China
Africa
Explore chapters and articles related to this topic
Network Meta-Analysis
Published in Ding-Geng (Din) Chen, Karl E. Peace, Applied Meta-Analysis with R and Stata, 2021
After we compared the effectiveness of the treatments, we have to rank the treatments to identify which treatment intervention shows the most superior treatment effect (Tonin et al., 2017). We can use the following command to generate a table as shown in Figure 12.18 and a figure as shown in Figure 12.19 to evaluate the treatment superiority.
Network Meta-Analysis
Published in Christopher H. Schmid, Theo Stijnen, Ian R. White, Handbook of Meta-Analysis, 2020
Adriani Nikolakopoulou, Ian R. White, Georgia Salanti
It is best to describe the full rank distribution. Considering only the probability of being at the first rank over-emphasizes the probability of the treatment producing favorable relative effects and ignores the probabilities of large unfavorable effects. Consequently, a treatment hierarchy using the probability of being at the first rank will favor treatments whose effects are estimated with large uncertainty. The cumulative rank (the probability that a treatment is ranked at least as high as a specific rank, e.g., at least as high as second) is better and if applied for all possible cumulative ranks uses all the ranking data.
Clinical Data Management and Statistical Design in the Clinical Research Process
Published in Gary M. Matoren, The Clinical Research Process in the Pharmaceutical Industry, 2020
Joseph R. Assenzo, Thomas W. Teal
Clinical studies will usually have more than one objective, and since the objectives may conflict it is desirable to rank them in order of importance. This facilitates evaluation of alternative experimental methods and clinical models.
Efficient estimators with categorical ranked set samples: estimation procedures for osteoporosis
Published in Journal of Applied Statistics, 2022
Armin Hatefi, Amirhossein Alvandi
BMD is one of the most reliable predictors for the diagnosis of bone disorder. According to the expert panel of WHO, the BMD of a patient is compared to the BMD norm of the reference group and is given by T-score. The reference group typically involves healthy young adults aged 20–29. The difference between BMD of a patient and BMD norm is assessed as a criterion to determine the bone disorder status which falls into three ordinal categories, including normal, osteopenia and osteoporosis. The status is considered normal when BMD is within 1 standard deviation (SD) from BMD norm (equivalently T-score between −1 and 1). The status is osteopenia when BMD falls within −1 and −2.5 SD from the norm and the status is osteoporosis when the BMD is less than −2.5 SD from norm ( [16,31]). BMD is obtained via dual X-ray absorptiometry (DXA) imaging. Medical experts are then required to segment the images manually and compute the necessary measurements. Despite the tremendous cost of BMD measurement, practitioners typically have access to inexpensive and easy to obtain factors such as age, weight and BMD from earlier surveys. These factors can be easily used to rank the patients. Therefore, the RSS as a cost-effective sampling scheme can be employed to estimate more efficiently the bone disorder population.
A spotlight on cross-sectional research: Addressing the issues of confounding and adjustment
Published in International Journal of Healthcare Management, 2021
Nestor Asiamah, Edwin Mends-Brew, Benjamin Kojo Teye Boison
The nursing performance scale modified by Asiamah [6] for measuring the job performance of health workers in a similar population was employed to measure job performance. This scale has 52 items and has produced satisfactory psychometric properties in previous studies. It also applies five levels of response that range from strongly disagree (1) to strongly agree (5). Training was measured in accordance with previous studies [6,37] in terms of the number of training programs a participant had acquired in his or her current hospital. Educational level was measured as the highest educational qualification obtained by the participant. Its measurement was based on this coding scheme: basic/secondary 1; diploma – 2; first degree – 3; Master’s degree – 4; and PhD or equivalent – 5. Job tenure was measured in terms of the number of years the individual participant had worked as a health worker. Job income was measured in terms of the employee’s current net monthly income. Job rank was measured in terms of the employee’s current rank in the hospital.
Worries and concerns of inflammatory bowel disease (IBD) patients in Belgium – a validation of the Dutch rating form
Published in Scandinavian Journal of Gastroenterology, 2020
Marta Walentynowicz, Iris Van de Pavert, Sofie Coenen, Liselotte Fierens, Johan Vlaeyen, Andreas von Leupoldt, Lukas Van Oudenhove, Séverine Vermeire, Gert Van Assche, Marc Ferrante, Ilse Van Diest
Concerning the effect of disease activity on worries and concerns, differences were observed between patients with active IBD, M(SD)active=42.54 (18.75) and clinical remission IBD, M(SD)remission=32.97 (17.29), t(494)=5.92, p<.001. This was particularly the case for patients with CD, among whom those with active disease had much higher levels of worries than those in clinical remission (see Supplementary Table 1 for details). For individual concerns, only 2 did not differ between the IBD patients with active disease versus remission, namely dying early and passing the disease to others (Table 1). Nevertheless, the rank ordering of mean scores by patients with different disease activities was comparable, with Spearman’s rho=.90, p<.001.