Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “subgrouping”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4Linked to original sources
PubMed2001

Subgroup analyses in randomised controlled trials: quantifying the risks of false-positives and false-negatives.

BACKGROUND: Subgroup analyses are common in randomised controlled trials (RCTs). There are many easily accessible guidelines on the selection and analysis of subgroups but the key messages do not seem to be universally accepted and inappropriate analyses continue to appear in the literature. This has potentially serious implications because erroneous identification of differential subgroup effects may lead to inappropriate provision or withholding of treatment. OBJECTIVES: (1) To quantify the extent to which subgroup analyses may be misleading. (2) To compare the relative merits and weaknesses of the two most common approaches to subgroup analysis: separate (subgroup-specific) analyses of treatment effect and formal statistical tests of interaction. (3) To establish what factors affect the performance of the two approaches. (4) To provide estimates of the increase in sample size required to detect differential subgroup effects. (5) To provide recommendations on the analysis and interpretation of subgroup analyses. METHODS: The performances of subgroup-specific and formal interaction tests were assessed by simulating data with no differential subgroup effects and determining the extent to which the two approaches (incorrectly) identified such an effect, and simulating data with a differential subgroup effect and determining the extent to which the two approaches were able to (correctly) identify it. Initially, data were simulated to represent the 'simplest case' of two equal-sized treatment groups and two equal-sized subgroups. Data were first simulated with no differential subgroup effect and then with a range of types and magnitudes of subgroup effect with the sample size determined by the nominal power (50-95%) for the overall treatment effect. Additional simulations were conducted to explore the individual impact of the sample size, the magnitude of the overall treatment effect, the size and number of treatment groups and subgroups and, in the case of continuous data, the variability of the data. The simulated data covered the types of outcomes most commonly used in RCTs, namely continuous (Gaussian) variables, binary outcomes and survival times. All analyses were carried out using appropriate regression models, and subgroup effects were identified on the basis of statistical significance at the 5% level. RESULTS: While there was some variation for smaller sample sizes, the results for the three types of outcome were very similar for simulations with a total sample size of greater than or equal to 200. With simulated simplest case data with no differential subgroup effects, the formal tests of interaction were significant in 5% of cases as expected, while subgroup-specific tests were less reliable and identified effects in 7-66% of cases depending on whether there was an overall treatment effect. The most common type of subgroup effect identified in this way was where the treatment effect was seen to be significant in one subgroup only. When a simulated differential subgroup effect was included, the results were dependent on the nominal power of the simulated data and the type and magnitude of the subgroup effect. However, the performance of the formal interaction test was generally superior to that of the subgroup-specific analyses, with more differential effects correctly identified. In addition, the subgroup-specific analyses often suggested the wrong type of differential effect. The ability of formal interaction tests to (correctly) identify subgroup effects improved as the size of the interaction increased relative to the overall treatment effect. When the size of the interaction was twice the overall effect or greater, the interaction tests had at least the same power as the overall treatment effect. However, power was considerably reduced for smaller interactions, which are much more likely in practice. The inflation factor required to increase the sample size to enable detection of the interaction with the same power as the overall effect varied with the size of the interaction. For an interaction of the same magnitude as the overall effect, the inflation factor was 4, and this increased dramatically to of greater than or equal to 100 for more subtle interactions of < 20% of the overall effect. Formal interaction tests were generally robust to alterations in the number and size of the treatment and subgroups and, for continuous data, the variance in the treatment groups, with the only exception being a change in the variance in one of the subgroups. In contrast, the performance of the subgroup-specific tests was affected by almost all of these factors with only a change in the number of treatment groups having no impact at all. CONCLUSIONS: While it is generally recognised that subgroup analyses can produce spurious results, the extent of the problem is almost certainly under-estimated. This is particularly true when subgroup-specific analyses are used. In addition, the increase in sample size required to identify differential subgroup effects may be substantial and the commonly used 'rule of four' may not always be sufficient, especially when interactions are relatively subtle, as is often the case. CONCLUSIONS--RECOMMENDATIONS FOR SUBGROUP ANALYSES AND THEIR INTERPRETATION: (1) Subgroup analyses should, as far as possible, be restricted to those proposed before data collection. Any subgroups chosen after this time should be clearly identified. (2) Trials should ideally be powered with subgroup analyses in mind. However, for modest interactions, this may not be feasible. (3) Subgroup-specific analyses are particularly unreliable and are affected by many factors. Subgroup analyses should always be based on formal tests of interaction although even these should be interpreted with caution. (4) The results from any subgroup analyses should not be over-interpreted. Unless there is strong supporting evidence, they are best viewed as a hypothesis-generation exercise. In particular, one should be wary of evidence suggesting that treatment is effective in one subgroup only. (5) Any apparent lack of differential effect should be regarded with caution unless the study was specifically powered with interactions in mind. CONCLUSIONS--RECOMMENDATIONS FOR RESEARCH: (1) The implications of considering confidence intervals rather than p-values could be considered. (2) The same approach as in this study could be applied to contexts other than RCTs, such as observational studies and meta-analyses. (3) The scenarios used in this study could be examined more comprehensively using other statistical methods, incorporating clustering effects, considering other types of outcome variable and using other approaches, such as Bootstrapping or Bayesian methods.

Data Interpretation, Statistical↗
PubMed1996

Identification of a variant subgroup A strain of respiratory syncytial virus.

During epidemiologic surveillance of children with respiratory syncytial virus (RSV) disease in Huntington, W.Va., we identified seven strains of a new variant subgroup A RSV (subgroup A-Var) by their reactions in an enzyme immunoassay with two anti-F monoclonal antibodies (MAbs) specific for two epitopes, F1 and F4, generated against the subgroup B RSV. The prototype strain of subgroup A and all other subgroup A field strains from that epidemiologic year failed to react with these two subgroup B MAbs. Additional enzyme immunoassays with 18 subgroup B anti-F MAbs specific for 14 epitopes showed that subgroup A-Var strains also reacted with a MAb specific for the subgroup B F2 epitope. In a radioimmune precipitation assay, the molecular size of the subgroup A-Var F2 subunit of the fusion (F) protein clearly differed from those of both prototype strains of subgroup A and subgroup B RSV. The molecular size of the F2 subunit of subgroup A-Var (24 kDa) was intermediate between the size of the F2 subunit of subgroup A (25 kDa) and that of subgroup B (23 kDa). However, the molecular sizes of the F1 subunits of both subgroup A and subgroup A-Var were identical (54 kDa) and slightly larger than those of the F1 subunits of both subgroups B1 and B2 (53 kDa). These data suggest that subgroup A-Var may represent a distinct RSV A subgroup, analogous to subgroup B1 and B2 RSV, and it is the first-identified naturally occurring subgroup A RSV with an F protein different from that of the prototype A RSV.

Antibodies, Monoclonal↗
PubMed2006

Development of degenerate and species-specific primers for the differential and simultaneous RT-PCR detection of grapevine-infecting nepoviruses of subgroups A, B and C.

Based on the nucleotide sequence homology of RNA-1 and RNA-2 of nepoviruses isolated from grapevines, three sets of degenerate primers, one for each of the three subgroups of the genus (A, B and C), were designed and proved effective for RT-PCR detection of subgroups in infected grapevines and herbaceous hosts. Primers designed specifically for detecting subgroup A species amplified a fragment of 255 bp from samples infected by Grapevine fanleaf virus (GFLV), Arabis mosaic virus (ArMV), Tobacco ringspot virus (TRSV) and Grapevine deformation virus (GDefV), but not from samples infected by other nepovirus species. Similarly, primers for detection of subgroup B nepoviruses amplified a 390 bp product from samples infected by Grapevine chrome mosaic virus (GCMV), Tomato black ring virus (TBRV), Grapevine Anatolian ringspot virus (GARSV) and Artichoke Italian latent virus (AILV). The third set of primers amplified a 640 bp fragment, only from samples infected by subgroup C nepoviruses, i.e Tomato ringspot virus (ToRSV) Grapevine Bulgarian latent virus (GBLV), and Grapevine Tunisian ringspot virus (GTRSV). These primers were able to detect simultaneously all viral species belonging to the same subgroup and to discriminate species of different subgroups. Multiplex-PCR detection of subgroup A and B nepoviruses was obtained using a specific primer (sense for subgroup A and antisense for subgroup B) for each of the species of the same subgroup in combination with the degenerate subgroup-specific primers. In this way it was possible to detect four different viral species in single samples containing mixtures of viruses of the same subgroup. In particular, for viruses of subgroup A (TRSV, GFLV, ArMV and GDefV) amplicons of 190, 259, 301 and 371 bp were obtained, whereas amplicons of 190, 278, 425 and 485 bp, respectively, were obtained from samples infected with viruses of subgroup B (GCMV, AILV, GARSV and TBRV).

