|
1
|
Hopkins WG. Replacing statistical significance and non-significance with better approaches to sampling uncertainty. Front Physiol 2022; 13:962132. [PMID: 36267575 PMCID: PMC9578285 DOI: 10.3389/fphys.2022.962132] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2022] [Accepted: 07/27/2022] [Indexed: 11/28/2022] Open
Abstract
A sample provides only an approximate estimate of the magnitude of an effect, owing to sampling uncertainty. The following methods address the issue of sampling uncertainty when researchers make a claim about effect magnitude: informal assessment of the range of magnitudes represented by the confidence interval; testing of hypotheses of substantial (meaningful) and non-substantial magnitudes; assessment of the probabilities of substantial and trivial (inconsequential) magnitudes with Bayesian methods based on non-informative or informative priors; and testing of the nil or zero hypothesis. Assessment of the confidence interval, testing of substantial and non-substantial hypotheses, and assessment of Bayesian probabilities with a non-informative prior are subject to differing interpretations but are all effectively equivalent and can reasonably define and provide necessary and sufficient evidence for substantial and trivial effects. Informative priors in Bayesian assessments are problematic, because they are hard to quantify and can bias the outcome. Rejection of the nil hypothesis (presented as statistical significance), and failure to reject the nil hypothesis (presented as statistical non-significance), provide neither necessary nor sufficient evidence for substantial and trivial effects. To properly account for sampling uncertainty in effect magnitudes, researchers should therefore replace rather than supplement the nil-hypothesis test with one or more of the other three equivalent methods. Surprisal values, second-generation p values, and the hypothesis comparisons of evidential statistics are three other recent approaches to sampling uncertainty that are not recommended. Important issues beyond sampling uncertainty include representativeness of sampling, accuracy of the statistical model, individual differences, individual responses, and rewards of benefit and costs of harm of clinically or practically important interventions and side effects.
Collapse
|
|
2
|
Gaffney K, Lucero A, Macartney-Coxson D, Clapham J, Whitfield P, Palmer BR, Wakefield S, Faulkner J, Stoner L, Rowlands DS. Effects of whey protein on skeletal muscle microvascular and mitochondrial plasticity following 10 weeks of exercise training in men with type 2 diabetes. Appl Physiol Nutr Metab 2021; 46:915-924. [PMID: 33591858 DOI: 10.1139/apnm-2020-0943] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Skeletal muscle microvascular dysfunction and mitochondrial rarefaction feature in type 2 diabetes mellitus (T2DM) linked to low tissue glucose disposal rate (GDR). Exercise training and milk protein supplementation independently promote microvascular and metabolic plasticity in muscle associated with improved nutrient delivery, but combined effects are unknown. In a randomised-controlled trial, 24 men (55.6 y, SD 5.7) with T2DM ingested whey protein drinks (protein/carbohydrate/fat: 20/10/3 g; WHEY) or placebo (carbohydrate/fat: 30/3 g; CON) before/after 45 mixed-mode intense exercise sessions over 10 weeks, to study effects on insulin-stimulated (hyperinsulinemic clamp) skeletal-muscle microvascular blood flow (mBF) and perfusion (near-infrared spectroscopy), and histological, genetic, and biochemical markers (biopsy) of microvascular and mitochondrial plasticity. WHEY enhanced insulin-stimulated perfusion (WHEY-CON 5.6%; 90% CI -0.1, 11.3), while mBF was not altered (3.5%; -17.5, 24.5); perfusion, but not mBF, associated (regression) with increased GDR. Exercise training increased mitochondrial (range of means: 40%-90%) and lipid density (20%-30%), enzyme activity (20%-70%), capillary:fibre ratio (∼25%), and lowered systolic (∼4%) and diastolic (4%-5%) blood pressure, but without WHEY effects. WHEY dampened PGC1α -2.9% (90% compatibility interval: -5.7, -0.2) and NOS3 -6.4% (-1.4, -0.2) expression, but other messenger RNA (mRNA) were unclear. Skeletal muscle microvascular and mitochondrial exercise adaptations were not accentuated by whey protein ingestion in men with T2DM. ANZCTR Registration Number: ACTRN12614001197628. Novelty: Chronic whey ingestion in T2DM with exercise altered expression of several mitochondrial and angiogenic mRNA. Whey added no additional benefit to muscle microvascular or mitochondrial adaptations to exercise. Insulin-stimulated perfusion increased with whey but was without impact on glucose disposal.
Collapse
Affiliation(s)
- Kim Gaffney
- School of Sport, Exercise and Nutrition, Massey University, Wellington and Auckland, New Zealand
| | - Adam Lucero
- School of Sport, Exercise and Nutrition, Massey University, Wellington and Auckland, New Zealand
| | - Donia Macartney-Coxson
- Human Genomics, Institute of Environmental and Scientific Research Ltd (ESR). Porirua, Wellington, New Zealand
| | - Jane Clapham
- Human Genomics, Institute of Environmental and Scientific Research Ltd (ESR). Porirua, Wellington, New Zealand
| | | | - Barry R Palmer
- School of Health Sciences, Massey University, Wellington, New Zealand
| | - StJohn Wakefield
- Department of Medicine, University of Otago, Wellington, New Zealand
| | - James Faulkner
- School of Sport, Health and Community, University of Winchester, Winchester, England
| | - Lee Stoner
- Department of Exercise and Sport Science, University of North Carolina, Chapel Hill, NC, USA
| | - David S Rowlands
- School of Sport, Exercise and Nutrition, Massey University, Wellington and Auckland, New Zealand
| |
Collapse
|
|
3
|
Pahuta MA, Werier J, Wai EK, van Walraven C, Coyle D. Back to Bayesian: A strategy to enhance prognostication of metastatic spine disease. Int J Clin Pract 2019; 73:e13322. [PMID: 30843333 DOI: 10.1111/ijcp.13322] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2018] [Revised: 01/14/2019] [Accepted: 02/12/2019] [Indexed: 11/30/2022] Open
Abstract
AIMS Clinicians must consider prognosis when offering treatment to patients with spine metastases. Although several prognostic indices have been developed and validated for this purpose, they may not be applicable in the current era of targeted systemic therapies. Even before the introduction of targeted therapies, these prognostic indices should not have been directly used for individual patient decision making without contextualising with other sources of data. By contextualising, we mean that prognostic estimates should not be based on these scores alone and formally incorporate clinically relevant factors not part of prognostic indices. Contextualisation requires the use of Bayesian statistics which may be unfamiliar to many readers. In this paper we show readers how to correctly apply prognostic scores to individual patients using Bayesian statistics. Through Bayesian analysis, we explore the impact of new targeted therapies on prognostic estimates obtained using the Tokuhashi score. METHODS We provide a worked calculation for the probability of a patient surviving up to 6 months using dichotomous prognostication. We then demonstrate how to calculate a patient's expected survival using continuous prognostication. Sensitivity of the posterior distribution to prior assumptions is illustrated through effective sample size adjustment. RESULTS When the predicted prognosis from the Tokuhashi score is contextualised with data on contemporary systemic treatments, patients previously deemed non-surgical candidates may be eligible for surgery. CONCLUSIONS Bayesian prognostication generates intuitive results and allows multiple data points to be synthesised transparently. These techniques can extend the usefulness of existing prognostic scores in the era of targeted systemic therapies.
