Dataset Information

The effects of advanced factor analysis approaches on outcomes in randomised trials for depression: protocol for secondary analysis of individual participant data.

ABSTRACT:

Background

Modern psychometric methods make it possible to eliminate nonperforming items and reduce measurement error. Application of these methods to existing outcome measures can reduce variability in scores, and may increase treatment effect sizes in depression treatment trials.

Aims

We aim to determine whether using confirmatory factor analysis techniques can provide better estimates of the true effects of treatments, by conducting secondary analyses of individual patient data from randomised trials of antidepressant therapies.

Method

We will access individual patient data from antidepressant treatment trials through Clinicalstudydatarequest.com and Vivli.org, specifically targeting studies that used the Hamilton Rating Scale for Depression (HRSD) as the outcome measure. Exploratory and confirmatory factor analytic approaches will be used to determine pre-treatment (baseline) and post-treatment models of depression, in terms of the number of factors and weighted scores of each item. Differences in the derived factor scores between baseline and outcome measurements will yield an effect size for factor-informed depression change. The difference between the factor-informed effect size and each original trial effect size, calculated with total HRSD-17 scores, will be determined, and the differences modelled with meta-analytic approaches. Risk differences for proportions of patients who achieved remission will also be evaluated. Furthermore, measurement invariance methods will be used to assess potential gender differences.

Conclusions

Our approach will determine whether adopting advanced psychometric analyses can improve precision and better estimate effect sizes in antidepressant treatment trials. The proposed methods could have implications for future trials and other types of studies that use patient-reported outcome measures.

SUBMITTER: Doyle F

PROVIDER: S-EPMC10594098 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The effects of advanced factor analysis approaches on outcomes in randomised trials for depression: protocol for secondary analysis of individual participant data.

Doyle Frank F Byrne David D Carney Robert M RM Cuijpers Pim P Dima Alexandra L AL Freedland Kenneth K Guerin Suzanne S Hevey David D Kathuria Bishember B Kelly Shane S McBride Stephen S Wallace Emma E Boland Fiona F

BJPsych open 20230811 5

<h4>Background</h4>Modern psychometric methods make it possible to eliminate nonperforming items and reduce measurement error. Application of these methods to existing outcome measures can reduce variability in scores, and may increase treatment effect sizes in depression treatment trials.<h4>Aims</h4>We aim to determine whether using confirmatory factor analysis techniques can provide better estimates of the true effects of treatments, by conducting secondary analyses of individual patient data ...[more]

PMID: 37565446

Similar Datasets

Project description:Parenteral anticoagulants may improve outcomes in patients with cancer by reducing risk of venous thromboembolic disease and through a direct antitumour effect. Study-level systematic reviews indicate a reduction in venous thromboembolism and provide moderate confidence that a small survival benefit exists. It remains unclear if any patient subgroups experience potential benefits.First, we will perform a comprehensive systematic search of MEDLINE, EMBASE and The Cochrane Library, hand search scientific conference abstracts and check clinical trials registries for randomised control trials of participants with solid cancers who are administered parenteral anticoagulants. We anticipate identifying at least 15 trials, exceeding 9000 participants. Second, we will perform an individual participant data meta-analysis to explore the magnitude of survival benefit and address whether subgroups of patients are more likely to benefit from parenteral anticoagulants. All analyses will follow the intention-to-treat principle. For our primary outcome, mortality, we will use multivariable hierarchical models with patient-level variables as fixed effects and a categorical trial variable as a random effect. We will adjust analysis for important prognostic characteristics. To investigate whether intervention effects vary by predefined subgroups of patients, we will test interaction terms in the statistical model. Furthermore, we will develop a risk-prediction model for venous thromboembolism, with a focus on control patients of randomised trials.Aside from maintaining participant anonymity, there are no major ethical concerns. This will be the first individual participant data meta-analysis addressing heparin use among patients with cancer and will directly influence recommendations in clinical practice guidelines. Major cancer guideline development organisations will use eventual results to inform their guideline recommendations. Several knowledge users will disseminate results through presentations at clinical rounds as well as national and international conferences. We will prepare an evidence brief and facilitate dialogue to engage policymakers and stakeholders in acting on findings.PROSPERO CRD42013003526.

