggregate results by gathering individual participant-level data (IPD) from international observational studies and standardising methods to determine the association of knee OA with mortality in the general population.MethodsSeven community-based cohorts were identified containing knee OA-related pain, radiographs, and time-to-mortality, six of which were available for analysis. A two-stage IPD meta-analysis framework was applied: (1) Cox proportional hazard models assessed time-to-mortality of participants with radiographic OA (ROA), OA-related pain (POA), and a combination of pain and ROA (PROA) against pain and ROA-free participants; (2) hazard ratios (HR) were then pooled using the Hartung-Knapp modification for random-effects meta-analysis.Findings10,723 participants in six cohorts from four countries were included in the analyses. Multivariable models (adjusting for age, sex, race, BMI, smoking, alcohol consumption, cardiovascular disease, and diabetes) showed a pooled HR, compared to pain and ROA-free participants, of 1.03 (0.83, 1.28) for ROA, 1.35 (1.12, 1.63) for POA, and 1.37 (1.22, 1.54) for PROA.DiscussionParticipants with POA or PROA had a 35-37% increased association with reduced time-to-mortality, independent of confounders. ROA showed no association with mortality, suggesting that OA-related knee pain may be driving the association with time-to-mortality.FundingVersus Arthritis Centre for Sport, Exercise and Osteoarthritis and Osteoarthritis Research Society International.

Additional file 20: Figure S15. Age-standardized YLD rates of anemia attributable to malaria for the 21 Global Burden of Disease regions by Socio-demographic Index, 1990���2019; Expected values based on Socio-demographic Index and disease rates in all locations are shown as the black line. Thirty points are plotted for each GBD region and show the observed age-standardized YLD rates from 1990 to 2019 for that region. YLD = years lived with disability. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 2: Table S2. Prevalent cases of anemia in 2019 and the percentage change in the age-standardized rates (ASRs) from 1990 to 2019, by severity and location (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 12: Figure S7. Age-standardized YLD rates of anemia attributable to chronic kidney disease for the 21 Global Burden of Disease regions by Socio-demographic Index, 1990���2019; Expected values based on Socio-demographic Index and disease rates in all locations are shown as the black line. Thirty points are plotted for each GBD region and show the observed age-standardized YLD rates from 1990 to 2019 for that region. YLD = years lived with disability. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 23: Figure S18. Age-standardized YLD rates of anemia attributable to ���other unspecified infectious diseases��� for the 21 Global Burden of Disease regions by Socio-demographic Index, 1990���2019; Expected values based on Socio-demographic Index and disease rates in all locations are shown as the black line. Thirty points are plotted for each GBD region and show the observed age-standardized YLD rates from 1990 to 2019 for that region. YLD = years lived with disability. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 9: Table S5. Years lived with disability (YLDs) due to anemia in 1990 and 2019 and the percentage change in the age-standardized rates (ASRs) per 100,000, by location (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 24: Figure S19. Age-standardized YLD rates of anemia attributable to schistosomiasis for the 21 Global Burden of Disease regions by Socio-demographic Index, 1990���2019; Expected values based on Socio-demographic Index and disease rates in all locations are shown as the black line. Thirty points are plotted for each GBD region and show the observed age-standardized YLD rates from 1990 to 2019 for that region. YLD = years lived with disability. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Supplemental Material, sj-pdf-2-ojs-10.1177_23259671211056645 for Health Conditions, Substance Use, Physical Activity, and Quality of Life in Current and Former Baseball Players by Garrett S. Bullock, Kristen F. Nicholson, Brian R. Waterman, Eric Niesen, Paul Salamh, Charles A. Thigpen, Ellen Shanley, Laurie Devaney, Gary S. Collins, Nigel K. Arden and Stephanie R. Filbay in Orthopaedic Journal of Sports Medicine

Additional file 18: Figure S13. Age-standardized YLD rates of anemia attributable to inflammatory bowel disease for the 21 Global Burden of Disease regions by Socio-demographic Index, 1990���2019; Expected values based on Socio-demographic Index and disease rates in all locations are shown as the black line. Thirty points are plotted for each GBD region and show the observed age-standardized YLD rates from 1990 to 2019 for that region. YLD = years lived with disability. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 6: Figure S3. The percentage change in the age-standardized point prevalence of anemia from 1990 to 2019 for the 21 Global Burden of Disease regions, by sex. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Additional file 1: Table S1. Definitions of mild, moderate, and severe anemia, based on blood hemoglobin concentration.

Additional file 4: Figure S1. The age-standardized point prevalence of anemia in 2019 for the 21 Global Burden of Disease regions, by sex. (Generated from data available from http://ghdx.healthdata.org/gbd-results-tool ).

Supplemental Material, sj-pdf-1-ojs-10.1177_23259671211056645 for Health Conditions, Substance Use, Physical Activity, and Quality of Life in Current and Former Baseball Players by Garrett S. Bullock, Kristen F. Nicholson, Brian R. Waterman, Eric Niesen, Paul Salamh, Charles A. Thigpen, Ellen Shanley, Laurie Devaney, Gary S. Collins, Nigel K. Arden and Stephanie R. Filbay in Orthopaedic Journal of Sports Medicine