Collapse
Affiliation(s)
- Markian A Pahuta
- Departments of Orthopaedic, Henry Ford Health System, Detroit, MI
| | - Joel Werier
- Division of Orthopaedic Surgery, The Ottawa Hospital, Ottawa, ON, Canada
| | - Eugene K Wai
- Division of Orthopaedic Surgery, The Ottawa Hospital, Ottawa, ON, Canada
| | - Carl van Walraven
- Ottawa Hospital Research Institute, School of Epidemiology and Public Health, University of Ottawa, Institute for Clinical Evaluative Sciences, Ottawa, ON, Canada
| | - Doug Coyle
- School of Epidemiology & Public Health, University of Ottawa, Ottawa, ON, Canada
| |
Collapse
|
|
4
|
Batterham AM, Hopkins WG. The Problems with “The Problem with ‘Magnitude-Based Inference’”. Med Sci Sports Exerc 2019; 51:599. [DOI: 10.1249/mss.0000000000001823] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/21/2022]
|
|
5
|
Johnson SR, Tomlinson GA, Granton JT, Hawker GA, Feldman BM. Applied Bayesian Methods in the Rheumatic Diseases. Rheum Dis Clin North Am 2018; 44:361-370. [PMID: 29622302 DOI: 10.1016/j.rdc.2018.01.003] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/31/2023]
Abstract
The use of applied Bayesian methods is increasing in rheumatology. Using the Bayes theorem, past evidence is updated with new data. Preexisting data are expressed as a prior probability distribution or prior. New observations are expressed as a likelihood. Through explicit incorporation of preexisting data and new data, this process informs how this new information should change the way we think. In this article, the authors highlight the use of applied Bayesian methods in the study of rheumatic diseases.
Collapse
Affiliation(s)
- Sindhu R Johnson
- Division of Rheumatology, Department of Medicine, Toronto Western Hospital, Mount Sinai Hospital, 155 College Street, Toronto, Ontario M5T 3M6, Canada; Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada; Toronto Western Hospital, 399 Bathurst Street, Toronto, Ontario M5T 2S8, Canada.
| | - George A Tomlinson
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada; Dalla Lana School of Public Health, University of Toronto, 155 College Street, Toronto, Ontario M5T 3M7, Canada; Department of Medicine, Division of Support Systems and Outcomes, Toronto General Hospital Research Institute, University Health Network, Mount Sinai Hospital, Eaton North, 13th Floor, Room 238, 200 Elizabeth Street, Toronto, Ontario M5G 2C4, Canada
| | - John T Granton
- Division of Respirology, Department of Medicine, Toronto General Hospital, University Health Network, MUNK Building, 11-1170, 200 Elizabeth Avenue, Toronto, Ontario M5G 2C4, Canada; Division of Critical Care Medicine, Department of Medicine, Toronto General Hospital, University Health Network, MUNK Building, 11-1170, 200 Elizabeth Avenue, Toronto, Ontario M5G 2C4, Canada
| | - Gillian A Hawker
- Institute of Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada; Division of Rheumatology, Department of Medicine, Women's College Hospital, 76 Grenville Street, 8th Floor East, Room 815, Toronto, Ontario M5S 1B2, Canada
| | - Brian M Feldman
- Institute of Health Policy, Management and Evaluation, Dalla Lana School of Public Health, University of Toronto, Toronto, Ontario, Canada; Division of Rheumatology, Department of Paediatrics, Hospital for Sick Children, 555 University Avenue, Toronto, Ontario M5G 1X8, Canada
| |
Collapse
|
|
6
|
Wellek S. A critical evaluation of the current "p-value controversy". Biom J 2017; 59:854-872. [PMID: 28504870 DOI: 10.1002/bimj.201700001] [Citation(s) in RCA: 48] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/08/2017] [Revised: 03/29/2017] [Accepted: 04/07/2017] [Indexed: 11/06/2022]
Abstract
This article has been triggered by the initiative launched in March 2016 by the Board of Directors of the American Statistical Association (ASA) to counteract the current p-value focus of statistical research practices that allegedly "have contributed to a reproducibility crisis in science." It is pointed out that in the very wide field of statistics applied to medicine, many of the problems raised in the ASA statement are not as severe as in the areas the authors may have primarily in mind, although several of them are well-known experts in biostatistics and epidemiology. This is mainly due to the fact that a large proportion of medical research falls under the realm of a well developed body of regulatory rules banning the most frequently occurring misuses of p-values. Furthermore, it is argued that reducing the statistical hypotheses tests nowadays available to the class of procedures based on p-values calculated under a traditional one-point null hypothesis amounts to ignoring important developments having taken place and going on within the statistical sciences. Although hypotheses testing is still an indispensable part of the statistical methodology required in medical and other areas of empirical research, there is a large repertoire of methods based on different paradigms of inference that provide ample options for supplementing and enhancing the methods of data analysis blamed in the ASA statement for causing a crisis.
Collapse
Affiliation(s)
- Stefan Wellek
- Department of Biostatistics, CIMH Mannheim, Mannheim Medical School of the University of Heidelberg, D-68159, Mannheim, J5, Germany.,Department of Medical Biostatistics, Epidemiology and Informatics, University of Mainz, D-55101, Mainz, Germany
| |
Collapse
|
|
7
|
Kee F, Owen T, Leathem R. Decision Making in a Multidisciplinary Cancer Team: Does Team Discussion Result in Better Quality Decisions? Med Decis Making 2016; 24:602-13. [PMID: 15534341 DOI: 10.1177/0272989x04271047] [Citation(s) in RCA: 38] [Impact Index Per Article: 4.2] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
To establish whether treatment recommendations made by clinicians concur with the best outcomes predicted from their prognostic estimates and whether team discussion improves the quality or outcome of their decision making, the authors studied real-time decision making by a lung cancer team. Clinicians completed pre- and postdiscussion questionnaires for 50 newly diagnosed patients. For each patient/doctor pairing, a decision model determined the expected patient outcomes from the clinician’s prognostic estimates. The difference between the expected utility of the recommended treatment and the maximum utility derived from the clinician’s predictions of the outcomes (the net utility loss) following all potential treatment modalities was calculated as an indicator of quality of the decision. The proportion of treatment decisions changed by the multidisciplinary team discussion was also calculated. Insofar as the change in net utility loss brought about by multidisciplinary team discussion was not significantly different from zero, team discussion did not improve the quality of decision making overall. However, given the modest power of the study, these findings must be interpreted with caution. In only 23 of 87 instances (26%) in which an individual specialist’s initial treatment preference differed from the final group judgment did the specialist finally concur with the group treatment choice after discussion. This study does not support the theory that team discussion improves decision making by closing a knowledge gap.
