Volume 28, Issue 14
Research Article

Addressing between‐study heterogeneity and inconsistency in mixed treatment comparisons: Application to stroke prevention treatments in individuals with non‐rheumatic atrial fibrillation

Nicola J. Cooper

Corresponding Author

E-mail address: njc21@le.ac.uk

Department of Health Sciences, University of Leicester, Leicester LE1 7RH, U.K.

MRC Training Fellow in Health Services Research.

Centre for Biostatistics and Genetic Epidemiology, Department of Health Sciences, University of Leicester, Adrian Building, Leicester LE1 7RH, U.K.Search for more papers by this author
Alex J. Sutton

Department of Health Sciences, University of Leicester, Leicester LE1 7RH, U.K.

Professor of Medical Statistics.

Search for more papers by this author
Danielle Morris

Section of Epidemiology, Institute of Cancer Research, Cotswold Road, Sutton, Surrey SM2 5NG, U.K.

Search for more papers by this author
A. E. Ades

Academic Unit of Primary Health Care, Department of Community Based Medicine, University of Bristol, Cotham House, Cotham Hill, Bristol BS6 6JL, U.K.

Professor of Public Health Science.

Search for more papers by this author
Nicky J. Welton

Academic Unit of Primary Health Care, Department of Community Based Medicine, University of Bristol, Cotham House, Cotham Hill, Bristol BS6 6JL, U.K.

Senior Research Fellow.

Search for more papers by this author
First published: 27 April 2009
Citations: 150

Abstract

Mixed treatment comparison models extend meta‐analysis methods to enable comparisons to be made between all relevant comparators in the clinical area of interest. In such modelling it is imperative that potential sources of variability are explored to explain both heterogeneity (variation in treatment effects between trials within pairwise contrasts) and inconsistency (variation in treatment effects between pairwise contrasts) to ensure the validity of the analysis.

The objective of this paper is to extend the mixed treatment comparison framework to allow for the incorporation of study‐level covariates in an attempt to explain between‐study heterogeneity and reduce inconsistency. Three possible model specifications assuming different assumptions are described and applied to a 17‐treatment network for stroke prevention treatments in individuals with non‐rheumatic atrial fibrillation.

The paper demonstrates the feasibility of incorporating covariates within a mixed treatment comparison framework and using model fit statistics to choose between alternative model specifications. Although such an approach may adjust for inconsistencies in networks, as for standard meta‐regression, the analysis will suffer from low power if the number of trials is small compared with the number of treatment comparators. Copyright © 2009 John Wiley & Sons, Ltd.