Project description:BackgroundIt remains unclear when standard systematic reviews and meta-analyses that rely on published aggregate data (AD) can provide robust clinical conclusions. We aimed to compare the results from a large cohort of systematic reviews and meta-analyses based on individual participant data (IPD) with meta-analyses of published AD, to establish when the latter are most likely to be reliable and when the IPD approach might be required.Methods and findingsWe used 18 cancer systematic reviews that included IPD meta-analyses: all of those completed and published by the Meta-analysis Group of the MRC Clinical Trials Unit from 1991 to 2010. We extracted or estimated hazard ratios (HRs) and standard errors (SEs) for survival from trial reports and compared these with IPD equivalents at both the trial and meta-analysis level. We also extracted or estimated the number of events. We used paired t tests to assess whether HRs and SEs from published AD differed on average from those from IPD. We assessed agreement, and whether this was associated with trial or meta-analysis characteristics, using the approach of Bland and Altman. The 18 systematic reviews comprised 238 unique trials or trial comparisons, including 37,082 participants. A HR and SE could be generated for 127 trials, representing 53% of the trials and approximately 79% of eligible participants. On average, trial HRs derived from published AD were slightly more in favour of the research interventions than those from IPD (HRAD to HRIPD ratio = 0.95, p = 0.007), but the limits of agreement show that for individual trials, the HRs could deviate substantially. These limits narrowed with an increasing number of participants (p < 0.001) or a greater number (p < 0.001) or proportion (p < 0.001) of events in the AD. On average, meta-analysis HRs from published AD slightly tended to favour the research interventions whether based on fixed-effect (HRAD to HRIPD ratio = 0.97, p = 0.088) or random-effects (HRAD to HRIPD ratio = 0.96, p = 0.044) models, but the limits of agreement show that for individual meta-analyses, agreement was much more variable. These limits tended to narrow with an increasing number (p = 0.077) or proportion of events (p = 0.11) in the AD. However, even when the information size of the AD was large, individual meta-analysis HRs could still differ from their IPD equivalents by a relative 10% in favour of the research intervention to 5% in favour of control. We utilised the results to construct a decision tree for assessing whether an AD meta-analysis includes sufficient information, and when estimates of effects are most likely to be reliable. A lack of power at the meta-analysis level may have prevented us identifying additional factors associated with the reliability of AD meta-analyses, and we cannot be sure that our results are generalisable to all outcomes and effect measures.ConclusionsIn this study we found that HRs from published AD were most likely to agree with those from IPD when the information size was large. Based on these findings, we provide guidance for determining systematically when standard AD meta-analysis will likely generate robust clinical conclusions, and when the IPD approach will add considerable value.

Project description:BackgroundLow-dose aspirin is of definite and substantial net benefit for many people who already have occlusive vascular disease. We have assessed the benefits and risks in primary prevention.MethodsWe undertook meta-analyses of serious vascular events (myocardial infarction, stroke, or vascular death) and major bleeds in six primary prevention trials (95,000 individuals at low average risk, 660,000 person-years, 3554 serious vascular events) and 16 secondary prevention trials (17,000 individuals at high average risk, 43,000 person-years, 3306 serious vascular events) that compared long-term aspirin versus control. We report intention-to-treat analyses of first events during the scheduled treatment period.FindingsIn the primary prevention trials, aspirin allocation yielded a 12% proportional reduction in serious vascular events (0.51% aspirin vs 0.57% control per year, p=0.0001), due mainly to a reduction of about a fifth in non-fatal myocardial infarction (0.18%vs 0.23% per year, p<0.0001). The net effect on stroke was not significant (0.20%vs 0.21% per year, p=0.4: haemorrhagic stroke 0.04%vs 0.03%, p=0.05; other stroke 0.16%vs 0.18% per year, p=0.08). Vascular mortality did not differ significantly (0.19%vs 0.19% per year, p=0.7). Aspirin allocation increased major gastrointestinal and extracranial bleeds (0.10%vs 0.07% per year, p<0.0001), and the main risk factors for coronary disease were also risk factors for bleeding. In the secondary prevention trials, aspirin allocation yielded a greater absolute reduction in serious vascular events (6.7%vs 8.2% per year, p<0.0001), with a non-significant increase in haemorrhagic stroke but reductions of about a fifth in total stroke (2.08%vs 2.54% per year, p=0.002) and in coronary events (4.3%vs 5.3% per year, p<0.0001). In both primary and secondary prevention trials, the proportional reductions in the aggregate of all serious vascular events seemed similar for men and women.InterpretationIn primary prevention without previous disease, aspirin is of uncertain net value as the reduction in occlusive events needs to be weighed against any increase in major bleeds. Further trials are in progress.FundingUK Medical Research Council, British Heart Foundation, Cancer Research UK, and the European Community Biomed Programme.