Collapse
Affiliation(s)
- Frank Kee
- Department of Epidemiology and Public Health, Queen's University Belfast, Belfast Northern Ireland.
| | | | | |
Collapse
|
|
8
|
Hopkins WG, Batterham AM. Error Rates, Decisive Outcomes and Publication Bias with Several Inferential Methods. Sports Med 2016; 46:1563-73. [DOI: 10.1007/s40279-016-0517-x] [Citation(s) in RCA: 59] [Impact Index Per Article: 6.6] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/22/2022]
|
|
9
|
Wheatley K, Wilson JS, Gaunt P, Marsden JR. Surgical excision margins in primary cutaneous melanoma: A meta-analysis and Bayesian probability evaluation. Cancer Treat Rev 2016; 42:73-81. [PMID: 26563920 DOI: 10.1016/j.ctrv.2015.10.013] [Citation(s) in RCA: 50] [Impact Index Per Article: 5.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2015] [Revised: 10/27/2015] [Accepted: 10/29/2015] [Indexed: 11/26/2022]
Abstract
BACKGROUND Surgery is the only curative treatment for primary cutaneous melanoma, therefore it is important to determine excision margins that minimise risk of local recurrence, distant recurrence and death. METHODS MEDLINE, EMBASE and Cochrane CENTRAL were searched from 2009 to 2015. Inclusion criteria were: population/setting - patients with primary melanoma; comparison - narrow versus wide margins; outcomes - overall survival, melanoma-specific survival, recurrence-free survival, and loco-regional recurrence; design - randomized controlled trials (RCTs). Results were pooled using meta-analysis and data explored using likelihood Bayesian probability plots. RESULTS Six RCTs with 4233 patients were included. Narrow margins were defined as 1 or 2 cm of clinically normal skin around the melanoma; wide margins as 3, 4 or 5 cm. Hazard ratios (HR) were as follows (HR>1 indicates wide margin better): overall survival 1.09 (95% CI 0.98-1.22; p=0.1); melanoma-specific survival 1.17 (CI 1.03-1.34; p=0.02); recurrence-free survival 1.08 (CI 0.97-1.20; p=0.2); loco-regional recurrence 1.10 (CI 0.96-1.26; p=0.2), with no evidence of heterogeneity between trials for any end point or within subgroup analyses. There was an 94% probability that overall survival was worse with a narrow margin and a 43% probability that it was more than 10% worse in proportional terms (i.e. HR>1.1). Probabilities that narrow margins were worse were 99%, 92% and 92% for melanoma-specific survival, recurrence-free survival and loco-regional recurrence respectively. CONCLUSIONS Contrary to recommendations in several national guidelines that narrow margins are safe, this systematic review and meta-analysis provides evidence that a narrow margin may lead to a worse outcome than a wide margin.
Collapse
Affiliation(s)
- Keith Wheatley
- Cancer Research UK Clinical Trials Unit, Institute of Cancer & Genomic Sciences, College of Medical and Dental Sciences, University of Birmingham, Birmingham B15 2TT, United Kingdom
| | - Jayne S Wilson
- Cancer Research UK Clinical Trials Unit, Institute of Cancer & Genomic Sciences, College of Medical and Dental Sciences, University of Birmingham, Birmingham B15 2TT, United Kingdom
| | - Piers Gaunt
- Cancer Research UK Clinical Trials Unit, Institute of Cancer & Genomic Sciences, College of Medical and Dental Sciences, University of Birmingham, Birmingham B15 2TT, United Kingdom
| | - Jerry R Marsden
- Skin Oncology Service, Queen Elizabeth Hospital Birmingham, Mindelsohn Way, Edgbaston, Birmingham B15 2WB, United Kingdom
| |
Collapse
|
|
10
|
Howley PP, Hancock SJ, Gibberd RW, Chuang S, Tuyl FA. Bayesian methods in reporting and managing Australian clinical indicators. World J Clin Cases 2015; 3:625-634. [PMID: 26244154 PMCID: PMC4517337 DOI: 10.12998/wjcc.v3.i7.625] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/26/2014] [Revised: 01/14/2015] [Accepted: 05/18/2015] [Indexed: 02/05/2023] Open
Abstract
Sustained clinical improvement is unlikely without appropriate measuring and reporting techniques. Clinical indicators are tools to help assess whether a standard of care is being met. They are used to evaluate the potential to improve the care provided by healthcare organisations (HCOs). The analysis and reporting of these indicators for the Australian Council on Healthcare Standards have used a methodology which estimates, for each of the 338 clinical indicators, the gains in the system that would result from shifting the mean proportion to the 20th centile. The results are used to provide a relative measure to help prioritise quality improvement activity within clinical areas, rather than simply focus on “poorer performing” HCOs. The method draws attention to clinical areas exhibiting larger between-HCO variation and affecting larger numbers of patients. HCOs report data in six-month periods, resulting in estimated clinical indicator proportions which may be affected by small samples and sampling variation. Failing to address such issues would result in HCOs exhibiting extremely small and large estimated proportions and inflated estimates of the potential gains in the system. This paper describes the 20th centile method of calculating potential gains for the healthcare system by using Bayesian hierarchical models and shrinkage estimators to correct for the effects of sampling variation, and provides an example case in Emergency Medicine as well as example expert commentary from colleges based upon the reports. The application of these Bayesian methods enables all collated data to be used, irrespective of an HCO’s size, and facilitates more realistic estimates of potential system gains.
Collapse
|
|
11
|
|
|
12
|
|
|
13
|
Wellek S, Ziegler A. Cochran-Armitage test versus logistic regression in the analysis of genetic association studies. Hum Hered 2011; 73:14-7. [PMID: 22212245 DOI: 10.1159/000334085] [Citation(s) in RCA: 12] [Impact Index Per Article: 0.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/06/2011] [Accepted: 09/24/2011] [Indexed: 11/19/2022] Open
Abstract
OBJECTIVE The Cochran-Armitage trend test based on the linear regression model has become a standard procedure for association testing in case-control studies. In contrast, the logistic regression model is generally used for estimating effect sizes. The aim of this paper is to propose an approach that allows for association testing and parameter estimation by means of the same statistic. METHODS/RESULTS The trend test is recommendable as a test of no association between genotype and risk of disease. It is a two-sample test for differences between cases and controls with respect to the average number of risk alleles occurring in the genotype of an individual. We argue that this difference is not of primary interest in genetic association studies. It should be replaced with the disease odds ratio, which can be assessed under both cohort sampling and case-control sampling. CONCLUSION The Cochran-Armitage trend test should be replaced by the Wald statistic from a logistic regression model for hypothesis testing and estimation in genetic association studies.
