Dataset Information

Reporting and methods in clinical prediction research: a systematic review.

ABSTRACT:

Background

We investigated the reporting and methods of prediction studies, focusing on aims, designs, participant selection, outcomes, predictors, statistical power, statistical methods, and predictive performance measures.

Methods and findings

We used a full hand search to identify all prediction studies published in 2008 in six high impact general medical journals. We developed a comprehensive item list to systematically score conduct and reporting of the studies, based on recent recommendations for prediction research. Two reviewers independently scored the studies. We retrieved 71 papers for full text review: 51 were predictor finding studies, 14 were prediction model development studies, three addressed an external validation of a previously developed model, and three reported on a model's impact on participant outcome. Study design was unclear in 15% of studies, and a prospective cohort was used in most studies (60%). Descriptions of the participants and definitions of predictor and outcome were generally good. Despite many recommendations against doing so, continuous predictors were often dichotomized (32% of studies). The number of events per predictor as a measure of statistical power could not be determined in 67% of the studies; of the remainder, 53% had fewer than the commonly recommended value of ten events per predictor. Methods for a priori selection of candidate predictors were described in most studies (68%). A substantial number of studies relied on a p-value cut-off of p<0.05 to select predictors in the multivariable analyses (29%). Predictive model performance measures, i.e., calibration and discrimination, were reported in 12% and 27% of studies, respectively.

Conclusions

The majority of prediction studies in high impact journals do not follow current methodological recommendations, limiting their reliability and applicability.

SUBMITTER: Bouwmeester W

PROVIDER: S-EPMC3358324 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Reporting and methods in clinical prediction research: a systematic review.

Bouwmeester Walter W Zuithoff Nicolaas P A NP Mallett Susan S Geerlings Mirjam I MI Vergouwe Yvonne Y Steyerberg Ewout W EW Altman Douglas G DG Moons Karel G M KG

PLoS medicine 20120522 5

<h4>Background</h4>We investigated the reporting and methods of prediction studies, focusing on aims, designs, participant selection, outcomes, predictors, statistical power, statistical methods, and predictive performance measures.<h4>Methods and findings</h4>We used a full hand search to identify all prediction studies published in 2008 in six high impact general medical journals. We developed a comprehensive item list to systematically score conduct and reporting of the studies, based on rece ...[more]

PMID: 22629234

Similar Datasets

Project description:BackgroundWith the growing excitement of the potential benefits of using machine learning and artificial intelligence in medicine, the number of published clinical prediction models that use these approaches has increased. However, there is evidence (albeit limited) that suggests that the reporting of machine learning-specific aspects in these studies is poor. Further, there are no reviews assessing the reporting quality or broadly accepted reporting guidelines for these aspects.ObjectiveThis paper presents the protocol for a systematic review that will assess the reporting quality of machine learning-specific aspects in studies that use machine learning to develop clinical prediction models.MethodsWe will include studies that use a supervised machine learning algorithm to develop a prediction model for use in clinical practice (ie, for diagnosis or prognosis of a condition or identification of candidates for health care interventions). We will search MEDLINE for studies published in 2019, pseudorandomly sort the records, and screen until we obtain 100 studies that meet our inclusion criteria. We will assess reporting quality with a novel checklist developed in parallel with this review, which includes content derived from existing reporting guidelines, textbooks, and consultations with experts. The checklist will cover 4 key areas where the reporting of machine learning studies is unique: modelling steps (order and data used for each step), model performance (eg, reporting the performance of each model compared), statistical methods (eg, describing the tuning approach), and presentation of models (eg, specifying the predictors that contributed to the final model).ResultsWe completed data analysis in August 2021 and are writing the manuscript. We expect to submit the results to a peer-reviewed journal in early 2022.ConclusionsThis review will contribute to more standardized and complete reporting in the field by identifying areas where reporting is poor and can be improved.Trial registrationPROSPERO International Prospective Register of Systematic Reviews CRD42020206167; https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=206167.International registered report identifier (irrid)RR1-10.2196/30956.

Project description:BackgroundWhile many studies have consistently found incomplete reporting of regression-based prediction model studies, evidence is lacking for machine learning-based prediction model studies. We aim to systematically review the adherence of Machine Learning (ML)-based prediction model studies to the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) Statement.MethodsWe included articles reporting on development or external validation of a multivariable prediction model (either diagnostic or prognostic) developed using supervised ML for individualized predictions across all medical fields. We searched PubMed from 1 January 2018 to 31 December 2019. Data extraction was performed using the 22-item checklist for reporting of prediction model studies ( www.TRIPOD-statement.org ). We measured the overall adherence per article and per TRIPOD item.ResultsOur search identified 24,814 articles, of which 152 articles were included: 94 (61.8%) prognostic and 58 (38.2%) diagnostic prediction model studies. Overall, articles adhered to a median of 38.7% (IQR 31.0-46.4%) of TRIPOD items. No article fully adhered to complete reporting of the abstract and very few reported the flow of participants (3.9%, 95% CI 1.8 to 8.3), appropriate title (4.6%, 95% CI 2.2 to 9.2), blinding of predictors (4.6%, 95% CI 2.2 to 9.2), model specification (5.2%, 95% CI 2.4 to 10.8), and model's predictive performance (5.9%, 95% CI 3.1 to 10.9). There was often complete reporting of source of data (98.0%, 95% CI 94.4 to 99.3) and interpretation of the results (94.7%, 95% CI 90.0 to 97.3).ConclusionSimilar to prediction model studies developed using conventional regression-based techniques, the completeness of reporting is poor. Essential information to decide to use the model (i.e. model specification and its performance) is rarely reported. However, some items and sub-items of TRIPOD might be less suitable for ML-based prediction model studies and thus, TRIPOD requires extensions. Overall, there is an urgent need to improve the reporting quality and usability of research to avoid research waste.Systematic review registrationPROSPERO, CRD42019161764.