Amino Acid Sequence↗
PubMed2001

Challenges of subgroup analyses in multinational clinical trials: experiences from the MERIT-HF trial.

BACKGROUND: International placebo-controlled survival trials (Metoprolol Controlled-Release Randomised Intervention Trial in Heart Failure [MERIT-HF], Cardiac Insufficiency Bisoprolol Study [CIBIS-II], and Carvedilol Prospective Randomized Cumulative Survival trial [COPERNICUS]) evaluating the effects of b-blockade in patients with heart failure have all demonstrated highly significant positive effects on total mortality as well as total mortality plus all-cause hospitalization. Also, the analysis of the US Carvedilol Program indicated an effect on these end points. Although none of these trials are large enough to provide definitive results in any particular subgroup, it is natural for physicians to examine the consistency of results across various subgroups or risk groups. Our purpose was to examine both predefined and post hoc subgroups in the MERIT-HF trial to provide guidance as to whether any subgroup is at increased risk, despite an overall strongly positive effect, and to discuss the difficulties and limitations in conducting such subgroup analyses. METHODS: The study was conducted at 313 clinical sites in 16 randomization regions across 14 countries, with a total of 3991 patients. Total mortality (first primary end point) and total mortality plus all-cause hospitalization (second primary end point) were analyzed on a time to first event. The first secondary end point was total mortality plus hospitalization for heart failure. RESULTS: Overall, MERIT-HF demonstrated a hazard ratio of 0.66 for total mortality and 0.81 for mortality plus all-cause hospitalization. The hazard ratio of the first secondary end point of mortality plus hospitalization for heart failure was 0.69. The results were remarkably consistent for both primary outcomes and the first secondary outcome across all predefined subgroups as well as for nearly all post hoc subgroups. The results of the post hoc US subgroup showed a mortality hazard ratio of 1.05. However, the US results regarding both the second primary combined outcome of total mortality plus all-cause hospitalization and of the first secondary combined outcome of total mortality plus heart failure hospitalization were in concordance with the overall results of MERIT-HF. Tests of country by treatment interaction (14 countries) revealed a nonsignificant P value of.22 for total mortality. The mortality hazard ratio for US patients in New York Heart Association (NYHA) class III/IV was 0.80, and it was 2.24 for patients in NYHA class II, which is not consistent with causality by biologic gradient. We have not been able to identify any confounding factor in baseline characteristics, baseline treatment, or treatment during follow-up that could account for any treatment by country interaction. Thus we attribute the US subgroup mortality hazard ratio to be due to chance. CONCLUSIONS: Just as we must be extremely cautious in overinterpreting positive effects in subgroups, even those that are predefined, we must also be cautious in focusing on subgroups with an apparent neutral or negative trend. We should examine subgroups to obtain a general sense of consistency, which is clearly the case in MERIT-HF. We should expect some variation of the treatment effect around the overall estimate as we examine a large number of subgroups because of small sample size in subgroups and chance. Thus the best estimate of the treatment effect on total mortality for any subgroup is the estimate of the hazard ratio for the overall trial.

Adrenergic beta-Antagonists↗
PubMed1995

Subgroup determination of group A rotaviruses recovered from piglets in Nigeria.