Collapse
Affiliation(s)
- Stefan Wellek
- Department of Biostatistics, Central Institute of Mental Health Mannheim, University of Heidelberg, Mannheim, Germany
| | | |
Collapse
|
|
14
|
Corrao S, Calvo L, Amico S, Scaglione R, Licata G. Evidence-Based Practice Needs Stronger Prognostic Scores for the Prediction of Recurrent Stroke. Stroke 2010; 41:e561. [DOI: 10.1161/strokeaha.110.588863] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Affiliation(s)
- Salvatore Corrao
- Dipartimento Biomedico di Medicina Interna e Specialistica, University of Palermo, Palermo, Italy
| | - Luigi Calvo
- Dipartimento Biomedico di Medicina Interna e Specialistica, University of Palermo, Palermo, Italy
| | - Salvatore Amico
- Dipartimento Biomedico di Medicina Interna e Specialistica, University of Palermo, Palermo, Italy
| | - Rosario Scaglione
- Dipartimento Biomedico di Medicina Interna e Specialistica, University of Palermo, Palermo, Italy
| | - Giuseppe Licata
- Dipartimento Biomedico di Medicina Interna e Specialistica, University of Palermo, Palermo, Italy
| |
Collapse
|
|
15
|
The long-term effects of breastfeeding on asthma and atopic disease. ADVANCES IN EXPERIMENTAL MEDICINE AND BIOLOGY 2009; 639:237-51. [PMID: 19227546 DOI: 10.1007/978-1-4020-8749-3_17] [Citation(s) in RCA: 16] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
In this review, the primary objective is to assess the evidence of whether breastfeeding protects against asthma and atopic disease for the long-term (long-term is defined here as >5 years of age). Two main types of observational epidemiological studies have been used to test this hypothesis. These are cohort studies of random samples of children and cohort studies of children with a family history of asthma or atopy. In each study type, exposure and outcome data are collected either prospectively or retrospectively. The 12 criteria for assessing the adequate measurement of exposure, outcome and statistics of cohort studies in this context are given in Table 17-1.
Collapse
|
|
16
|
JOHNSON SINDHUR, FELDMAN BRIANM, POPE JANETE, TOMLINSON GEORGEA. Shifting Our Thinking About Uncommon Disease Trials: The Case of Methotrexate in Scleroderma. J Rheumatol 2009; 36:323-9. [DOI: 10.3899/jrheum.071169] [Citation(s) in RCA: 59] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022]
Abstract
Objective.Randomized trials for uncommon diseases suffer from methodological challenges: difficulty in recruiting sufficient numbers of patients and low power to detect important treatment effects. Using traditional (frequentist) analysis, p values > 0.05 mean investigators are unable to reject the null hypothesis (of no treatment effect). The medical community often labels trials with p values > 0.05 as “negative.” Our study demonstrates how Bayesian analysis conveys more relevant information to clinicians — using the example of methotrexate (MTX) in systemic sclerosis (SSc).Methods.Data from 71 patients with diffuse SSc (n = 35 MTX, n = 36 placebo) in the trial were reanalyzed using Bayesian models. We examined 3 primary outcomes: modified Rodnan skin score (MRSS), University of California Los Angeles (UCLA) skin score, and physician global assessment of overall disease activity. Using noninformative prior probability distributions, the probability of beneficial treatment effects for each outcome and the probability of simultaneous benefit in outcomes were computed.Results.The probability that treatment with MTX results in better mean outcomes than placebo was 94% for MRSS, 96% for UCLA skin score, and 88% for physician global assessment. There was 96% probability that at least 2 of 3 primary outcomes were better on treatment.Conclusion.Bayesian analysis of uncommon disease trials allows for more flexible and clinically relevant interpretations of the data. From the trial data, clinicians can infer that MTX has a high probability of beneficial effects on skin score and global assessment.
Collapse
|
|
17
|
Wijeysundera DN, Austin PC, Hux JE, Beattie WS, Laupacis A. Bayesian statistical inference enhances the interpretation of contemporary randomized controlled trials. J Clin Epidemiol 2008; 62:13-21.e5. [PMID: 18947971 DOI: 10.1016/j.jclinepi.2008.07.006] [Citation(s) in RCA: 123] [Impact Index Per Article: 7.2] [Reference Citation Analysis] [Abstract] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/02/2007] [Revised: 07/18/2008] [Accepted: 07/26/2008] [Indexed: 10/21/2022]
Abstract
OBJECTIVE Randomized trials generally use "frequentist" statistics based on P-values and 95% confidence intervals. Frequentist methods have limitations that might be overcome, in part, by Bayesian inference. To illustrate these advantages, we re-analyzed randomized trials published in four general medical journals during 2004. STUDY DESIGN AND SETTING We used Medline to identify randomized superiority trials with two parallel arms, individual-level randomization and dichotomous or time-to-event primary outcomes. Studies with P<0.05 in favor of the intervention were deemed "positive"; otherwise, they were "negative." We used several prior distributions and exact conjugate analyses to calculate Bayesian posterior probabilities for clinically relevant effects. RESULTS Of 88 included studies, 39 were positive using a frequentist analysis. Although the Bayesian posterior probabilities of any benefit (relative risk or hazard ratio<1) were high in positive studies, these probabilities were lower and variable for larger benefits. The positive studies had only moderate probabilities for exceeding the effects that were assumed for calculating the sample size. By comparison, there were moderate probabilities of any benefit in negative studies. CONCLUSION Bayesian and frequentist analyses complement each other when interpreting the results of randomized trials. Future reports of randomized trials should include both.
Collapse
Affiliation(s)
- Duminda N Wijeysundera
- Department of Health Policy Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.
| | | | | | | | | |
Collapse
|
|
18
|
Abstract
This review examines the state of Bayesian thinking as Statistics in Medicine was launched in 1982, reflecting particularly on its applicability and uses in medical research. It then looks at each subsequent five-year epoch, with a focus on papers appearing in Statistics in Medicine, putting these in the context of major developments in Bayesian thinking and computation with reference to important books, landmark meetings and seminal papers. It charts the growth of Bayesian statistics as it is applied to medicine and makes predictions for the future. From sparse beginnings, where Bayesian statistics was barely mentioned, Bayesian statistics has now permeated all the major areas of medical statistics, including clinical trials, epidemiology, meta-analyses and evidence synthesis, spatial modelling, longitudinal modelling, survival modelling, molecular genetics and decision-making in respect of new technologies.
