ACcurate COnsensus Reporting Document (ACCORD) explanation and elaboration: Guidance and examples to support reporting consensus methods.

BACKGROUND: When research evidence is limited, inconsistent, or absent, healthcare decisions and policies need to be based on consensus among interested stakeholders. In these processes, the knowledge, experience, and expertise of health professionals, researchers, policymakers, and the public are systematically collected and synthesised to reach agreed clinical recommendations and/or priorities. However, despite the influence of consensus exercises, the methods used to achieve agreement are often poorly reported. The ACCORD (ACcurate COnsensus Reporting Document) guideline was developed to help report any consensus methods used in biomedical research, regardless of the health field, techniques used, or application. This explanatory document facilitates the use of the ACCORD checklist. METHODS AND FINDINGS: This paper was built collaboratively based on classic and contemporary literature on consensus methods and publications reporting their use. For each ACCORD checklist item, this explanation and elaboration document unpacks the pieces of information that should be reported and provides a rationale on why it is essential to describe them in detail. Furthermore, this document offers a glossary of terms used in consensus exercises to clarify the meaning of common terms used across consensus methods, to promote uniformity, and to support understanding for consumers who read consensus statements, position statements, or clinical practice guidelines (CPGs). The items are followed by examples of reporting items from the ACCORD guideline, in text, tables, and figures. CONCLUSIONS: The ACCORD materials-including the reporting guideline and this explanation and elaboration document-can be used by anyone reporting a consensus exercise used in the context of health research. As a reporting guideline, ACCORD helps researchers to be transparent about the materials, resources (both human and financial), and procedures used in their investigations so readers can judge the trustworthiness and applicability of their results/recommendations.

ACCORD (ACcurate COnsensus Reporting Document): A reporting guideline for consensus methods in biomedicine developed via a modified Delphi.

BACKGROUND: In biomedical research, it is often desirable to seek consensus among individuals who have differing perspectives and experience. This is important when evidence is emerging, inconsistent, limited, or absent. Even when research evidence is abundant, clinical recommendations, policy decisions, and priority-setting may still require agreement from multiple, sometimes ideologically opposed parties. Despite their prominence and influence on key decisions, consensus methods are often poorly reported. Our aim was to develop the first reporting guideline dedicated to and applicable to all consensus methods used in biomedical research regardless of the objective of the consensus process, called ACCORD (ACcurate COnsensus Reporting Document). METHODS AND FINDINGS: We followed methodology recommended by the EQUATOR Network for the development of reporting guidelines: a systematic review was followed by a Delphi process and meetings to finalize the ACCORD checklist. The preliminary checklist was drawn from the systematic review of existing literature on the quality of reporting of consensus methods and suggestions from the Steering Committee. A Delphi panel (n = 72) was recruited with representation from 6 continents and a broad range of experience, including clinical, research, policy, and patient perspectives. The 3 rounds of the Delphi process were completed by 58, 54, and 51 panelists. The preliminary checklist of 56 items was refined to a final checklist of 35 items relating to the article title (n = 1), introduction (n = 3), methods (n = 21), results (n = 5), discussion (n = 2), and other information (n = 3). CONCLUSIONS: The ACCORD checklist is the first reporting guideline applicable to all consensus-based studies. It will support authors in writing accurate, detailed manuscripts, thereby improving the completeness and transparency of reporting and providing readers with clarity regarding the methods used to reach agreement. Furthermore, the checklist will make the rigor of the consensus methods used to guide the recommendations clear for readers. Reporting consensus studies with greater clarity and transparency may enhance trust in the recommendations made by consensus panels.

Open science practices need substantial improvement in prognostic model studies in oncology using machine learning.