Project description:IntroductionInhaled corticosteroids (ICS) can improve clinical outcomes in patients with chronic obstructive pulmonary disease (COPD) and eosinophilic airway inflammation, but they also increase the risk of side effects like pneumonia. Blood eosinophils guide ICS use, though evidence is limited. The predictors of treatment REsponse to ICS in COPD: a randomised controlled trials (RCTs) individual participant Data re-Evaluation (ICS-RECODE) research programme will leverage data from large RCTs to identify patients who benefit most from ICS with minimal risk. This protocol details an individual participant data (IPD) meta-analysis, assessing ICS safety, efficacy and treatment×covariate interactions to identify predictors of treatment response.Methods and analysisThis meta-analysis will adhere to Cochrane, IPD handbook and Grading of Recommendations Assessment, Development and Evaluation (GRADE) guidance. We will conduct a two-stage IPD meta-analysis of RCTs evaluating the addition of ICS to maintenance COPD treatments. Only RCTs with at least 500 participants across all eligible arms will be included, to allow for treatment×covariate interaction evaluation. Primary outcomes are severe and moderate or severe exacerbation rates; secondary outcomes assess both safety and efficacy. Data from each RCT will be reanalysed using rigorous, consistent statistical methods. Treatment×covariate interactions will be assessed at the RCT level. Trial treatment effects and the coefficients of treatment×covariate interaction analyses will be pooled using random effects model meta-analysis. Risk of bias will be appraised using RoB-2 informed by IPD, and certainty of evidence will be assessed with GRADE and the Instrument to assess the Credibility of Effect Modification Analyses.The ICS-RECODE IPD meta-analysis will make use of the best available data to define evidence-based, precision medicine approaches for ICS use in COPD.Ethics and disseminationThe Health Research Authority approved the ICS-RECODE study, exempting it from ethics review (HRA UK, Reference: 24/HRA/0460). Our findings will be published in peer-reviewed journals and shared with the scientific and broader stakeholder communities.Prospero registration numberCRD42024508286.

Project description:BackgroundIncreasingly in network meta-analysis (NMA), there is a need to incorporate non-randomised evidence to estimate relative treatment effects, and in particular in cases with limited randomised evidence, sometimes resulting in disconnected networks of treatments. When combining different sources of data, complex NMA methods are required to address issues associated with participant selection bias, incorporating single-arm trials (SATs), and synthesising a mixture of individual participant data (IPD) and aggregate data (AD). We develop NMA methods which synthesise data from SATs and randomised controlled trials (RCTs), using a mixture of IPD and AD, for a dichotomous outcome.MethodsWe propose methods under both contrast-based (CB) and arm-based (AB) parametrisations, and extend the methods to allow for both within- and across-trial adjustments for covariate effects. To illustrate the methods, we use an applied example investigating the effectiveness of biologic disease-modifying anti-rheumatic drugs for rheumatoid arthritis (RA). We applied the methods to a dataset obtained from a literature review consisting of 14 RCTs and an artificial dataset consisting of IPD from two SATs and AD from 12 RCTs, where the artificial dataset was created by removing the control arms from the only two trials assessing tocilizumab in the original dataset.ResultsWithout adjustment for covariates, the CB method with independent baseline response parameters (CBunadjInd) underestimated the effectiveness of tocilizumab when applied to the artificial dataset compared to the original dataset, albeit with significant overlap in posterior distributions for treatment effect parameters. The CB method with exchangeable baseline response parameters produced effectiveness estimates in agreement with CBunadjInd, when the predicted baseline response estimates were similar to the observed baseline response. After adjustment for RA duration, there was a reduction in across-trial heterogeneity in baseline response but little change in treatment effect estimates.ConclusionsOur findings suggest incorporating SATs in NMA may be useful in some situations where a treatment is disconnected from a network of comparator treatments, due to a lack of comparative evidence, to estimate relative treatment effects. The reliability of effect estimates based on data from SATs may depend on adjustment for covariate effects, although further research is required to understand this in more detail.