Collapse
Affiliation(s)
- Deborah Ashby
- Wolfson Institute of Preventive Medicine, Barts and The London, Queen Mary's School of Medicine & Dentistry, University of London, Charterhouse Square, London EC1M 6BQ, UK.
| |
Collapse
|
|
19
|
Green MJ, Burton PR, Green LE, Schukken YH, Bradley AJ, Peeler EJ, Medley GF. The use of Markov chain Monte Carlo for analysis of correlated binary data: patterns of somatic cells in milk and the risk of clinical mastitis in dairy cows. Prev Vet Med 2004; 64:157-74. [PMID: 15325770 DOI: 10.1016/j.prevetmed.2004.05.006] [Citation(s) in RCA: 44] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/08/2003] [Revised: 03/30/2004] [Accepted: 05/06/2004] [Indexed: 10/26/2022]
Abstract
Two analytical approaches were used to investigate the relationship between somatic cell concentrations in monthly quarter milk samples and subsequent, naturally occurring clinical mastitis in three dairy herds. Firstly, cows with clinical mastitis were selected and a conventional matched analysis was used to compare affected and unaffected quarters of the same cow. The second analysis included all cows, and in order to overcome potential bias associated with the correlation structure, a hierarchical Bayesian generalised linear mixed model was specified. A Markov chain Monte Carlo (MCMC) approach, that is Gibbs sampling, was used to estimate parameters. The results of both the matched analysis and the hierarchical modelling suggested that quarters with a somatic cell count (SCC) in the range 41,000-100,000 cells/ml had a lower risk of clinical mastitis during the next month than quarters <41,000 cell/ml. Quarters with an SCC >200,000 cells/ml were at the greatest risk of clinical mastitis in the next month. There was a reduced risk of clinical mastitis between 1 and 2 months later in quarters with an SCC of 81,000-150,000 cells/ml compared with quarters below this level. The hierarchical modelling analysis identified a further reduced risk of clinical mastitis between 2 and 3 months later in quarters with an SCC 61,000-150,000 cells/ml, compared to other quarters. We conclude that low concentrations of somatic cells in milk are associated with increased risk of clinical mastitis, and that high concentrations are indicative of pre-existing immunological mobilisation against infection. The variation in risk between quarters of affected cows suggests that local quarter immunological events, rather than solely whole cow factors, have an important influence on the risk of clinical mastitis. MCMC proved a useful tool for estimating parameters in a hierarchical Bernoulli model. Model construction and an approach to assessing goodness of model fit are described.
Collapse
Affiliation(s)
- M J Green
- Ecology and Epidemiology Group, Department of Biological Sciences, University of Warwick, Coventry CV4 7AL, UK.
| | | | | | | | | | | | | |
Collapse
|
|
20
|
Kurinczuk JJ, Hansen M, Bower C. The risk of birth defects in children born after assisted reproductive technologies. Curr Opin Obstet Gynecol 2004; 16:201-9. [PMID: 15129049 DOI: 10.1097/00001703-200406000-00002] [Citation(s) in RCA: 33] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022]
Abstract
PURPOSE OF REVIEW This review addresses the question of whether there is evidence of an increased risk of birth defects in children born following assisted reproductive technologies compared with spontaneously conceived children. RECENT FINDINGS Three recent studies added relatively little new information given their modest size (56-472 assisted reproductive technology children). We therefore considered all published papers that compared birth defects in children born following assisted reproductive technologies with those in children born following spontaneous conception. Overall, only six of the 26 relevant papers concluded there was an increased risk of birth defects following assisted reproductive technologies. The interpretation of many studies was based on statistical significance testing alone. When results showed a greater proportion of defects in the assisted reproductive technology group compared with the spontaneous group, but the results were not statistically significant, this was often interpreted as showing no increase in risk, rather than an increase in risk that may have been due to chance. The vast majority of individual studies were too small to have sufficient power to detect, as statistically significant, clinically relevant results. We found that although only eight (30%) of the studies had statistically significant results, 24 (89%) had an odds ratio estimate comparing assisted reproductive technology with spontaneously conceived children of over 1.0; 19 (70%) had an estimate of 1.20 or greater; and 14 (52%) had an estimate of 1.5 or greater. SUMMARY Current evidence suggests there is an elevated risk of birth defects in children born following assisted reproductive technologies. Whilst others may disagree with our interpretation, one certainly cannot exclude this possibility on the basis of the current evidence.
Collapse
|
|
21
|
|
|
22
|
Oddy WH, Peat JK. Breastfeeding, asthma, and atopic disease: an epidemiological review of the literature. J Hum Lact 2003; 19:250-61; quiz 262-6. [PMID: 12931775 DOI: 10.1177/0890334403255516] [Citation(s) in RCA: 32] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/26/2022]
Abstract
Two main types of observational epidemiological studies have been used to question whether breastfeeding protects children from developing atopic disease and asthma. These are cohort studies of random samples of children and cohort studies of children with a family history of asthma or atopy. In each study type, exposure and outcome data are collected either prospectively or retrospectively. In this review, the primary objective was to assess the evidence of whether breastfeeding protects against asthma and atopic disease. As an outcome of this review, an analytical perspective with clinical implications is given.
Collapse
Affiliation(s)
- Wendy H Oddy
- Telethon Institute for Child Health Research and the Department of Nutrition, Dietetics, and Food Science, Curtin University of Technology, Perth, Western Australia, Australia
| | | |
Collapse
|
|
23
|
Abstract
OBJECTIVES To test the hypothesis that leatherwork is associated with male infertility mediated through the development of oligozoospermia. The basis of any association was postulated, at the outset, to be with exposure to the solvents used in leatherwork. METHODS All new referrals with infertility presenting in Leicestershire hospital clinics between November 1988 and September 1992 and Kettering District General Hospital from August 1990 were eligible to participate; 88.5% agreed to be interviewed. Exposure to leatherwork and work with solvents was defined by job title. Comparisons were made with fertile controls and in an analysis within men from infertile couples with oligozoospermia as the primary outcome. Effects on sperm motility and deformity were investigated secondarily. Analyses used logistic regression for binary outcomes and multilevel modelling for continuous outcomes. RESULTS 1906 men were interviewed. Compared with the fertile controls the men from infertile couples were 1.10 times (95% confidence interval (95% CI) 0.46 to 2.63; p=0.99) more likely to be leatherworkers and 1.73 times (95% CI 1.26 to 2.38; p<0.001) more likely to work with solvents. Compared with other men, leatherworkers were 1.20 times (95% CI 0.43 to 3.33; p=0.73) more likely to present with oligozoospermia and 1.65 times (95% CI 0.37 to 7.30; p=0.51) more likely to present with teratozoospermia. Being a leatherworker was associated with only a 6% reduction in sperm concentration; motility and deformity were similarly unaffected by this exposure. Work with solvents did not statistically, nor clinically, increase the risk of oligozoospermia, teratozoospermia, or asthenozoospermia. CONCLUSIONS There was little evidence to support the hypothesis that leatherwork is associated with an increased risk of presenting with infertility or oligozoospermia. There was limited evidence that leatherwork is a risk factor for teratozoospermia. Workers with solvents were at an increased risk of presenting with infertility, although this was not mediated through effects on standard measures of semen quality; this finding merits further investigation.