Subgroup analysis using subgroup-specific monoclonal ELISA revealed a preponderance of subgroup 2-specific antigens of group A porcine rotaviruses over subgroup 1. Of 113 polyacrylamide gel electrophoresis-positive test samples, obtained from 4 States of Nigeria, 31 (27.4%) and 45 (39.8%) were determined to have subgroup 1 and 2 specificities, respectively. However, 37 (32.7%) test samples could not be classified into any of the known group A rotavirus subgroups. These "unclassifiable" samples probably had neither subgroup 1 nor 2 specificities in ELISA or could belong to a third subgroup unknown or not investigated in this study. In all age groups investigated, subgroup 1 and 2 specific antigens were prevalent. This was also observed after yearly analysis of subgroup specificity; however, a higher prevalence of subgroup 2 specificity was observed in 1990 and 1991. Subgroup 1 rotaviruses were found in all the 4 States sampled (Plateau, Benue, Oyo, and Cross River), whereas subgroup 2 rotaviruses were detected only in Plateau State. All rotaviruses recovered in this study had long genome electrophoretic migration patterns, irrespective of subgroup. Thus genomic diversity of group A rotaviruses does not necessarily reflect antigenic diversity, as there is no mandatory correlation between genome electropherotype pattern and subgroup specificity.

Age Factors↗
PubMed1991

Prevalence of respiratory syncytial virus subgroups A and B in France from 1982 to 1990.

A fluorescence antibody test with monoclonal antibodies was used to determine the subgroup (A or B) of respiratory syncytial virus from infants hospitalized in Caen, France, over eight consecutive epidemics from 1982 to 1990. From 1982 to 1985, 27 (30%) out of 90 frozen nasal slides were classified as subgroup A strains and 63 (70%) were classified as subgroup B. B strains predominated over A in 1983-1984 and 1984-1985. From 1985 to 1990, 284 respiratory syncytial virus field strains were reisolated from frozen materials; 115 (40.5%) were typed as subgroup A and 169 (59.5%) were typed as subgroup B. In 1985-1986, 1986-1987, and 1988-1989, both subgroups were present in almost equal numbers; subgroup A (88.3%) predominated in 1987-1988, and subgroup B (84.5%) predominated in 1989-1990. In conclusion, both subgroups occur together each year, and one subgroup rarely predominates, e.g., subgroup A in 1987-1988 and subgroup B in 1983-1984 and 1989-1990. Therefore, there is a gradual change of the predominant subgroup into another over a period of about 5 years; the relative frequency of subgroup A strains increased from 1983 to 1988, whereas the percentage of subgroup B decreased during the same period.

Antibodies, Monoclonal↗
PubMed1998

An empirical analysis of eating disorder, not otherwise specified: preliminary support for a distinct subgroup.

OBJECTIVE: In recent years, there has been debate concerning whether distinct subgroups exist within the eating disorder, not otherwise specified (EDNOS) diagnostic category. One subgroup that has been suggested is binge-eating disorder (BED). While BED has received some research attention, relatively little is known about other possible subgroups within the EDNOS category. The purpose of the present study is to empirically investigate whether distinct subgroups exist within the diagnostic category of EDNOS. METHOD: Participants were 53 EDNOS patients who presented to psychotherapy clinics for treatment of an eating disorder. Information gathered from a clinical assessment, which included a clinical interview and self-report questionnaires, was used in the analyses of the study. RESULTS: Using cluster analytic procedures, two subgroups of patients diagnosed with EDNOS were identified. The two subgroups differed from each other in terms of weight, binging, and body image variables. Specifically, the second subgroup (of 11 patients) appeared to be a distinct subgroup of overweight binge-eating patients, while the first subgroup appeared to be a heterogenous group of EDNOS patients. The overweight binge-eating subgroup was significantly higher in current weight, in reported highest adult weight, in reported higher lowest adult weight, and had more binges per week than the heterogenous EDNOS subgroup. Interestingly, the two subgroups did not differ in terms of self-reported purging and/or compensatory behaviors (e.g., vomiting and laxative use). DISCUSSION: The results of the present study provide preliminary support for a distinct subgroup within the EDNOS diagnostic category. This subgroup resembles BED, with the exception of the presence of purging behaviors. The findings of the present study suggest the need to further investigate the exclusionary criteria of purging/compensatory behaviors for the BED diagnosis.

Adult↗
PubMed2006

Interpretation of subgroup results in clinical trial publications: insights from a survey of medical specialists in Ontario, Canada.