Number of times cited according to CrossRef: 150

  • A comparison of Bayesian and frequentist methods in random‐effects network meta‐analysis of binary data, Research Synthesis Methods, 10.1002/jrsm.1397, 11, 3, (363-378), (2020).
  • Heterogeneity and Subgroup Analysis in Network Meta-Analysis, Design and Analysis of Subgroups with Biopharmaceutical Applications, 10.1007/978-3-030-40105-4_18, (369-385), (2020).
  • Charting the landscape of graphical displays for meta-analysis and systematic reviews: a comprehensive review, taxonomy, and feature analysis, BMC Medical Research Methodology, 10.1186/s12874-020-0911-9, 20, 1, (2020).
  • Systematic review and sequential network meta‐analysis on the efficacy of periodontal regenerative therapies, Journal of Clinical Periodontology, 10.1111/jcpe.13338, 47, 9, (1108-1120), (2020).
  • Effectiveness and adverse events of topical and allergen immunotherapy for atopic dermatitis: a systematic review and network meta-analysis protocol, Systematic Reviews, 10.1186/s13643-020-01472-w, 9, 1, (2020).
  • The impact of clinical heterogeneity on conducting network meta-analyses in transthyretin amyloidosis with polyneuropathy, Current Medical Research and Opinion, 10.1080/03007995.2020.1725742, (1-1), (2020).
  • Dysfunctional posttraumatic cognitions, posttraumatic stress and depression in children and adolescents exposed to trauma: a network analysis, Journal of Child Psychology and Psychiatry, 10.1111/jcpp.13101, 61, 1, (77-87), (2019).
  • Fluorescence fingerprints of oral bacteria, Journal of Biophotonics, 10.1002/jbio.201900190, 13, 1, (2019).
  • Applying an improved failure mode effect analysis method to evaluate the safety of a three‐in‐one machine tool, Human Factors and Ergonomics in Manufacturing & Service Industries, 10.1002/hfm.20823, 30, 1, (71-82), (2019).
  • Identification and characterization of latent classes based on drug use among men who have sex with men at risk of sexually transmitted infections in Amsterdam, the Netherlands, Addiction, 10.1111/add.14774, 115, 1, (121-133), (2019).
  • Fasting C‐peptide, a biomarker for hypoglycaemia risk in insulin‐naïve people with type 2 diabetes initiating basal insulin glargine 100 U/mL, Diabetes, Obesity and Metabolism, 10.1111/dom.13897, 22, 3, (315-323), (2019).
  • Network Meta-analysis, Health Services Evaluation, 10.1007/978-1-4939-8715-3_36, (577-615), (2019).
  • MetaInsight: An interactive web‐based tool for analyzing, interrogating, and visualizing network meta‐analyses using R‐shiny and netmeta, Research Synthesis Methods, 10.1002/jrsm.1373, 10, 4, (569-581), (2019).
  • The Use of Metaanalysis in Pharmacoepidemiology, Pharmacoepidemiology, 10.1002/9781119413431, (897-947), (2019).
  • Identifying inconsistency in network meta‐analysis: Is the net heat plot a reliable method?, Statistics in Medicine, 10.1002/sim.8383, 38, 29, (5547-5564), (2019).
  • Predicting changes in mean length with an age‐structured stock assessment model, Natural Resource Modeling, 10.1111/nrm.12218, 32, 4, (2019).
  • Do new and relocating firms have different preferences for accessibility?, Papers in Regional Science, 10.1111/pirs.12458, 98, 6, (2315-2341), (2019).
  • Artificial neural network‐based modeling of snow properties using field data and hyperspectral imagery, Natural Resource Modeling, 10.1111/nrm.12229, 32, 4, (2019).
  • Determinants of international tourist choices in Italian provinces: A joint demand–supply approach with spatial effects, Papers in Regional Science, 10.1111/pirs.12467, 98, 6, (2251-2273), (2019).
  • Considerations in testing treatment effects on transient event driven health status changes measured by patient reported outcomes, Statistics in Medicine, 10.1002/sim.8376, 38, 29, (5497-5511), (2019).
  • Nonparametric estimation of the cumulative incidence function under outcome misclassification using external validation data, Statistics in Medicine, 10.1002/sim.8380, 38, 29, (5512-5527), (2019).