Collapse
Affiliation(s)
- J J Kurinczuk
- Department of Epidemiology and Public Health, University of Leicester, 22-8 Princess Road West, Leicester LE1 6TP, UK.
| | | |
Collapse
|
|
24
|
Burton PR, Palmer LJ, Jacobs K, Keen KJ, Olson JM, Elston RC. Ascertainment adjustment: where does it take us? Am J Hum Genet 2000; 67:1505-14. [PMID: 11078478 PMCID: PMC1287927 DOI: 10.1086/316899] [Citation(s) in RCA: 41] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2000] [Accepted: 10/02/2000] [Indexed: 11/03/2022] Open
Abstract
It is commonly assumed that the parameter estimates of a statistical genetics model that has been adjusted for ascertainment will estimate parameters in the general population from which the ascertained subpopulation was originally drawn. We show that this is true only in certain restricted circumstances. More generally, ascertainment-adjusted parameter estimates reflect parameters in the ascertained subpopulation. In many situations, this shift in perspective is immaterial: the parameters of interest are the same in the ascertained sample and in the population from which it was drawn, and it is therefore irrelevant to which population inferences are presumed to apply. In other circumstances, however, this is not so. This has important implications, particularly for studies investigating the etiology of complex diseases.
Collapse
Affiliation(s)
- P R Burton
- Genetic Epidemiology Unit, Department of Epidemiology and Public Health, University of Leicester, United Kingdom.
| | | | | | | | | | | |
Collapse
|
|
25
|
Gurrin LC, Kurinczuk JJ, Burton PR. Bayesian statistics in medical research: an intuitive alternative to conventional data analysis. J Eval Clin Pract 2000; 6:193-204. [PMID: 10970013 DOI: 10.1046/j.1365-2753.2000.00216.x] [Citation(s) in RCA: 45] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/11/2023]
Abstract
Statistical analysis of both experimental and observational data is central to medical research. Unfortunately, the process of conventional statistical analysis is poorly understood by many medical scientists. This is due, in part, to the counter-intuitive nature of the basic tools of traditional (frequency-based) statistical inference. For example, the proper definition of a conventional 95% confidence interval is quite confusing. It is based upon the imaginary results of a series of hypothetical repetitions of the data generation process and subsequent analysis. Not surprisingly, this formal definition is often ignored and a 95% confidence interval is widely taken to represent a range of values that is associated with a 95% probability of containing the true value of the parameter being estimated. Working within the traditional framework of frequency-based statistics, this interpretation is fundamentally incorrect. It is perfectly valid, however, if one works within the framework of Bayesian statistics and assumes a 'prior distribution' that is uniform on the scale of the main outcome variable. This reflects a limited equivalence between conventional and Bayesian statistics that can be used to facilitate a simple Bayesian interpretation based on the results of a standard analysis. Such inferences provide direct and understandable answers to many important types of question in medical research. For example, they can be used to assist decision making based upon studies with unavoidably low statistical power, where non-significant results are all too often, and wrongly, interpreted as implying 'no effect'. They can also be used to overcome the confusion that can result when statistically significant effects are too small to be clinically relevant. This paper describes the theoretical basis of the Bayesian-based approach and illustrates its application with a practical example that investigates the prevalence of major cardiac defects in a cohort of children born using the assisted reproduction technique known as ICSI (intracytoplasmic sperm injection).
Collapse
Affiliation(s)
- L C Gurrin
- Women and Infants Research Foundation, King Edward Memorial Hospital, Subiaco, Perth, Australia
| | | | | |
Collapse
|
|
26
|
Burton PR, Gurrin LC, Campbell MJ. Clinical significance not statistical significance: a simple Bayesian alternative to p values. J Epidemiol Community Health 1998; 52:318-23. [PMID: 9764283 PMCID: PMC1756718 DOI: 10.1136/jech.52.5.318] [Citation(s) in RCA: 69] [Impact Index Per Article: 2.6] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
OBJECTIVES To take the common "Bayesian" interpretation of conventional confidence intervals to its logical conclusion, and hence to derive a simple, intuitive way to interpret the results of public health and clinical studies. DESIGN AND SETTING The theoretical basis and practicalities of the approach advocated is at first explained and then its use is illustrated by referring to the interpretation of a real historical cohort study. The study considered compared survival on haemodialysis (HD) with that on continuous ambulatory peritoneal dialysis (CAPD) in 389 patients dialysed for end stage renal disease in Leicestershire between 1974 and 1985. Careful interpretation of the study was essential. This was because although it had relatively low statistical power, it represented all of the data that were available at the time and it had to inform a critical clinical policy decision: whether or not to continue putting the majority of new patients onto CAPD. MEASUREMENTS AND ANALYSIS Conventional confidence intervals are often interpreted using subjective probability. For example, 95% confidence intervals are commonly understood to represent a range of values within which one may be 95% certain that the true value of whatever one is estimating really lies. Such an interpretation is fundamentally incorrect within the framework of conventional, frequency-based, statistics. However, it is valid as a statement of Bayesian posterior probability, provided that the prior distribution that represents pre-existing beliefs is uniform, which means flat, on the scale of the main outcome variable. This means that there is a limited equivalence between conventional and Bayesian statistics, which can be used to draw simple Bayesian style statistical inferences from a standard analysis. The advantage of such an approach is that it permits intuitive inferential statements to be made that cannot be made within a conventional framework and this can help to ensure that logical decisions are taken on the basis of study results. In the particular practical example described, this approach is applied in the context of an analysis based upon proportional hazards (Cox) regression. MAIN RESULTS AND CONCLUSIONS The approach proposed expresses conclusions in a manner that is believed to be a helpful adjunct to more conventional inferential statements. It is of greatest value in those situations in which statistical significance may bear little relation to clinical significance and a conventional analysis using p values is liable to be misleading. Perhaps most importantly, this includes circumstances in which an important public health or clinical decision must be based upon a study that has unavoidably low statistical power. However, it is also useful in situations in which a decision must be based upon a large study that indicates that an effect that is highly statistically significant seems too small to be of practical relevance. In the illustrative example described, the approach helped in making a decision regarding the use of CAPD in Leicestershire during the latter half of the 1980s.