OBJECTIVE: To describe the frequency of open science practices in a contemporary sample of studies developing prognostic models using machine learning methods in the field of oncology. STUDY DESIGN AND SETTING: We conducted a systematic review, searching the MEDLINE database between December 1, 2022, and December 31, 2022, for studies developing a multivariable prognostic model using machine learning methods (as defined by the authors) in oncology. Two authors independently screened records and extracted open science practices. RESULTS: We identified 46 publications describing the development of a multivariable prognostic model. The adoption of open science principles was poor. Only one study reported availability of a study protocol, and only one study was registered. Funding statements and conflicts of interest statements were common. Thirty-five studies (76%) provided data sharing statements, with 21 (46%) indicating data were available on request to the authors and seven declaring data sharing was not applicable. Two studies (4%) shared data. Only 12 studies (26%) provided code sharing statements, including 2 (4%) that indicated the code was available on request to the authors. Only 11 studies (24%) provided sufficient information to allow their model to be used in practice. The use of reporting guidelines was rare: eight studies (18%) mentioning using a reporting guideline, with 4 (10%) using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis Or Diagnosis statement, 1 (2%) using Minimum Information About Clinical Artificial Intelligence Modeling and Consolidated Standards Of Reporting Trials-Artificial Intelligence, 1 (2%) using Strengthening The Reporting Of Observational Studies In Epidemiology, 1 (2%) using Standards for Reporting Diagnostic Accuracy Studies, and 1 (2%) using Transparent Reporting of Evaluations with Nonrandomized Designs. CONCLUSION: The adoption of open science principles in oncology studies developing prognostic models using machine learning methods is poor. Guidance and an increased awareness of benefits and best practices of open science are needed for prediction research in oncology.

The Uptake of the Core Outcome Set for Non-Specific Low Back Pain Clinical Trials is Poor: A Meta-Epidemiological Study of Trial Registrations.

We conducted a meta-epidemiological study on all non-specific low back pain (NSLBP) trial registrations on the World Health Organization International Clinical Trials Registry Platform and ClinicalTrials.gov. We aimed to 1) assess the uptake of the core outcome set (COS) for NSLBP in clinical trials; 2) assess the uptake of the core outcome measurement set for NSLBP in clinical trials; and 3) determine whether specific study characteristics are associated with the COS uptake. After applying the relevant filters for the condition, study type, and phase of the trial, 240 registry entries were included in this study. Only 50 (20.8%) entries showed a full COS uptake, and this rate did not increase over time. Most registry entries that planned to measure physical functioning (n = 152) used the Roland-Morris Disability Questionnaire (n = 74; 48.7%); a small percentage used the numeric rating scale (n = 60; 27.3%) or Short Form-12 (n = 5; 8.3%) if they planned to measure pain intensity (n = 220) or health-related quality of life (n = 60), respectively. Only the planned sample size (OR = 1.02; 95% CI = 1.01, 1.03) showed a significant but small association with COS uptake. The uptake of the COS for NSLBP is poor. Only 21% of the randomized controlled trials aimed to measure all COS domains in their study registration and COS uptake is not increased over time. Great heterogeneity in measurement instruments was also observed, revealing poor core outcome measurement set uptake. PERSPECTIVE: The Core Outcome Set (COS) for non-specific low back pain was published more than 20 years ago. We evaluated whether trial registrations are using this set of outcomes when testing interventions for low back pain. Full uptake was found only in 21% of the sample, and this is not increasing over time. Researchers should use the COS to ensure that trials measure relevant outcomes consistently.

An evidence-informed policymaking (EIPM) competency profile for the Brazilian Health System developed through consensus: process and outcomes.

BACKGROUND: Evidence-informed policymaking (EIPM) requires a set of individual and organizational knowledge, skills and attitudes that should be articulated with background factors and needs. In this regard, the development of an EIPM competency profile is important to support the diagnosis, planning and implementation of EIPM. PURPOSE: To present the process and outcomes of the development of an EIPM competency profile by an expert committee, to be applied in different contexts of the Brazilian Health System. METHODS: A committee of experts in EIPM shared different views, experiences and opinions to develop an EIPM competency profile for Brazil. In six consensus workshops mediated by facilitators, the committee defined from macro problems to key actions and performances essential for the competency profile. The development steps consisted of: (1) Constitution of the committee, including researchers, professionals with practical experience, managers, and educators; (2) Development of a rapid review on EIPM competency profiles; (3) Agreement on commitments and responsibilities in the processes; (4) Identification and definition of macro problems relating to the scope of the competency profile; and (5) Outlining of general and specific capacities, to be incorporated into the competency profile, categorized by key actions. RESULTS: The development of the EIPM competency profile was guided by the following macro problems: (1) lack of systematic and transparent decision-making processes in health policy management; (2) underdeveloped institutional capacity for knowledge management and translation; and (3) incipient use of scientific evidence in the formulation and implementation of health policies. A general framework of key actions and performances of the EIPM Competency Profile for Brazil was developed, including 42 specific and general key actions distributed by area of activity (Health Management, Scientific Research, Civil Society, Knowledge Translation, and Cross-sectional areas). CONCLUSIONS: The competency profile presented in this article can be used in different contexts as a key tool for the institutionalization of EIPM.