  • Analyzing discrete competing risks data with partially overlapping or independent data sources and nonstandard sampling schemes, with application to cancer registries, Statistics in Medicine, 10.1002/sim.8381, 38, 29, (5528-5546), (2019).
  • Two‐stage enrichment clinical trial design with adjustment for misclassification in predictive biomarkers, Statistics in Medicine, 10.1002/sim.8370, 38, 29, (5445-5469), (2019).
  • Multi‐stage enrichment and basket trial designs with population selection, Statistics in Medicine, 10.1002/sim.8371, 38, 29, (5470-5485), (2019).
  • Botulinum Toxins Type A (Bont-A) in the Management of Lower Limb Spasticity in Children: A Systematic Literature Review and Bayesian Network Meta-analysis, Journal of Child Neurology, 10.1177/0883073819830579, (088307381983057), (2019).
  • Efectividad de las intervenciones para revertir el diagnóstico del síndrome metabólico: actualización de un metaanálisis de comparación mixta de tratamientos, Biomédica, 10.7705/biomedica.4684, 39, 4, (647-662), (2019).
  • Network meta-analysis explained, Archives of Disease in Childhood - Fetal and Neonatal Edition, 10.1136/archdischild-2018-315224, 104, 1, (F8-F12), (2018).
  • Assessing the consistency assumptions underlying network meta‐regression using aggregate data, Research Synthesis Methods, 10.1002/jrsm.1327, 10, 2, (207-224), (2018).
  • References, Network Meta‐Analysis for Decision Making, 10.1002/9781118951651, (409-445), (2018).
  • A design‐by‐treatment interaction model for network meta‐analysis and meta‐regression with integrated nested Laplace approximations, Research Synthesis Methods, 10.1002/jrsm.1285, 9, 2, (179-194), (2018).
  • Graphs of study contributions and covariate distributions for network meta‐regression, Research Synthesis Methods, 10.1002/jrsm.1292, 9, 2, (243-260), (2018).
  • A framework for identifying treatment‐covariate interactions in individual participant data network meta‐analysis, Research Synthesis Methods, 10.1002/jrsm.1300, 9, 3, (393-407), (2018).
  • Power and commensurate priors for synthesizing aggregate and individual patient level data in network meta‐analysis, Journal of the Royal Statistical Society: Series C (Applied Statistics), 10.1111/rssc.12275, 67, 4, (1047-1069), (2018).
  • Klinische Studien zu neuen direkten oralen Antikoagulanzien, Phlebologie, 10.12687/phleb2146-3-2013, 42, 03, (139-148), (2018).
  • Thirty Years of Evidence on the Efficacy of Drug Treatments for Chronic Heart Failure With Reduced Ejection Fraction, Circulation: Heart Failure, 10.1161/CIRCHEARTFAILURE.116.003529, 10, 1, (2017).
  • Network Meta-analysis, Methods in Health Services Research, 10.1007/978-1-4939-6704-9_13-1, (1-38), (2017).
  • Diagnostics for generalized linear hierarchical models in network meta‐analysis, Research Synthesis Methods, 10.1002/jrsm.1246, 8, 3, (333-342), (2017).
  • Network meta‐analysis including treatment by covariate interactions: Consistency can vary across covariate values, Research Synthesis Methods, 10.1002/jrsm.1257, 8, 4, (485-495), (2017).
  • Combining randomized and non‐randomized evidence in network meta‐analysis, Statistics in Medicine, 10.1002/sim.7223, 36, 8, (1210-1226), (2017).
  • Three-dimensional evidence network plot system: covariate imbalances and effects in network meta-analysis explored using a new software tool, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2017.03.008, 86, (182-195), (2017).
  • Additional considerations are required when preparing a protocol for a systematic review with multiple interventions, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2016.11.015, 83, (65-74), (2017).
  • Multiple Score Comparison: a network meta-analysis approach to comparison and external validation of prognostic scores, BMC Medical Research Methodology, 10.1186/s12874-017-0433-2, 17, 1, (2017).
  • Common pitfalls and mistakes in the set-up, analysis and interpretation of results in network meta-analysis: what clinicians should look for in a published article, Evidence Based Mental Health, 10.1136/eb-2017-102753, 20, 3, (88-94), (2017).