Project description:IntroductionWith mental ill health listed as a top cause of global disease burden, there is an urgent need to prioritise mental health promotion programmes. Mindfulness-based programmes (MBPs) are being widely implemented to reduce stress in non-clinical settings. In a recent aggregate-level meta-analysis we found that, compared with no intervention, these MBPs reduce average psychological distress. However, heterogeneity between studies impedes generalisation of effects across every setting. Study-level effect modifiers were insufficient to reduce heterogeneity; studying individual-level effect modifiers is warranted. This requires individual participant data (IPD) and larger samples than those found in existing individual trials.Methods and analysisWe propose an IPD meta-analysis. Our primary aim is to see if, and how, baseline psychological distress, gender, age, education and dispositional mindfulness moderate the effect of MBPs on distress. We will search 13 databases for good-quality randomised controlled trials comparing in-person, expert-defined MBPs in non-clinical settings with passive controls. Two researchers will independently select, extract and appraise trials using the revised Cochrane risk-of-bias tool. Anonymised IPD of eligible trials will be sought from authors, who will be invited to collaborate.The primary outcome will be psychological distress measured using psychometrically validated questionnaires at 1-6 months after programme completion. Pairwise random-effects two-stage IPD meta-analyses will be conducted. Moderator analyses will follow a 'deft' approach. We will estimate subgroup-specific intervention effects. Secondary outcomes and sensitivity analyses are prespecified. Multiple imputation strategies will be applied to missing data.Ethics and disseminationThe findings will refine our knowledge on the effectiveness of MBPs and help improve the targeting of MBPs in non-clinical settings. They will be shared in accessible formats with a range of stakeholders. Public and professional stakeholders are being involved in the planning, conduct and dissemination of this project.Prospero registration numberCRD42020200117.

Project description:IntroductionTrauma-focused cognitive behavioural therapies are the first-line treatment for posttraumatic stress disorder (PTSD) in children and adolescents. Nevertheless, open questions remain with respect to efficacy: why does this first-line treatment not work for everyone? For whom does it work best? Individual clinical trials often do not provide sufficient statistical power to examine and substantiate moderating factors. To overcome the issue of limited power, an individual participant data meta-analysis of randomised trials evaluating forms of trauma-focused cognitive behavioural therapy in children and adolescents aged 6-18 years will be conducted.Methods and analysisWe will update the National Institute for Health and Care Excellence guideline literature search from 2018 with an electronic search in the databases PsycINFO, MEDLINE, Embase, Cochrane Central Register of Controlled Trials and CINAHL with the terms (trauma* OR stress*) AND (cognitive therap* OR psychotherap*) AND (trial* OR review*). Electronic searches will be supplemented by a comprehensive grey literature search in archives and trial registries. Only randomised trials that used any manualised psychological treatment-that is a trauma-focused cognitive behavioural therapy for children and adolescents-will be included. The primary outcome variable will be child-reported posttraumatic stress symptoms (PTSS) post-treatment. Proxy-reports (teacher, parent and caregiver) will be analysed separately. Secondary outcomes will include follow-up assessments of PTSS, PTSD diagnosis and symptoms of comorbid disorders such as depression, anxiety-related and externalising problems. Random-effects models applying restricted maximum likelihood estimation will be used for all analyses. We will use the Revised Cochrane Risk of Bias tool to measure risk of bias.Ethics and disseminationContributing study authors need to have permission to share anonymised data. Contributing studies will be required to remove patient identifiers before providing their data. Results will be published in a peer-reviewed journal and presented at international conferences.Prospero registration numberCRD42019151954.

Project description:BackgroundStatin therapy is effective for the prevention of atherosclerotic cardiovascular disease and is widely prescribed, but there are persisting concerns that statin therapy might frequently cause muscle pain or weakness. We aimed to address these through an individual participant data meta-analysis of all recorded adverse muscle events in large, long-term, randomised, double-blind trials of statin therapy.MethodsRandomised trials of statin therapy were eligible if they aimed to recruit at least 1000 participants with a scheduled treatment duration of at least 2 years, and involved a double-blind comparison of statin versus placebo or of a more intensive versus a less intensive statin regimen. We analysed individual participant data from 19 double-blind trials of statin versus placebo (n=123 940) and four double-blind trials of a more intensive versus a less intensive statin regimen (n=30 724). Standard inverse-variance-weighted meta-analyses of the effects on muscle outcomes were conducted according to a prespecified protocol.FindingsAmong 19 placebo-controlled trials (mean age 63 years [SD 8], with 34 533 [27·9%] women, 59 610 [48·1%] participants with previous vascular disease, and 22 925 [18·5%] participants with diabetes), during a weighted average median follow-up of 4·3 years, 16 835 (27·1%) allocated statin versus 16 446 (26·6%) allocated placebo reported muscle pain or weakness (rate ratio [RR] 1·03; 95% CI 1·01-1·06). During year 1, statin therapy produced a 7% relative increase in muscle pain or weakness (1·07; 1·04-1·10), corresponding to an absolute excess rate of 11 (6-16) events per 1000 person-years, which indicates that only one in 15 ([1·07-1·00]/1·07) of these muscle-related reports by participants allocated to statin therapy were actually due to the statin. After year 1, there was no significant excess in first reports of muscle pain or weakness (0·99; 0·96-1·02). For all years combined, more intensive statin regimens (ie, 40-80 mg atorvastatin or 20-40 mg rosuvastatin once per day) yielded a higher RR than less intensive or moderate-intensity regimens (1·08 [1·04-1·13] vs 1·03 [1·00-1·05]) compared with placebo, and a small excess was present (1·05 [0·99-1·12]) for more intensive regimens after year 1. There was no clear evidence that the RR differed for different statins, or in different clinical circumstances. Statin therapy yielded a small, clinically insignificant increase in median creatine kinase values of approximately 0·02 times the upper limit of normal.InterpretationStatin therapy caused a small excess of mostly mild muscle pain. Most (>90%) of all reports of muscle symptoms by participants allocated statin therapy were not due to the statin. The small risks of muscle symptoms are much lower than the known cardiovascular benefits. There is a need to review the clinical management of muscle symptoms in patients taking a statin.FundingBritish Heart Foundation, Medical Research Council, Australian National Health and Medical Research Council.