Artificial intelligence in lung cancer diagnostic imaging: a review of the reporting and conduct of research published 2018-2019.

Objective: This study aimed to describe the methodologies used to develop and evaluate models that use artificial intelligence (AI) to analyse lung images in order to detect, segment (outline borders of), or classify pulmonary nodules as benign or malignant. Methods: In October 2019, we systematically searched the literature for original studies published between 2018 and 2019 that described prediction models using AI to evaluate human pulmonary nodules on diagnostic chest images. Two evaluators independently extracted information from studies, such as study aims, sample size, AI type, patient characteristics, and performance. We summarised data descriptively. Results: The review included 153 studies: 136 (89%) development-only studies, 12 (8%) development and validation, and 5 (3%) validation-only. CT scans were the most common type of image type used (83%), often acquired from public databases (58%). Eight studies (5%) compared model outputs with biopsy results. 41 studies (26.8%) reported patient characteristics. The models were based on different units of analysis, such as patients, images, nodules, or image slices or patches. Conclusion: The methods used to develop and evaluate prediction models using AI to detect, segment, or classify pulmonary nodules in medical imaging vary, are poorly reported, and therefore difficult to evaluate. Transparent and complete reporting of methods, results and code would fill the gaps in information we observed in the study publications. Advances in knowledge: We reviewed the methodology of AI models detecting nodules on lung images and found that the models were poorly reported and had no description of patient characteristics, with just a few comparing models' outputs with biopsies results. When lung biopsy is not available, lung-RADS could help standardise the comparisons between the human radiologist and the machine. The field of radiology should not give up principles from the diagnostic accuracy studies, such as the choice for the correct ground truth, just because AI is used. Clear and complete reporting of the reference standard used would help radiologists trust in the performance that AI models claim to have. This review presents clear recommendations about the essential methodological aspects of diagnostic models that should be incorporated in studies using AI to help detect or segmentate lung nodules. The manuscript also reinforces the need for more complete and transparent reporting, which can be helped using the recommended reporting guidelines.

Reporting guidelines used varying methodology to develop recommendations.

BACKGROUND AND OBJECTIVES: We investigated the developing methods of reporting guidelines in the EQUATOR (Enhancing the QUAlity and Transparency Of health Research) Network's database. METHODS: In October 2018, we screened all records and excluded those not describing reporting guidelines from further investigation. Twelve researchers performed duplicate data extraction on bibliometrics, scope, development methods, presentation, and dissemination of all publications. Descriptive statistics were used to summarize the findings. RESULTS: Of the 405 screened records, 262 described a reporting guidelines development. The number of reporting guidelines increased over the past 3 decades, from 5 in the 1990s and 63 in the 2000s to 157 in the 2010s. Development groups included 2-151 people. Literature appraisal was performed during the development of 56% of the reporting guidelines; 33% used surveys to gather external opinion on items to report; and 42% piloted or sought external feedback on their recommendations. Examples of good reporting for all reporting items were presented in 30% of the reporting guidelines. Eighteen percent of the reviewed publications included some level of spin. CONCLUSION: Reporting guidelines have been developed with varying methodology. Reporting guideline developers should use existing guidance and take an evidence-based approach, rather than base their recommendations on expert opinion of limited groups of individuals.

Efficacy and safety of hemodialysis strategies for pregnant women with chronic kidney disease: Systematic review.

Pregnancy in chronic kidney disease (CKD) women is relatively rare, and the less risky choice of hemodialysis is unknown. The objective of this systematic review was to identify, systematically evaluate and summarize the available evidence on the efficacy and safety of hemodialysis strategies for pregnant CKD women. Sensitive search strategies were applied to six databases without data or language restrictions. Comparative (randomized and non-randomized) studies were prioritized. Two reviewers independently selected, extracted, and critically evaluated data from studies. The risk of bias assessment was performed using the ROBINS-I tool, considering the study design (non-randomized comparative observational studies). The certainty of the evidence was assessed using the GRADE approach. From 7210 references identified, six retrospective cohort studies were included (576 women). The effects of intensive hemodialysis (over 20 h/week) are uncertain for maternal and neonatal mortality (Peto odds ratio [OR] 0.85; 95% confidence interval [95% CI] 0.26-2.80), miscarriage (Peto OR 0, 38; 95% CI 0.12-1.23), stillbirths (Peto OR 0, 56; 95% CI 0.13-2.31), preterm birth (Peto OR 0.87; 95% CI 0.33-2.28), low birth weight (Peto OR 0.71; 95% CI 0.20-2.50) and congenital anomalies rates. The certainty of the evidence was very low due to studies methodological limitations and effect estimates imprecision. The uncertainty about intensive versus conventional hemodialysis effects for pregnant women with CKD and the imprecision in the estimated effects precludes any recommendation. The strategy choice must consider treatment availability, costs, and maternal social aspects until future studies provide more reliable evidence. PROSPERO CRD42021259237.