  • Comparative efficacy and tolerability of pharmacological and somatic interventions in adult patients with treatment-resistant depression: a systematic review and network meta-analysis, Current Medical Research and Opinion, 10.1080/03007995.2016.1277201, 33, 4, (701-711), (2017).
  • Clinical trials with new oral anticoagulants, Hämostaseologie, 10.5482/HAMO-12-11-0021, 33, 01, (62-70), (2017).
  • Effectiveness and Tolerability of Different Recommended Doses of PPIs and H2RAs in GERD: Network Meta-Analysis and GRADE system, Scientific Reports, 10.1038/srep41021, 7, (41021), (2017).
  • Acupuncture for chronic pain and depression in primary care: a programme of research, Programme Grants for Applied Research, 10.3310/pgfar05030, 5, 3, (1-316), (2017).
  • Keeping Children Safe: a multicentre programme of research to increase the evidence base for preventing unintentional injuries in the home in the under-fives, Programme Grants for Applied Research, 10.3310/pgfar05140, 5, 14, (1-834), (2017).
  • Adalimumab, etanercept and ustekinumab for treating plaque psoriasis in children and young people: systematic review and economic evaluation, Health Technology Assessment, 10.3310/hta21640, 21, 64, (1-244), (2017).
  • Treatments for Lupus Nephritis: A Systematic Review and Network Metaanalysis, The Journal of Rheumatology, 10.3899/jrheum.160041, 43, 10, (1801-1815), (2016).
  • GetReal in network meta‐analysis: a review of the methodology, Research Synthesis Methods, 10.1002/jrsm.1195, 7, 3, (236-263), (2016).
  • Epidemiology Characteristics, Methodological Assessment and Reporting of Statistical Analysis of Network Meta-Analyses in the Field of Cancer, Scientific Reports, 10.1038/srep37208, 6, 1, (2016).
  • Methods for network meta-analysis of continuous outcomes using individual patient data: a case study in acupuncture for chronic pain, BMC Medical Research Methodology, 10.1186/s12874-016-0224-1, 16, 1, (2016).
  • Comparative effectiveness of immunosuppressive drugs and corticosteroids for lupus nephritis: a systematic review and network meta-analysis, Systematic Reviews, 10.1186/s13643-016-0328-z, 5, 1, (2016).
  • Risk of serious infections with immunosuppressive drugs and glucocorticoids for lupus nephritis: a systematic review and network meta-analysis, BMC Medicine, 10.1186/s12916-016-0673-8, 14, 1, (2016).
  • Efficacy and safety of antithrombotic regimens after coronary intervention in patients on oral anticoagulation: Traditional and Bayesian meta-analysis of clinical trials, International Journal of Cardiology, 10.1016/j.ijcard.2015.12.005, 205, (89-96), (2016).
  • Network meta-analysis of efficacy and safety of competitive oral anticoagulants in patients undergoing radiofrequency catheter ablation of atrial fibrillation, Journal of Interventional Cardiac Electrophysiology, 10.1007/s10840-016-0126-5, 46, 3, (213-224), (2016).
  • Comparative safety profile of hyaluronic acid products for knee osteoarthritis: a systematic review and network meta-analysis, Osteoarthritis and Cartilage, 10.1016/j.joca.2016.07.010, 24, 12, (2022-2041), (2016).
  • Comparative efficacy of disease-modifying therapies for patients with relapsing remitting multiple sclerosis: Systematic review and network meta-analysis, Multiple Sclerosis and Related Disorders, 10.1016/j.msard.2016.06.001, 9, (23-30), (2016).
  • Tofacitinib Versus Biologic Treatments in Patients With Active Rheumatoid Arthritis Who Have Had an Inadequate Response to Tumor Necrosis Factor Inhibitors: Results From a Network Meta-analysis, Clinical Therapeutics, 10.1016/j.clinthera.2016.11.004, 38, 12, (2628-2641.e5), (2016).
  • Efficacy of two noninvasive weaning strategies in intubated patients with chronic obstructive pulmonary disease: A meta-analysis and indirect treatment comparison, Heart & Lung, 10.1016/j.hrtlng.2015.12.008, 45, 2, (132-139), (2016).