Collapse
Affiliation(s)
- P R Burton
- Division of Biostatistics and Genetic Epidemiology, TVW Telethon Institute for Child Health Research, West Perth, Australia
| | | | | |
Collapse
|
|
27
|
Le Souëf P. Use of cohorts with extensive longitudinal data in investigating the molecular genetics of asthma. Clin Exp Allergy 1998; 28 Suppl 1:46-50; discussion 65-6. [PMID: 9641592 DOI: 10.1046/j.1365-2222.1998.0280s1046.x] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
Recent studies have associated several chromosomal regions and specific polymorphisms with asthma, atopy and airway hyperresponsiveness. Most of these studies have been cross-sectional which substantially limits their power to analyse genotype/phenotype associations. Asthma is a such a highly variable condition that future genotype/phenotype studies should use longitudinal data. Populations with extensive long-term longitudinal data will facilitate more precise definition of phenotype and allow analysis of asthma's natural history. Longitudinal information also means that each phenotypic attribute can be quantified and considered with respect to age. Collecting longitudinal data prospectively would be extremely expensive and take many years. Using existing longitudinal data sets would clearly be much quicker and more economical, but there are very few suitable data sets to be found. Studying a normal and an asthmatic population is ideal and would provide complementary genotype/phenotype information. This approach is a logical step to using the genotypic information obtained from cross-sectional molecular genetic studies to more critically establish the effect of genotype on phenotype.
Collapse
Affiliation(s)
- P Le Souëf
- Department of Paediatrics, Children's Hospital Medical Centre, University of Western Australia, Perth, Australia
| |
Collapse
|
|
28
|
Bower C, Condon R, Payne J, Burton P, Watson C, Wild B. Measuring the impact of conjugate vaccines on invasive Haemophilus influenzae type b infection in Western Australia. Aust N Z J Public Health 1998; 22:67-72. [PMID: 9599855 DOI: 10.1111/j.1467-842x.1998.tb01147.x] [Citation(s) in RCA: 14] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022] Open
Abstract
Haemophilus influenzae type b (Hib) causes serious infections in 26-59 per 100,000 non-Aboriginal Australian children under five years of age. Aboriginal children suffer much higher rates of infection (> or = 150 per 100,000), and at an earlier age, and have a greater risk of death and disability due to Hib infection. In 1992 and 1993, four conjugate Hib vaccines were introduced in Australia, and a nationally funded program of infant vaccination was begun in July 1993. This study aimed at evaluating the effectiveness of Hib vaccination in Aboriginal and non-Aboriginal children in Western Australia using a population-based active surveillance system for non-Aboriginal children and a case control study for Aboriginal children. The incidence of invasive Hib disease in non-Aboriginal children fell from 30.9 per 100,000 before vaccination was available to 6.3 per 100,000 in the second year after its introduction. The vaccine efficacy was estimated to be 80 per cent for Aboriginal children (odds ratio 0.20, 95 per cent CI 0.01-2.76) and, after adjustment for confounders, 75 per cent (odds ratio 0.25, CI 0.02-3.66). Based on the adjusted value (75 per cent), and using a Bayesian approach, we estimate that the posterior probability was 0.55 that the true vaccine efficacy is greater than 70 per cent, and 0.69 that the efficacy is greater than 50 per cent. We conclude that Hib vaccination is effective in preventing invasive Hib disease in Aboriginal and non-Aboriginal children in Australia.
Collapse
Affiliation(s)
- C Bower
- TVW Telethon Institute for Child Health Research, West Perth, Western Australia.
| | | | | | | | | | | |
Collapse
|
|
29
|
Abstract
The purpose of this case-control study was to identify antenatal and perinatal risk factors for sudden infant death syndrome (SIDS) in Aboriginal infants in Western Australia (WA). Cases were all Aboriginal infants born in WA from 1980 to 1990 inclusive and classified as dying from SIDS in WA. Controls consisted of a matched group and a random group both selected from liveborn Aboriginal infants born from 1980 to 1990. Multivariate modelling showed that SIDS in Aboriginal infants was strongly related to young maternal age (< 20 years, odds ratio (OR) = 2.89), high parity (parity > 3, OR = 4.40) and being small-for-gestational age (OR = 3.36) but was not associated with single marital status (OR = 0.95) or male sex (OR = 0.97). Although the study was based on routinely collected data, results do highlight some important groups for SIDS prevention. To gain further knowledge in terms of SIDS in Aboriginal infants, there is an urgent need to collect information concerning infant care practices in the Aboriginal community.
Collapse
Affiliation(s)
- L M Alessandri
- TVW Telethon Institute for Child Health Research, West Perth, Australia.
| | | | | | | |
Collapse
|
|
30
|
Thornton JG, Lilford RJ. Preterm breech babies and randomised trials of rare conditions. BRITISH JOURNAL OF OBSTETRICS AND GYNAECOLOGY 1996; 103:611-3. [PMID: 8688384 DOI: 10.1111/j.1471-0528.1996.tb09826.x] [Citation(s) in RCA: 16] [Impact Index Per Article: 0.6] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Affiliation(s)
- J G Thornton
- Centre for Reproduction, Growth and Development, University of Leeds
| | | |
Collapse
|
|
31
|
Lilford RJ, Thornton JG, Braunholtz D. Clinical trials and rare diseases: a way out of a conundrum. BMJ (CLINICAL RESEARCH ED.) 1995; 311:1621-5. [PMID: 8555809 PMCID: PMC2551510 DOI: 10.1136/bmj.311.7020.1621] [Citation(s) in RCA: 165] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/31/2023]
Abstract
Currently, clinical trials tend to be individually funded and applicants must include a power calculation in their grant request. However, conventional levels of statistical precision are unlikely to be obtainable prospectively if the trial is required to evaluate treatment of a rare disease. This means that clinicians treating such diseases remain in ignorance and must form their judgments solely on the basis of (potentially biased) observational studies experience, and anecdote. Since some unbiased evidence is clearly better than none, this state of affairs should not continue. However, conventional (frequentist) confidence limits are unlikely to exclude a null result, even when treatments differ substantially. Bayesian methods utilise all available data to calculate probabilities that may be extrapolated directly to clinical practice. Funding bodies should therefore fund a repertoire of small trials, which need have no predetermined end, alongside standard larger studies.