Existing guidance on reporting of consensus methodology: a systematic review to inform ACCORD guideline development.

OBJECTIVE: To identify evidence on the reporting quality of consensus methodology and to select potential checklist items for the ACcurate COnsensus Reporting Document (ACCORD) project to develop a consensus reporting guideline. DESIGN: Systematic review. DATA SOURCES: Embase, MEDLINE, Web of Science, PubMed, Cochrane Library, Emcare, Academic Search Premier and PsycINFO from inception until 7 January 2022. ELIGIBILITY CRITERIA: Studies, reviews and published guidance addressing the reporting quality of consensus methodology for improvement of health outcomes in biomedicine or clinical practice. Reports of studies using or describing consensus methods but not commenting on their reporting quality were excluded. No language restrictions were applied. DATA EXTRACTION AND SYNTHESIS: Screening and data extraction of eligible studies were carried out independently by two authors. Reporting quality items addressed by the studies were synthesised narratively. RESULTS: Eighteen studies were included: five systematic reviews, four narrative reviews, three research papers, three conference abstracts, two research guidance papers and one protocol. The majority of studies indicated that the quality of reporting of consensus methodology could be improved. Commonly addressed items were: consensus panel composition; definition of consensus and the threshold for achieving consensus. Items least addressed were: public patient involvement (PPI); the role of the steering committee, chair, cochair; conflict of interest of panellists and funding. Data extracted from included studies revealed additional items that were not captured in the data extraction form such as justification of deviation from the protocol or incentives to encourage panellist response. CONCLUSION: The results of this systematic review confirmed the need for a reporting checklist for consensus methodology and provided a range of potential checklist items to report. The next step in the ACCORD project builds on this systematic review and focuses on reaching consensus on these items to develop the reporting guideline. PROTOCOL REGISTRATION: https://osf.io/2rzm9.

AGREE-S: AGREE II extension for surgical interventions: appraisal instrument.

BACKGROUND: The Appraisal of Guidelines Research and Evaluation (AGREE) II instrument was developed to evaluate the quality of clinical practice guidelines. Evidence suggests that development, reporting, and appraisal of guidelines on surgical interventions may be better informed by modification of the instrument. OBJECTIVE: We aimed to develop an AGREE II extension specifically designed for appraisal of guidelines of surgical interventions. METHODS: In a three-part project funded by the United European Gastroenterology and the European Association for Endoscopic Surgery, (i) we identified factors that were associated with higher quality of surgical guidelines, (ii) we statistically calibrated the AGREE II instrument in the context of surgical guidelines using correlation, reliability, and factor analysis, and (iii) we undertook a Delphi consensus process of stakeholders to inform the development of an AGREE II extension instrument for surgical interventions. RESULTS: Several features were prioritized by stakeholders as of particular importance for guidelines of surgical interventions, including development of a guideline protocol, consideration of practice variability and surgical expertise in different settings, and specification of infrastructures required to implement the recommendations. The AGREE-S-AGREE II extension instrument for surgical interventions has 25 items, compared to the 23 items of the original AGREE II instrument, organized into the following 6 domains: Scope and purpose, Stakeholders, Evidence synthesis, Development of recommendations, Editorial independence, and Implementation and update. As the original instrument, it concludes with an overall appraisal of the quality of the guideline and a judgement on whether the guideline is recommended for use. Several items were amended and rearranged among domains, and an item was deleted. The Rigor of Development domain of the original AGREE II was divided into Evidence Synthesis and Development of Recommendations. Items of the AGREE II domain Clarity of Presentation were incorporated in the new domain Development of Recommendations. Three new items were introduced, addressing the development of a guideline protocol, support by a guideline methodologist, and consideration of surgical experience/expertise. CONCLUSION: The AGREE-S appraisal instrument has been developed to be used for assessment of the methodological and reporting quality of guidelines on surgical interventions.