BACKGROUND: Clinicians routinely apply randomized trial evidence to their patients who meet study selection criteria. However, little is known about how clinicians interpret conflicting subgroup data. METHODS: We mailed a self-administered survey to all practicing cardiologists (n = 309) and 695 randomly chosen other specialists in Ontario, Canada. The survey presented 6 hypothetical trials where a subgroup result deviated from the overall result. We also elicited responses to some general statements about clinical evidence and subgroups. RESULTS: Completed surveys were received from 435 physicians (44%). Faced with overall benefit but no apparent treatment effect in a subgroup, almost 44% would exclude subgroup-type patients, notwithstanding the hazard of beta error. Given overall harm but significant benefit for a subgroup, responses were split approximately 60:40 between continuing conventional therapy for all and treating subgroup-type patients with the new drug. For an overall null result with a positive treatment-subgroup interaction term, 25% of respondents would continue conventional therapy, whereas 69% would adopt the new drug for subgroup-type patients. Physicians with an academic appointment, devoting more time to research, or with formal training in research methodology were more likely to ignore subgroups unless a treatment-subgroup interaction term was significant (P values ranging from .018 to <.0001). Asked if in general they paid special attention to individual subgroup results, respondents were again divided with 37.5% agreeing, 39.5% disagreeing, and the rest undecided. CONCLUSION: Clinicians disagree sharply in interpretation of clinical trials when the overall and subgroup results diverge. Clearer guidelines are needed for undertaking, reporting, and interpreting subgroup analyses.

Cardiology↗
PubMed1996

Inter-relationships among subgroups, serotypes, and electropherotypes of rotaviruses isolated from humans.

In an epidemiological study of human rotavirus (HRV) infections in metro Jeddah, Saudi Arabia, the relationships among subgroups, serotypes, and RNA electropherotypes of the rotavirus isolates were investigated. Of the 523 rotavirus-positive stool specimens, 245 were examined for subgroup, serotype, and electropherotype. Of these, 84 isolates were analyzed for their subgroup and RNA electropherotype specificites, 12 (14.3%) were of subgroup 1, 69 (82.1%) were of subgroup II, and 3 (3.6%) were a mixture of subgroup I and II. Of the subgroup 1 specimens, 5 (41.7%) showed long electrophoretic migration patterns and 7 (58.3%) showed short patterns. In subgroup II specimens, 66 (95.7%) were of long patterns and 3 (4.3%) of short patterns. The relationship between HRVS serotypes and electropherotypes was also determined for the same 245 rotavirus specimens. Of these, 36 (14.7%) exhibited short RNA patterns and 209 (85.3%) exhibited long patterns. The short pattern specimens consisted of serotype 1 (8.3%), serotype 2 (63.9%), serotype 3 and serotype 4 (2.8%) each. The long pattern specimens consisted of serotype 1 (60.3%), serotype 2 (1.4%), serotype 3 (7.2%) and serotype 4 (17.7%). Among the previous 245 specimens, subgroup specificities were available for 51 specimens. All subgroup I were of serotype 2, and all subgroup II were of serotype 1, 3 or 4. RNAs of either subgroup showed both long and short electropherotypes. No relationship could be established between subgroups or serotypes and a particular electropherotype. It seems unlikely that electropherotyping of human rotavirus (HRV) can be used for identifying the subgroups or serotypes of strains.

Child, Preschool↗
PubMed2006

Subgroup analyses in therapeutic cardiovascular clinical trials: are most of them misleading?

BACKGROUND: Treatment decisions in clinical cardiology are directed by results from randomized clinical trials (RCTs). We studied the appropriateness of the use and interpretation of subgroup analysis in current therapeutic cardiovascular RCTs. METHODS: We reviewed main reports of phase 3 cardiovascular RCTs with at least 100 patients, published in 2002 and 2004, and from major journals (Circulation, J Am Coll Cardiol, Am Heart J, Am J Cardiol, N Engl J Med, Lancet, JAMA, BMJ, Ann Intern Med). Information on subgroups included prespecification, number, interaction test use, significant subgroups found, and emphasis on findings. We examined appropriateness of reporting and differences according to sample size, overall trial result, and CONSORT adoption. RESULTS: We selected 63 RCTs, with a median of 496 (range 100-15,245) patients. Thirty-nine RCTs were reported with subgroup analyses and 26 with > 5 subgroups. No trial was specifically powered to detect subgroup effects, and only 14 RCTs were reported with fully prespecified subgroups. Only 11 RCTs were reported with interaction tests. Furthermore, 21 RCTs were reported with claims of significant subgroups and 15 with equal or more emphasis to subgroups than to the overall results. Subgroup analyses in large RCTs (> 500 patients) were reported more often than in small ones (24/30 vs 15/33, P = .005). No differences were found according to overall result (positive/negative) or CONSORT adoption. CONCLUSIONS: Subgroup analyses in recent cardiovascular RCTs were reported with several shortcomings, including a lack of prespecification and testing of a large number of subgroups without the use of the statistically appropriate test for interaction. Reporting of subgroup analysis needs to be substantially improved because emphasis on these secondary results may mislead treatment decisions.