  • UK publicly funded Clinical Trials Units supported a controlled access approach to share individual participant data but highlighted concerns, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2015.07.002, 70, (17-25), (2016).
  • A Bayesian network meta-analysis for binary outcome: how to do it, Statistical Methods in Medical Research, 10.1177/0962280213500185, 25, 5, (1757-1773), (2016).
  • An overview of methods for network meta-analysis using individual participant data: when do benefits arise?, Statistical Methods in Medical Research, 10.1177/0962280216660741, (096228021666074), (2016).
  • A cost-effectiveness modelling study of strategies to reduce risk of infection following primary hip replacement based on a systematic review, Health Technology Assessment, 10.3310/hta20540, 20, 54, (1-144), (2016).
  • Albendazole and Corticosteroids for the Treatment of Solitary Cysticercus Granuloma: A Network Meta-analysis, PLOS Neglected Tropical Diseases, 10.1371/journal.pntd.0004418, 10, 2, (e0004418), (2016).
  • Assumptions of Mixed Treatment Comparisons in Health Technology Assessments - Challenges and Possible Steps for Practical Application, PLOS ONE, 10.1371/journal.pone.0160712, 11, 8, (e0160712), (2016).
  • A Bayesian missing data framework for generalized multiple outcome mixed treatment comparisons, Research Synthesis Methods, 10.1002/jrsm.1153, 7, 1, (6-22), (2015).
  • ‘Arm‐based’ parameterization for network meta‐analysis, Research Synthesis Methods, 10.1002/jrsm.1187, 7, 3, (306-313), (2015).
  • Indirect comparison of the antiviral efficacy of peginterferon alpha 2a plus ribavirin used with or without simeprevir in genotype 4 hepatitis C virus infection, where common comparator study arms are lacking: a special application of the matching adjusted indirect comparison methodology, Current Medical Research and Opinion, 10.1185/03007995.2015.1106934, 32, 1, (147-154), (2015).
  • Optimal drug regimens for primary biliary cirrhosis: a systematic review and network meta-analysis, Oncotarget, 10.18632/oncotarget.4528, 6, 27, (24533-24549), (2015).
  • Incorporation of individual‐patient data in network meta‐analysis for multiple continuous endpoints, with application to diabetes treatment, Statistics in Medicine, 10.1002/sim.6519, 34, 20, (2794-2819), (2015).
  • Network meta‐analysis of longitudinal data using fractional polynomials, Statistics in Medicine, 10.1002/sim.6492, 34, 15, (2294-2311), (2015).
  • A general framework for comparative Bayesian meta-analysis of diagnostic studies, BMC Medical Research Methodology, 10.1186/s12874-015-0061-7, 15, 1, (2015).
  • Critical Appraisal of Network Meta-Analyses Evaluating the Efficacy and Safety of New Oral Anticoagulants in Atrial Fibrillation Stroke Prevention Trials, Value in Health, 10.1016/j.jval.2014.10.012, 18, 2, (234-249), (2015).
  • A primer on network meta-analysis with emphasis on mental health, Evidence Based Mental Health, 10.1136/eb-2015-102088, 18, 2, (40-46), (2015).
  • Comparative effectiveness of exercise and drug interventions on mortality outcomes: metaepidemiological study, British Journal of Sports Medicine, 10.1136/bjsports-2015-f5577rep, 49, 21, (1414-1422), (2015).
  • Accounting for Heterogeneity in Relative Treatment Effects for Use in Cost-Effectiveness Models and Value-of-Information Analyses, Medical Decision Making, 10.1177/0272989X15570113, 35, 5, (608-621), (2015).
  • Network Meta-Analysis of Randomized Controlled Trials, Medicine, 10.1097/MD.0000000000000609, 94, 11, (e609), (2015).
  • Graduated compression stockings for the prevention of deep-vein thrombosis in postoperative surgical patients: a systematic review and economic model with a value of information analysis, Health Technology Assessment, 10.3310/hta19980, 19, 98, (1-220), (2015).
  • The Effect of Glucagon-Like Peptide 1 Receptor Agonists on Weight Loss in Type 2 Diabetes: A Systematic Review and Mixed Treatment Comparison Meta-Analysis, PLOS ONE, 10.1371/journal.pone.0126769, 10, 6, (e0126769), (2015).