ACCORD guideline for reporting consensus-based methods in biomedical research and clinical practice: a study protocol.

BACKGROUND: Structured, systematic methods to formulate consensus recommendations, such as the Delphi process or nominal group technique, among others, provide the opportunity to harness the knowledge of experts to support clinical decision making in areas of uncertainty. They are widely used in biomedical research, in particular where disease characteristics or resource limitations mean that high-quality evidence generation is difficult. However, poor reporting of methods used to reach a consensus - for example, not clearly explaining the definition of consensus, or not stating how consensus group panellists were selected - can potentially undermine confidence in this type of research and hinder reproducibility. Our objective is therefore to systematically develop a reporting guideline to help the biomedical research and clinical practice community describe the methods or techniques used to reach consensus in a complete, transparent, and consistent manner. METHODS: The ACCORD (ACcurate COnsensus Reporting Document) project will take place in five stages and follow the EQUATOR Network guidance for the development of reporting guidelines. In Stage 1, a multidisciplinary Steering Committee has been established to lead and coordinate the guideline development process. In Stage 2, a systematic literature review will identify evidence on the quality of the reporting of consensus methodology, to obtain potential items for a reporting checklist. In Stage 3, Delphi methodology will be used to reach consensus regarding the checklist items, first among the Steering Committee, and then among a broader Delphi panel comprising participants with a range of expertise, including patient representatives. In Stage 4, the reporting guideline will be finalised in a consensus meeting, along with the production of an Explanation and Elaboration (E&E) document. In Stage 5, we plan to publish the reporting guideline and E&E document in open-access journals, supported by presentations at appropriate events. Dissemination of the reporting guideline, including a website linked to social media channels, is crucial for the document to be implemented in practice. DISCUSSION: The ACCORD reporting guideline will provide a set of minimum items that should be reported about methods used to achieve consensus, including approaches ranging from simple unstructured opinion gatherings to highly structured processes.

Perfil de competência do profissional em PIE no Brasil: relatório / Projeto ESPIE / Professional competency profile in PIE in Brazil: report / ESPIE Project

O projeto Apoio à Formulação e Implementação de Políticas Públicas de Saúde Informadas por Evidências (ESPIE) é desenvolvido pelo Instituto Sírio-Libanês de Ensino e Pesquisa do Hospital Sírio-Libanês (IEP/HSL), no âmbito do Programa de Apoio ao Desenvolvimento Institucional do Sistema Único de Saúde (PROADI-SUS), em parceria com o Departamento de Ciência e Tecnologia da Secretaria de Ciência, Tecnologia, Inovação e Insumos Estratégicos do Ministério da Saúde (DECIT/SCTIE/MS). O projeto ESPIE desenvolveu o Perfil de Competência do Profissional de PIE para o Brasil, com o objetivo de subsidiar atividades educacionais relacionadas com Políticas Informadas por Evidências (PIE), mas também apoiar o planejamento e ações de diferentes organizações no contexto da gestão da saúde no Sistema Único de Saúde (SUS). O perfil de competência foi desenvolvido e validado por um grupo de autoria constituído por técnicos das instituições envolvidas e especialistas convidados. O objetivo de criação do grupo de autoria foi agregar diferentes visões, experiências e opiniões ao processo de construção do perfil de competência em PIE. O grupo de autoria discutiu e definiu, ao longo de seis oficinas realizadas no ano de 2021, desde os macroproblemas até as ações-chave e desempenhos considerados essenciais. O processo de elaboração deste perfil foi orientado pelos seguintes macroproblemas: 1) processos decisórios na gestão das políticas de saúde pouco sistemáticos e transparentes; 2) capacidade institucional para gestão e tradução do conhecimento pouco desenvolvida e 3) incipiente incorporação das evidências científicas ao processo de formulação e implementação de políticas de saúde. Este documento consiste um meta-ponto de vista sobre o perfil de competência do profissional de PIE no Brasil e está endereçado aos macroproblemas no âmbito do SUS e inclui ações-chave e desempenhos que compõem um conjunto de conhecimentos, habilidades e atitudes, necessário para uma atuação institucional competente em PIE.

Improving medical research in the United Kingdom.

Poor quality medical research causes serious harms by misleading healthcare professionals and policymakers, decreasing trust in science and medicine, and wasting public funds. Here we outline underlying problems including insufficient transparency, dysfunctional incentives, and reporting biases. We make the following recommendations to address these problems: Journals and funders should ensure authors fulfil their obligation to share detailed study protocols, analytical code, and (as far as possible) research data. Funders and journals should incentivise uptake of registered reports and establish funding pathways which integrate evaluation of funding proposals with initial peer review of registered reports. A mandatory national register of interests for all those who are involved in medical research in the UK should be established, with an expectation that individuals maintain the accuracy of their declarations and regularly update them. Funders and institutions should stop using metrics such as citations and journal's impact factor to assess research and researchers and instead evaluate based on quality, reproducibility, and societal value. Employers and non-academic training programmes for health professionals (clinicians hired for patient care, not to do research) should not select based on number of research publications. Promotions based on publication should be restricted to those hired to do research.

AGREE-S: AGREE II extension for surgical interventions - United European Gastroenterology and European Association for Endoscopic Surgery methodological guide.

BACKGROUND: The Appraisal of Guidelines for Research and Evaluation (AGREE) II instrument has been developed to inform the methodology, reporting and appraisal of clinical practice guidelines. Evidence suggests that the quality of surgical guidelines can be improved, and the structure and content of AGREE II can be modified to help enhance the quality of guidelines of surgical interventions. OBJECTIVE: To develop an extension of AGREE II specifically designed for guidelines of surgical interventions. METHODS: In the tripartite Guideline Assessment Project (GAP) funded by United European Gastroenterology and the European Association for Endoscopic Surgery, (i) we assessed the quality of surgical guidelines and we identified factors associated with higher quality (GAP I); (ii) we applied correlation analysis, factor analysis and the item response theory to inform an adaption of AGREE II for the purposes of surgical guidelines (GAP II); and (iii) we developed an AGREE II extension for surgical interventions, informed by the results of GAP I, GAP II, and a Delphi process of stakeholders, including representation from interventional and surgical disciplines; the Guideline International Network (GIN); the Grading of Recommendations Assessment, Development and Evaluation (GRADE) Working Group; the Enhancing the QUAlity and Transparency Of health Research (EQUATOR) initiative; and representation of surgical journal editors and patient/public. RESULTS: We developed AGREE-S, an AGREE II extension for surgical interventions, which comprises 24 items organized in 6 domains; Scope and purpose, Stakeholders, Evidence synthesis, Development of recommendations, Editorial independence, and Implementation and update. The panel of stakeholders proposed 3 additional items: development of a guideline protocol, consideration of practice variability and surgical/interventional expertise in different settings, and specification of infrastructures required to implement the recommendations. Three of the existing items were amended, 7 items were rearranged among the domains, and one item was removed. The domain Rigour of Development was divided into domains on Evidence Synthesis and Development of Recommendations. The new domain Development of Recommendations incorporates items from the original AGREE II domain Clarity of Presentation. CONCLUSION: AGREE-S is an evidence-based and stakeholder-informed extension of the AGREE II instrument, that can be used as a guide for the development and adaption of guidelines on surgical interventions.

Efficacy and safety of home-based intravenous antibiotic therapy among adults: a systematic review.

The aim of this study was to identify, systematically assess and summarise the available evidence about the efficacy and safety of intravenous home antibiotic therapy. In this systematic review, we considered studies of adults with any kind of infection and recommended intravenous antibiotic therapy. We included studies comparing therapy given at the patient's home versus any other setting (other levels of healthcare services or sites). We performed wide and sensitive literature searches with strategies adjusted for each of the electronic databases, including CINAHL, ClinicalTrials.gov, Cochrane Library, Embase, Epistemonikos, Health System Evidence, LILACS, MEDLINE and grey literature (OpenGrey). We used the Cochrane risk-of-bias and GRADE tools to evaluate the risk of bias and the certainty of evidence. At least two reviewers, working independently, selected the studies, extracted data and critically evaluated the evidence. We performed random-effects meta-analyses where possible. From 20 099 references initially identified, we included 6 randomised controlled trials (RCTs) with 616 participants. We considered the certainty of the body of evidence as low to very low regarding infection resolution after 6 weeks, risk of adverse events, mortality and clinical status. Based on six RCTs with considerable risk of bias, this systematic review found low or very low evidence about the advantages of intravenous antibiotic therapy at home. The imprecision of the results does not allow us to recommend or contraindicate the use of this strategy in clinical practice. [PROSPERO register: this review protocol was prospectively submitted at the PROSPERO register base at 31 January 2021 (submission no. 42021234454)].