Cardiovascular Diseases↗
PubMed2003

How should subgroup analyses affect clinical practice? Insights from the Metoprolol Succinate Controlled-Release/Extended-Release Randomized Intervention Trial in Heart Failure (MERIT-HF).

CONTEXT: The Metoprolol CR/XL Randomized Intervention Trial in Chronic Heart Failure (MERIT-HF), the Cardiac Insufficiency Bisoprolol Study II (CIBIS-II), and the Carvedilol Prospective Randomized Cumulative Survival Study (COPERNICUS) have all demonstrated highly significant positive effects on total mortality as well as total mortality plus all-cause hospitalization in patients with heart failure. While none of these trials are large enough to provide definitive results in any particular subgroup, it is of interest for physicians to examine the consistency of results as regards efficacy and safety for various subgroups or risk groups. OBJECTIVE: To summarize results from both predefined as well as post-hoc subgroup analyses performed in the MERIT-HF trial, and to provide guidance as to whether any subgroup is at increased risk, despite an overall strongly positive effect, and to discuss the difficulties and limitations in conducting such subgroup analyses. For some subgroups we performed metaanalyses with data from the CIBIS II and COPERNICUS trials in order to obtain more robust data on mortality in subgroups with a small number of deaths (e.g. for women). SETTING: MERIT-HF was run in 14 countries, and randomized a total of 3,991 patients with symptomatic systolic heart failure (NYHA class II to IV with ejection fraction < or =0.40). Treatment was initiated with a very low dose with careful titration to a maximum target dose of 200 mg metoprolol succinate controlled release/extended release (CR/XL), or highest tolerated dose. MAIN OUTCOME MEASURES: Total mortality (first primary endpoint), total mortality plus all-cause hospitalization (second primary endpoint), and total mortality plus hospitalization for heart failure (first secondary endpoint) analyzed on a time to first event basis. RESULTS: Overall, MERIT-HF demonstrated a 34% reduction in total mortality ( p = 0.00009 nominal) and a 19% reduction for mortality plus all-cause hospitalization ( p = 0.00012). The first secondary endpoint of mortality plus hospitalization for heart failure was reduced by 31% ( p = 0.0000008). The results were remarkably consistent for both primary outcomes and the first secondary outcome across all predefined subgroups as well as nearly all post-hoc subgroups. Metoprolol CR/XL has been very well tolerated, overall as well as in all subgroups analyzed. Overall 87% of the patients reached a dose of 100 mg or more of metoprolol CR/XL once daily, and 64% reached the target dose of 200 mg once daily. CONCLUSION: Our results show that when carefully titrated, metoprolol CR/XL can safely be instituted for the overwhelming majority of outpatients with clinically stable systolic heart failure, with minimal side effects or deterioration. The time has come to overcome the barriers that physicians perceive to beta-blocker treatment, and to provide it to the large number of patients with heart failure in need of this therapy, including also high risk patients like elderly patients, patients with severe heart failure, and patients with diabetes. Because of the increased risk, these are the patients in whom treatment will have the greatest impact as shown by number of lives saved and number of hospitalizations avoided. The target dose should be strived for in all patients who tolerate this dose. We should expect some variation of the treatment effect around the overall estimate as we examine a large number of subgroups due to small sample size in subgroups and due to chance. However, we believe that the best estimate of treatment effect for any particular subgroup should be the overall effect observed in the trial.

Adrenergic beta-Antagonists↗