Project description:BackgroundThere has been a rapid growth in the publication of new prediction models relevant to child and adolescent mental health. However, before their implementation into clinical services, it is necessary to appraise the quality of their methods and reporting. We conducted a systematic review of new prediction models in child and adolescent mental health, and examined their development and validation.MethodWe searched five databases for studies developing or validating multivariable prediction models for individuals aged 18 years old or younger from 1 January 2018 to 18 February 2021. Quality of reporting was assessed using the Transparent Reporting of a multivariable prediction models for Individual Prognosis Or Diagnosis checklist, and quality of methodology using items based on expert guidance and the PROBAST tool.ResultsWe identified 100 eligible studies: 41 developing a new prediction model, 48 validating an existing model and 11 that included both development and validation. Most publications (k = 75) reported a model discrimination measure, while 26 investigations reported calibration. Of 52 new prediction models, six (12%) were for suicidal outcomes, 18 (35%) for future diagnosis, five (10%) for child maltreatment. Other outcomes included violence, crime, and functional outcomes. Eleven new models (21%) were developed for use in high-risk populations. Of development studies, around a third were sufficiently statistically powered (k = 16%, 31%), while this was lower for validation investigations (k = 12, 25%). In terms of performance, the discrimination (as measured by the C-statistic) for new models ranged from 0.57 for a tool predicting ADHD diagnosis in an external validation sample to 0.99 for a machine learning model predicting foster care permanency.ConclusionsAlthough some tools have recently been developed for child and adolescent mental health for prognosis and child maltreatment, none can be currently recommended for clinical practice due to a combination of methodological limitations and poor model performance. New work needs to use ensure sufficient sample sizes, representative samples, and testing of model calibration.

Project description:BackgroundRandomised controlled trials (RCTs) represent the gold standard methodological design to evaluate the effectiveness of an intervention in humans but they are subject to bias, including study publication bias and outcome reporting bias. National and international organisations and charities give recommendations for good research practice in relation to RCTs but to date no review of these guidelines has been undertaken with respect to reporting bias.MethodsNational and international organisations and UK based charities listed on the Association for Medical Research Charities website were contacted in 2007; they were considered eligible for this review if they funded RCTs. Guidelines were obtained and assessed in relation to what was written about trial registration, protocol adherence and trial publication. It was also noted whether any monitoring against these guidelines was undertaken. This information was necessary to discover how much guidance researchers are given on the publication of results, in order to prevent study publication bias and outcome reporting bias.ResultsSeventeen organisations and 56 charities were eligible of 140 surveyed for this review, although there was no response from 12. Trial registration, protocol adherence, trial publication and monitoring against the guidelines were often explicitly discussed or implicitly referred too. However, only eleven of these organisations or charities mentioned the publication of negative as well as positive outcomes and just three of the organisations specifically stated that the statistical analysis plan should be strictly adhered to and all changes should be reported.ConclusionOur review indicates that there is a need to provide more detailed guidance for those conducting and reporting clinical trials to help prevent the selective reporting of results. Statements found in the guidelines generally refer to publication bias rather than outcome reporting bias. Current guidelines need to be updated and include the statement that all primary and secondary outcomes prespecified in the protocol should be fully reported and should not be selected for inclusion in the final report based on their results.

Project description:BackgroundIn diagnostic studies, a single and error-free test that can be used as the reference (gold) standard often does not exist. One solution is the use of panel diagnosis, i.e., a group of experts who assess the results from multiple tests to reach a final diagnosis in each patient. Although panel diagnosis, also known as consensus or expert diagnosis, is frequently used as the reference standard, guidance on preferred methodology is lacking. The aim of this study is to provide an overview of methods used in panel diagnoses and to provide initial guidance on the use and reporting of panel diagnosis as reference standard.Methods and findingsPubMed was systematically searched for diagnostic studies applying a panel diagnosis as reference standard published up to May 31, 2012. We included diagnostic studies in which the final diagnosis was made by two or more persons based on results from multiple tests. General study characteristics and details of panel methodology were extracted. Eighty-one studies were included, of which most reported on psychiatry (37%) and cardiovascular (21%) diseases. Data extraction was hampered by incomplete reporting; one or more pieces of critical information about panel reference standard methodology was missing in 83% of studies. In most studies (75%), the panel consisted of three or fewer members. Panel members were blinded to the results of the index test results in 31% of studies. Reproducibility of the decision process was assessed in 17 (21%) studies. Reported details on panel constitution, information for diagnosis and methods of decision making varied considerably between studies.ConclusionsMethods of panel diagnosis varied substantially across studies and many aspects of the procedure were either unclear or not reported. On the basis of our review, we identified areas for improvement and developed a checklist and flow chart for initial guidance for researchers conducting and reporting of studies involving panel diagnosis. Please see later in the article for the Editors' Summary.

Project description:ObjectiveTo assess whether the completeness of reporting of health research is related to journals' endorsement of reporting guidelines.DesignSystematic review.Data sourcesReporting guidelines from a published systematic review and the EQUATOR Network (October 2011). Studies assessing the completeness of reporting by using an included reporting guideline (termed "evaluations") (1990 to October 2011; addendum searches in January 2012) from searches of either Medline, Embase, and the Cochrane Methodology Register or Scopus, depending on reporting guideline name.Study selectionEnglish language reporting guidelines that provided explicit guidance for reporting, described the guidance development process, and indicated use of a consensus development process were included. The CONSORT statement was excluded, as evaluations of adherence to CONSORT had previously been reviewed. English or French language evaluations of included reporting guidelines were eligible if they assessed the completeness of reporting of studies as a primary intent and those included studies enabled the comparisons of interest (that is, after versus before journal endorsement and/or endorsing versus non-endorsing journals).Data extractionPotentially eligible evaluations of included guidelines were screened initially by title and abstract and then as full text reports. If eligibility was unclear, authors of evaluations were contacted; journals' websites were consulted for endorsement information where needed. The completeness of reporting of reporting guidelines was analyzed in relation to endorsement by item and, where consistent with the authors' analysis, a mean summed score.Results101 reporting guidelines were included. Of 15,249 records retrieved from the search for evaluations, 26 evaluations that assessed completeness of reporting in relation to endorsement for nine reporting guidelines were identified. Of those, 13 evaluations assessing seven reporting guidelines (BMJ economic checklist, CONSORT for harms, PRISMA, QUOROM, STARD, STRICTA, and STROBE) could be analyzed. Reporting guideline items were assessed by few evaluations.ConclusionsThe completeness of reporting of only nine of 101 health research reporting guidelines (excluding CONSORT) has been evaluated in relation to journals' endorsement. Items from seven reporting guidelines were quantitatively analyzed, by few evaluations each. Insufficient evidence exists to determine the relation between journals' endorsement of reporting guidelines and the completeness of reporting of published health research reports. Journal editors and researchers should consider collaborative prospectively designed, controlled studies to provide more robust evidence.Systematic review registrationNot registered; no known register currently accepts protocols for methodology systematic reviews.

Project description:BACKGROUND:Pictorial blood loss assessment charts (PBACs) represent the most widely used method to assess menstrual blood loss (MBL) in clinical trials. The aims of this review were to: (1) determine the diagnostic accuracy of PBACs that have been validated against the reference alkaline hematin technique; (2) categorize the pitfalls of using obsolete and nonvalidated charts; (3) provide guidelines for development of a new PBAC or use of an existing chart to measure MBL in clinical trials; and (4) consider the feasibility of using pictorial charts in primary care. METHODS:A literature review was conducted using Embase and MEDLINE databases. The review identified reports of women with self-perceived or actual heavy menstrual bleeding (HMB), bleeding disorders, abnormal uterine bleeding, leiomyomata (uterine fibroids) or endometriosis, and women undergoing treatment for HMB, as well as those with normal menstrual periods. Data were reviewed from studies that focused on the development and validation of PBACs and from those that used derivative noncertified charts to assess HMB. RESULTS:Nine studies reported validation of PBAC scoring systems against the alkaline hematin technique. Across these studies, the sensitivity was 58-97%, the specificity was 7.5-95.5%, the positive and negative likelihood ratios were 1.1-13.8 and 0.14-0.56, respectively, and the diagnostic odds ratio was 2.6-52.4. The cut-off score above which the diagnosis of HMB was made ranged from 50 to 185. Several modifications of these PBACs were used in other studies; however, objective confirmation of their validity was not reported. Overall, there was widespread inconsistency of chart design, scoring systems, diagnostic cut-off limits and post-treatment outcome measures. CONCLUSIONS:PBACs are best suited to the controlled and specific environment of clinical studies, where clinical outcome parameters are defined. The current lack of standardization precludes widespread use of the PBAC in primary care. REVIEW REGISTRATION NUMBER:PROSPERO international prospective register of systematic reviews: CRD42016030083.

Dataset Information

Reporting and methods in clinical prediction research: a systematic review.

Background

Methods and findings

Conclusions

Publications

Reporting and methods in clinical prediction research: a systematic review.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets