An Example on the Value of Non-Randomisation in Clinical Trials in Complementary Medicine

Luedtke, Rainer; Weber, U.; Fischer, Irene; Friese, Karl-Heinz; Moêller, H.

doi:10.1159/000057272

Cited by 8 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…After further review of articles, 15 articles were excluded from further analysis as the outcomes were continuous and it was not possible to calculate an odds ratio or risk ratio [59,86,88,111,120,124,137,150,152,160,162,193,195,196,206]. For all selected reports published through 2003, we abstracted the following items: (i) the number of variables used to predict treatment and outcome, respectively; (ii) the unadjusted (crude) estimate for the treatment-outcome association; (iii) the estimates for the treatment-outcome association adjusted by use of PS matching, PS adjustment, and/or multivariable outcome models, including models without PS and with PS as well as covariates; (iv) the predictive value of the PS as assessed by the area under the receiver operating characteristic (ROC) curve (equivalent to the c-statistic in logistic regression); and (v) the percent of exposed participants that could be matched to unexposed participants (where applicable).…”

Section: Resultsmentioning

confidence: 99%

A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods

Stürmer

Joshi

Glynn

et al. 2006

Journal of Clinical Epidemiology

585

497

View full text Add to dashboard Cite

show abstract

Section: Resultsmentioning

confidence: 99%

A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods

Stürmer

Joshi

Glynn

et al. 2006

Journal of Clinical Epidemiology

585

497

View full text Add to dashboard Cite

show abstract

“…The application of variance analysis models using covariates, either by direct inclusion of multiple moderator variables or by taking the diversion to calculate a propensity score, improves the power of the results in a comparative study. In our case the two statistical techniques led to similar results, making the question of which method is more suitable a secondary one [13]. Instead, we consider the question concerning the nature of the relevant adjustment factors to be more important.…”

Section: Discussionmentioning

confidence: 59%

Treatment Outcomes in Patients with Migraine: An Ex-Post-Facto Comparison of Two In-Patient Facilities

Weidenhammer¹,

Linde²,

Melchart³

2004

Complement Med Res

View full text Add to dashboard Cite

Background: In two hospitals we performed an open, prospective observational study on patients with chronic headache as a measure of internal quality assurance using identical methods. Available data were subordinately analysed in order to compare both studies. Questions: Are the patient samples of both hospitals comparable? If not, which form of statistical adjustment is recommended? Are there differences in the outcome measures of both facilities? Methods: The outcomes were defined as differences between baseline values and values at discharge from hospital, respectively 6 months after. Frequency of headache attacks, intensity of pain, intensity of general complaints as well as of concomitant symptoms, and quality of life were determined in advance as dependent variables. To compare both patient groups univariate analysis of variance without and with inclusion of covariates were used. For calculating propensity scores (conditional probability of belonging to one of two groups) a logistic regression with the same covariates serving as independent variables was performed. Patients: 426 patients with the main diagnosis ‘Migraine’ and complete data sets concerning the covariates were selected for analysis. 87% of patients are female, the mean age is 45.5 ± 11.7 years (range 14–73 yrs). Results: 4 out of 11 potential covariates show statistically significant differences between the patients of both hospitals. Correct classification of patients by means of the propensity score succeeds in 67%. Comparing the outcomes at discharge from hospital, significant differences between both groups exist which are, with one exception, not affected by controlling for covariates. 6 months after discharge two of the initial differences between both patient groups are no longer present. These findings are independent from the statistical technique of risk adjustment. Conclusions: Because of the observed differences between both patient groups it is recommended to adjust data by regression analysis in order to enhance comparability. The choice for one of the two proposed techniques is secondary. With respect to the analyses clear differences between both hospitals exist in short-term outcomes, disappearing 6 months later.

show abstract

“…Unfortunately, this raises other problems which can invalidate the trial results. A detailed discussion on this topic is found in [22]. Generally, besides randomisation, our study showed two major problems.…”

Section: Discussionmentioning

confidence: 89%

“…In randomised trials which compare complementary and conventional therapies a small external validity can be expected [22]. We therefore recommend to perform a clinical trial which both a randomised and a non-randomised comparison.…”

Section: Discussionmentioning

confidence: 99%

A Non-Randomised Pilot Study to Compare Complementary and Conventional Treatments of Acute Sinusitis

Weber¹,

Luedtke

Friese³

et al. 2002

Complement Med Res

Self Cite

View full text Add to dashboard Cite

Background: It is still under discussion whether antibiotics are effective in the treatment of acute sinusitis. Moreover, they are known to have considerable side-effects. In contrast, complementary approaches are reported to have little side-effects and an equivalent efficiency. Objectives: To assess the success of conventional and complementary treatments of acute sinusitis and to estimate the patient numbers needed to confirm therapeutic equivalence. Treatment success was measured by three different scores, assessed by both patients and physicians. Methods: Multicentre (2 complementary and 3 conventional ENT centres), non-randomised, controlled clinical trial with 63 patients (complementary group 30, conventional group 33 patients). To control for confounders treatment differences were estimated by propensity score techniques. Treatments: The choice of medication was entirely left to the physician. We recommended to use antibiotics, secretolytics and symptomimetics in the conventional group and a combination of the herbal remedy Sinupret^® and the homeopathic remedy Cinnabaris 3X in the complementary group. Results: Treatment differences varied substantially depending on the outcome measure, but they were always not clinically relevant. Conventional treatment was slightly better when the outcome was assessed by the physicians (1.8 score points) but slightly worse when it was assessed by patients (0.2 score points) or in terms of the HCG-5 quality of life score (0.8 score points). p values were always > 0.3. Conclusions: Both treatments appear to be equally effective (or ineffective). Results might be biased because both treatment groups differed substantially. Randomised trials including at least 400 patients are needed to produce valid results.

show abstract

An Example on the Value of Non-Randomisation in Clinical Trials in Complementary Medicine

Cited by 8 publications

References 23 publications

A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods

A review of the application of propensity score methods yielded increasing use, advantages in specific settings, but not substantially different estimates compared with conventional multivariable methods

Treatment Outcomes in Patients with Migraine: An Ex-Post-Facto Comparison of Two In-Patient Facilities

A Non-Randomised Pilot Study to Compare Complementary and Conventional Treatments of Acute Sinusitis

Contact Info

Product

Resources

About