Collapse
Affiliation(s)
- R J Lilford
- West Midlands Health Authority, Arthur Thomson House, Birmingham
| | | | | |
Collapse
|
|
32
|
Stick SM, Burton PR, Clough JB, Cox M, LeSouëf PN, Sly PD. The effects of inhaled beclomethasone dipropionate on lung function and histamine responsiveness in recurrently wheezy infants. Arch Dis Child 1995; 73:327-32. [PMID: 7492197 PMCID: PMC1511345 DOI: 10.1136/adc.73.4.327] [Citation(s) in RCA: 39] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/25/2023]
Abstract
Inhaled steroids improve pulmonary function and bronchial responsiveness in older asthmatics. Data from studies using subjective outcome measures to determine the effectiveness of inhaled steroids in infants with recurrent wheezing are equivocal. Therefore, this study tested the hypothesis that beclomethasone dipropionate improves pulmonary function, including bronchial responsiveness to histamine, in recurrently wheezy infants. The study was double blind, placebo controlled lasting nine weeks. After the first baseline week, pulmonary function was measured using the rapid thoracoabdominal compression technique and bronchial responsiveness assessed with a histamine challenge test. Infants were then randomly allocated to receive doses of placebo or beclomethasone dipropionate (100 micrograms/puff) from metered aerosols. Two puffs of test aerosol were administered twice daily for eight weeks via a large volume spacer fitted with a facemask. Symptoms were recorded daily and pulmonary function and bronchial responsiveness assessed at the end of the treatment period; 50 infants, median age 12 months (range 5 to 18 months), were recruited. Twenty three in the beclomethasone dipropionate group and 15 in the placebo group completed the study and had pairs of pulmonary function measurements. Three were probable treatment failures (one beclomethasone dipropionate, two placebo), three were possible treatment failures (placebo), and others were non-compliant with study protocol. Baseline variables were not significantly different between those infants who completed the study and those who did not. Beclomethasone dipropionate and placebo groups were similar in all respects at baseline. Lung function and symptoms improved for both groups of infants during the study. Bronchial responsiveness increased significantly in the placebo group but there were not statistically significant differences between groups for any of the other outcome measures. It is concluded that beclomethasone dipropionate (400 microgram daily) via a large volume spacer does not significantly improve lung function or symptoms in recurrently wheezy infants but might hav a beneficial effect on bronchial responsiveness.
Collapse
Affiliation(s)
- S M Stick
- Department of Respiratory Medicine, Princess Margaret Hospital for Children, Perth, Western Australia
| | | | | | | | | | | |
Collapse
|
|
33
|
Adamson SJ, Alessandri LM, Badawi N, Burton PR, Pemberton PJ, Stanley F. Predictors of neonatal encephalopathy in full-term infants. BMJ (CLINICAL RESEARCH ED.) 1995; 311:598-602. [PMID: 7663254 PMCID: PMC2550662 DOI: 10.1136/bmj.311.7005.598] [Citation(s) in RCA: 124] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/26/2023]
Abstract
OBJECTIVE Preliminary investigation of the contribution of adverse antepartum and intrapartum factors to neonatal encephalopathy in singleton neonates born full term. DESIGN Matched case-control study based on incidence density sampling of controls. SETTING Two major teaching hospitals (one paediatric and one obstetric) and three peripheral maternity hospitals in Perth, Western Australia (population 1.2 million). SUBJECTS 89 cases, all the full term singleton neonates born during an eight month period in 1992 who fulfilled one or more of six criteria during the first week of life (seizures, abnormal conscious state, persistent hypertonia or hypotonia, and feeding or respiratory difficulties of central origin). One full term control infant without neonatal encephalopathy was matched to each case by sex, hospital of delivery, time of day and day of the week of birth, and maternal health insurance status. MAIN OUTCOME MEASURES Odds ratio estimates of relative risk of neonatal encephalopathy associated with antepartum and intrapartum factors. RESULTS Estimated incidence of moderate or severe encephalopathy in first week of life was 3.75 per 1000 full term live births. Thirteen cases and no controls had evidence suggestive of important intrapartum hypoxia, and in only five of these cases was the neurological condition at birth attributed to events during the intrapartum period. Univariate conditional logistic regression analysis identified significant differences between cases and controls for maternal vaginal bleeding in pregnancy, maternal thyroxine treatment, congenital abnormalities, induction of labour, interval from membrane rupture to delivery, maternal pyrexia in labour, augmentation of labour, abnormal intrapartum cardiotocograms, and meconium in labour. Family history of convulsions also approached significance. CONCLUSIONS Our preliminary results suggest that intrapartum hypoxia, according to currently used criteria, was not the cause of neonatal encephalopathy in most cases in this population. Our findings suggest that many aetiologies of neonatal encephalopathy originate in the antepartum period.
Collapse
Affiliation(s)
- S J Adamson
- Department of Neonatology, Princess Margaret Hospital for Children, Subiacco, Western Australia
| | | | | | | | | | | |
Collapse
|
|
34
|
Faillace WJ. A no-touch technique protocol to diminish cerebrospinal fluid shunt infection. SURGICAL NEUROLOGY 1995; 43:344-50. [PMID: 7792703 DOI: 10.1016/0090-3019(95)80060-t] [Citation(s) in RCA: 56] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
Abstract
BACKGROUND Cerebrospinal fluid (CSF) shunts become infected primarily by bacterial organisms indigenous to the patient's skin flora, but bacteria from the operating room environment, hospital, or no obvious source may also infect a shunt. To decrease the incidence of shunt infection, a no-touch technique protocol was developed and utilized in a prospective manner. METHODS A before-after trial analysis was performed to compare the infection rates between patients who had CSF shunts placed using the no-touch technique protocol versus patients who had surgery without the protocol. Patients were stratified by age, etiology of hydrocephalus, type of shunt surgery, and presence of a contaminated skin wound, namely, tracheostomy, gastrostomy-jejunostomy, colostomy, or halo. The differences in infection rates were analyzed with the Fisher exact test with midpoint value correction, and standard statistical methods were used to calculate the 90% confidence interval odds ratio and number to treat. RESULTS The no-touch technique protocol resulted in a clinically significant threefold decrease in shunt infection rate from 9.1% to 2.9% (p = 0.058 at 0.10 level, odds ratio 0.305, confidence interval 0.084-1.11), and a near threefold decrease in the infection rate per patient from 11.3% to 3.9% (p = 0.032 at 0.10 level, odds ratio 0.243, confidence interval 0.065-0.906). CONCLUSIONS The no-touch technique protocol as described herein is a useful method to decrease shunt infection. A larger prospective, randomized, multicenter clinical trial is encouraged to stringently assess the efficacy of the protocol.
Collapse
Affiliation(s)
- W J Faillace
- Department of Neurosurgery and Pediatrics, University of Florida Health Science Center, Jacksonville 32209, USA
| |
Collapse
|
|
35
|
Cobo E, Campbell MJ. Interpreting results of observational research. P values are still useful. BMJ (CLINICAL RESEARCH ED.) 1994; 309:1439. [PMID: 7819867 PMCID: PMC2541353 DOI: 10.1136/bmj.309.6966.1439a] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/27/2023]
|