GoodReports: developing a website to help health researchers find and use reporting guidelines.

BACKGROUND: Th EQUATOR Network improves the quality and transparency in health research, primarily by promoting awareness and use of reporting guidelines. In 2018, the UK EQUATOR Centre launched GoodReports.org , a website that helps authors find and use reporting guidelines. This paper describes the tool's development so far. We describe user experience and behaviour of using GoodReports.org both inside and outside a journal manuscript submission process. We intend to use our findings to inform future development and testing of the tool. METHODS: We conducted a survey to collect data on user experience of the GoodReports website. We cross-checked a random sample of 100 manuscripts submitted to a partner journal to describe the level of agreement between the tool's checklist recommendation and what we would have recommended. We compared the proportion of authors submitting a completed reporting checklist alongside their manuscripts between groups exposed or not exposed to the GoodReports tool. We also conducted a study comparing completeness of reporting of manuscript text before an author received a reporting guideline recommendation from GoodReports.org with the completeness of the text subsequently submitted to a partner journal. RESULTS: Seventy percent (423/599) of survey respondents rated GoodReports 8 or more out of 10 for usefulness, and 74% (198/267) said they had made changes to their manuscript after using the website. We agreed with the GoodReports reporting guideline recommendation in 84% (72/86) of cases. Of authors who completed the guideline finder questionnaire, 14% (10/69) failed to submit a completed checklist compared to 30% (41/136) who did not use the tool. Of the 69 authors who received a GoodReports reporting guideline recommendation, 20 manuscript pairs could be reviewed before and after use of GoodReports. Five included more information in their methods section after exposure to GoodReports. On average, authors reported 57% of necessary reporting items before completing a checklist on GoodReports.org and 60% after. CONCLUSION: The data suggest that reporting guidance is needed early in the writing process, not at submission stage. We are developing GoodReports by adding more reporting guidelines and by creating editable article templates. We will test whether GoodReports users write more complete study reports in a randomised trial targeting researchers starting to write health research articles.

Protocol for development of a reporting guideline (TRIPOD-AI) and risk of bias tool (PROBAST-AI) for diagnostic and prognostic prediction model studies based on artificial intelligence.

INTRODUCTION: The Transparent Reporting of a multivariable prediction model of Individual Prognosis Or Diagnosis (TRIPOD) statement and the Prediction model Risk Of Bias ASsessment Tool (PROBAST) were both published to improve the reporting and critical appraisal of prediction model studies for diagnosis and prognosis. This paper describes the processes and methods that will be used to develop an extension to the TRIPOD statement (TRIPOD-artificial intelligence, AI) and the PROBAST (PROBAST-AI) tool for prediction model studies that applied machine learning techniques. METHODS AND ANALYSIS: TRIPOD-AI and PROBAST-AI will be developed following published guidance from the EQUATOR Network, and will comprise five stages. Stage 1 will comprise two systematic reviews (across all medical fields and specifically in oncology) to examine the quality of reporting in published machine-learning-based prediction model studies. In stage 2, we will consult a diverse group of key stakeholders using a Delphi process to identify items to be considered for inclusion in TRIPOD-AI and PROBAST-AI. Stage 3 will be virtual consensus meetings to consolidate and prioritise key items to be included in TRIPOD-AI and PROBAST-AI. Stage 4 will involve developing the TRIPOD-AI checklist and the PROBAST-AI tool, and writing the accompanying explanation and elaboration papers. In the final stage, stage 5, we will disseminate TRIPOD-AI and PROBAST-AI via journals, conferences, blogs, websites (including TRIPOD, PROBAST and EQUATOR Network) and social media. TRIPOD-AI will provide researchers working on prediction model studies based on machine learning with a reporting guideline that can help them report key details that readers need to evaluate the study quality and interpret its findings, potentially reducing research waste. We anticipate PROBAST-AI will help researchers, clinicians, systematic reviewers and policymakers critically appraise the design, conduct and analysis of machine learning based prediction model studies, with a robust standardised tool for bias evaluation. ETHICS AND DISSEMINATION: Ethical approval has been granted by the Central University Research Ethics Committee, University of Oxford on 10-December-2020 (R73034/RE001). Findings from this study will be disseminated through peer-review publications. PROSPERO REGISTRATION NUMBER: CRD42019140361 and CRD42019161764.