  • An Assessment of the Methodological Quality of Published Network Meta-Analyses: A Systematic Review, PLOS ONE, 10.1371/journal.pone.0121715, 10, 4, (e0121715), (2015).
  • Network meta-analysis to evaluate the effectiveness of interventions to prevent falls in children under age 5 years, Injury Prevention, 10.1136/injuryprev-2013-041135, 21, 2, (98-108), (2014).
  • Meta-Analysis in Epidemiology, Handbook of Epidemiology, 10.1007/978-0-387-09834-0, (1377-1411), (2014).
  • A selection model for accounting for publication bias in a full network meta‐analysis, Statistics in Medicine, 10.1002/sim.6321, 33, 30, (5399-5412), (2014).
  • Hierarchical network meta‐analysis models to address sparsity of events and differing treatment classifications with regard to adverse outcomes, Statistics in Medicine, 10.1002/sim.6131, 33, 14, (2449-2466), (2014).
  • Network meta-analysis of (individual patient) time to event data alongside (aggregate) count data, BMC Medical Research Methodology, 10.1186/1471-2288-14-105, 14, 1, (2014).
  • ¿Cómo comparar fármacos biológicos?, Reumatología Clínica, 10.1016/j.reuma.2014.06.001, 10, 6, (353-359), (2014).
  • How to Compare Biologic Drugs, Reumatología Clínica (English Edition), 10.1016/j.reumae.2014.07.001, 10, 6, (353-359), (2014).
  • A process for assessing the feasibility of a network meta-analysis: a case study of everolimus in combination with hormonal therapy versus chemotherapy for advanced breast cancer, BMC Medicine, 10.1186/1741-7015-12-93, 12, 1, (2014).
  • Review of mixed treatment comparisons in published systematic reviews shows marked increase since 2009, Journal of Clinical Epidemiology, 10.1016/j.jclinepi.2013.07.014, 67, 2, (138-143), (2014).
  • Indirect Treatment Comparison/Network Meta-Analysis Study Questionnaire to Assess Relevance and Credibility to Inform Health Care Decision Making: An ISPOR-AMCP-NPC Good Practice Task Force Report, Value in Health, 10.1016/j.jval.2014.01.004, 17, 2, (157-173), (2014).
  • Initial orthodontic alignment effectiveness with self-ligating and conventional appliances: A network meta-analysis in practice, American Journal of Orthodontics and Dentofacial Orthopedics, 10.1016/j.ajodo.2013.12.016, 145, 4, (S152-S163), (2014).
  • The efficacy of duloxetine, non-steroidal anti-inflammatory drugs, and opioids in osteoarthritis: a systematic literature review and meta-analysis, BMC Musculoskeletal Disorders, 10.1186/1471-2474-15-76, 15, 1, (2014).
  • Comparative efficacy, acceptability, and safety of medicinal, cognitive-behavioral therapy, and placebo treatments for acute major depressive disorder in children and adolescents: a multiple-treatments meta-analysis, Current Medical Research and Opinion, 10.1185/03007995.2013.860020, 30, 6, (971-995), (2014).
  • VenUS IV (Venous leg Ulcer Study IV) – compression hosiery compared with compression bandaging in the treatment of venous leg ulcers: a randomised controlled trial, mixed-treatment comparison and decision-analytic model, Health Technology Assessment, 10.3310/hta18570, 18, 57, (1-294), (2014).
  • Mixed treatment comparison of prophylaxis against invasive fungal infections in neutropenic patients receiving therapy for haematological malignancies: a systematic review, Journal of Antimicrobial Chemotherapy, 10.1093/jac/dkt329, 69, 1, (1-11), (2013).
  • Bayesian network meta‐analysis for unordered categorical outcomes with incomplete data, Research Synthesis Methods, 10.1002/jrsm.1103, 5, 2, (162-185), (2013).
  • Assessing key assumptions of network meta‐analysis: a review of methods, Research Synthesis Methods, 10.1002/jrsm.1085, 4, 4, (291-323), (2013).
  • Comparative Tolerability and Harms of Individual Statins, Circulation: Cardiovascular Quality and Outcomes, 10.1161/CIRCOUTCOMES.111.000071, 6, 4, (390-399), (2013).
  • See more

The full text of this article hosted at iucr.org is unavailable due to technical difficulties.