Project description:Objective To assess the effect of the FTO genotype on weight loss after dietary, physical activity, or drug based interventions in randomised controlled trials.Design Systematic review and random effects meta-analysis of individual participant data from randomised controlled trials.Data sources Ovid Medline, Scopus, Embase, and Cochrane from inception to November 2015.Eligibility criteria for study selection Randomised controlled trials in overweight or obese adults reporting reduction in body mass index, body weight, or waist circumference by FTO genotype (rs9939609 or a proxy) after dietary, physical activity, or drug based interventions. Gene by treatment interaction models were fitted to individual participant data from all studies included in this review, using allele dose coding for genetic effects and a common set of covariates. Study level interactions were combined using random effect models. Metaregression and subgroup analysis were used to assess sources of study heterogeneity.Results We identified eight eligible randomised controlled trials for the systematic review and meta-analysis (n=9563). Overall, differential changes in body mass index, body weight, and waist circumference in response to weight loss intervention were not significantly different between FTO genotypes. Sensitivity analyses indicated that differential changes in body mass index, body weight, and waist circumference by FTO genotype did not differ by intervention type, intervention length, ethnicity, sample size, sex, and baseline body mass index and age category.Conclusions We have observed that carriage of the FTO minor allele was not associated with differential change in adiposity after weight loss interventions. These findings show that individuals carrying the minor allele respond equally well to dietary, physical activity, or drug based weight loss interventions and thus genetic predisposition to obesity associated with the FTO minor allele can be at least partly counteracted through such interventions.Systematic review registration PROSPERO CRD42015015969.

Project description:BackgroundMeta-analyses of individual-level data from randomised trials are often required to detect clinically worthwhile effects. The Cholesterol Treatment Trialists' Collaboration, which includes data from numerous large long-term statin trials, is conducting a review of the effects of statin therapy on all adverse events collected in those trials. This article describes the approaches used and challenges faced to systematically capture and categorise the data.MethodsProtocols, statistical analysis plans, case report forms, clinical study reports and datasets were obtained, reviewed and checked. Relevant baseline and follow-up data from each trial was then reorganised into standardised formats based upon the Clinical Data Interchange Standards Consortium Study Data Tabulation Model. Adverse event data were organised and coded (automatically or, where necessary, manually) according to a common medical dictionary based upon the Medical Dictionary for Regulatory Activities.ResultsData from 23 double-blind statin trials and 5 open-label statin trials were provided, either through direct data transfer or through online access platforms. Together, these trials provided 845 datasets containing over 38 million records relating to 30,495 study variables and 181,973 randomised participants. Of the 46 Clinical Data Interchange Standards Consortium Study Data Tabulation Model domains that could potentially have been used to organise the data, the 13 most relevant to the project were identified and utilised, including 6 domains related to post-randomisation adverse events. Nearly 1.2 million adverse events were extracted and mapped to over 45,000 unique adverse event terms. Of these adverse events, 99% were coded to a Medical Dictionary for Regulatory Activities 'lower level term', with the remainder coded to a 'higher level term' or, very rarely, only a 'higher level group term'.ConclusionIn this meta-analysis of adverse event data from the large randomised trials of statins, approaches based on common standards for data organisation and classification have provided a resource capable of allowing reliable and rapid evaluation of any previously unknown benefits or hazards of statin therapy.

Dataset Information

The effects of advanced factor analysis approaches on outcomes in randomised trials for depression: protocol for secondary analysis of individual participant data.

Background

Aims

Method

Conclusions

Publications

The effects of advanced factor analysis approaches on outcomes in randomised trials for depression: protocol for secondary analysis of individual participant data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets