PubMed Health⌕ Search

Biomedical subjects

John M Lachin

Publications and source records attributed to John M Lachin.

11 recordsLinked to original sources
PubMed2005

A review of methods for futility stopping based on conditional power.

Conditional power (CP) is the probability that the final study result will be statistically significant, given the data observed thus far and a specific assumption about the pattern of the data to be observed in the remainder of the study, such as assuming the original design effect, or the effect estimated from the current data, or under the null hypothesis. In many clinical trials, a CP computation at a pre-specified point in the study, such as mid-way, is used as the basis for early termination for futility when there is little evidence of a beneficial effect. Brownian motion can be used to describe the distribution of the interim Z-test value, the corresponding B-value, and the CP values under a specific assumption about the future data. A stopping boundary on the CP value specifies an equivalent boundary on the B-value from which the probability of stopping for futility can then be computed based on the planned study design (sample size and duration) and the assumed true effect size. This yields expressions for the total type I and II error probabilities. As the probability of stopping increases, the probability of a type I error alpha decreases from the nominal desired level (e.g. 0.05) while the probability of a type II error beta increases from the level specified in the study design. Thus a stopping boundary on the B-value can be determined such that the inflation in type II error probability is controlled at a desired level. An iterative procedure is also described that determines a stopping boundary on the B-value and a final test critical Z-value with specified type I and II error probabilities. The implementation in conjunction with a group sequential analysis for effectiveness is also described.

Biometry↗
PubMed2004

Conflicts of interest in data monitoring of industry versus publicly financed clinical trials.

The FDA Guidance, while highly appropriate for industry sponsored trials, need not be imposed on publicly (e.g. NIH) financed clinical trials. While the potential for conflicts of interest exist in the latter, they are in general manageable and pose an acceptable low risk of threatening the integrity of a study. However, the Guidance should heighten the awareness of all investigators in public trials to the potential for the appearance of conflicts and to the need for full and open participation in the management of dualities of interest.

Clinical Trials Data Monitoring Committees↗
PubMed2004

C-peptide is the appropriate outcome measure for type 1 diabetes clinical trials to preserve beta-cell function: report of an ADA workshop, 21-22 October 2001.

The underlying cause of type 1 diabetes, loss of beta-cell function, has become the therapeutic target for a number of interventions in patients with type 1 diabetes. Even though insulin therapies continue to improve, it remains difficult to achieve normal glycemic control in type 1 diabetes, especially long term. The associated risks of hypoglycemia and end-organ diabetic complications remain. Retention of beta-cell function in patients with type 1 diabetes is known to result in improved glycemic control and reduced hypoglycemia, retinopathy, and nephropathy. To facilitate the development of therapies aimed at altering the type 1 diabetes disease process, an American Diabetes Association workshop was convened to identify appropriate efficacy outcome measures in type 1 diabetes clinical trials. The following consensus emerged: While measurements of immune responses to islet cells are important in elucidating pathogenesis, none of these measures have directly correlated with the decline in endogenous insulin secretion. HbA(1c) is a highly valuable clinical measure of glycemic control, but it is an insensitive measure of beta-cell function, particularly with the currently accepted standard of near-normal glycemic control. Rates of severe hypoglycemia and diabetic complications ultimately will be improved by therapies that are effective at preserving beta-cell function but as primary outcomes require inordinately large and protracted trials. Endogenous insulin secretion is assessed best by measurement of C-peptide, which is cosecreted with insulin in a one-to-one molar ratio but unlike insulin experiences little first pass clearance by the liver. Measurement of C-peptide under standardized conditions provides a sensitive, well accepted, and clinically validated assessment of beta-cell function. C-peptide measurement is the most suitable primary outcome for clinical trials of therapies aimed at preserving or improving endogenous insulin secretion in type 1 diabetes patients. Available data demonstrate that even relatively modest treatment effects on C-peptide will result in clinically meaningful benefits. The development of therapies for addressing this important unmet clinical need will be facilitated by trials that are carefully designed with beta-cell function as determined by C-peptide measurement as the primary efficacy outcome.

C-Peptide↗
PubMed2003

Over-ruling a group sequential boundary--a stopping rule versus a guideline.

We evaluate the properties of group sequential procedures where the trial is continued even though the boundary for statistical significance (stopping) to demonstrate effectiveness has been crossed. In this case, one may buy-back the previously spent alpha probability to be re-spent or re-distributed at future looks. We show that such plans using an O'Brien-Fleming-like spending function have a negligible effect on the final type I error probability and on the ultimate power of the study. With a Pocock-like bound, however, there is a small additional loss in power. We also show that this approach can be simplified by using a fixed-sample size Z critical value for future looks after buying-back previously spent alpha, such as using a critical Z value of 1.96 for alpha=0.025. We show that this procedure preserves the type I error probability while incurring a minimal loss in power. In this sense, one still has a stopping boundary rather than simply a guideline. This concept is discussed relative to monitoring procedures for inferiority or futility, and cases where both an upper and lower boundary are employed.

Biometry↗
PubMed2003

Group sequential large sample T2-like chi2 tests for multivariate observations.

In many studies, a K degree of freedom large sample chi2 test is used to assess the effect of treatment on a multivariate response, such as an omnibus T2-like test of a difference between two treatment groups in any of K repeated measures. Alternately, a K df chi2 test may be used to test the equality of K+1 groups in a single outcome measure. Jennison and Turnbull (Biometrika 1991; 78: 133-141) describe group sequential chi2 and F-tests for normal errors linear models, and Proschan, Follmann and Geller (Statist. Med. 1994; 13: 1441-1452) describe group sequential tests for K+1 group comparisons. These methods apply to sequences of statistics that can be characterized as having an independent increments variance-covariance structure, thus simplifying the computation of the sequential variance-covariance matrix and the resulting sequential test boundaries. However, many commonly used statistics do not share this structure, including a Liang-Zeger (Biometrika 1986; 73: 13-22) GEE longitudinal analysis with an independence working correlation structure and a Wei-Lachin (J. Amer. Statist. Assoc. 1984; 79: 653-661) multivariate Wilcoxon rank test, among others. For such analyses, this paper describes the computation of group sequential boundaries for the interim analysis of emerging results using K df tests that are expressed as quadratic forms in a statistics vector that is distributed as multivariate normal, at least asymptotically. We derive the elements of the covariance matrix of multiple successive K df chi2 statistics based on established theorems on the distribution of quadratic forms. This covariance matrix is estimated by augmenting the data from the successive interim analyses into a single analysis from which the component sequential tests and their variance-covariance matrix can then be extracted. Boundary values for the sequential statistics can then be computed using the method of Slud and Wei (J. Amer. Statist. Assoc. 1982; 77: 862-868) or using the alpha-spending function of Lan and DeMets (Biometrika 1983; 70: 659-663) with a surrogate measure of information. An example is presented using the analysis of repeated cholesterol measurements in a clinical trial.

Biometry↗
PubMed2003

Costs associated with the primary prevention of type 2 diabetes mellitus in the diabetes prevention program.

OBJECTIVE: To describe the costs of the Diabetes Prevention Program (DPP) interventions to prevent or delay type 2 diabetes. RESEARCH DESIGN AND METHODS: We describe the direct medical costs, direct nonmedical costs, and indirect costs of the placebo, metformin, and intensive lifestyle interventions over the 3-year study period of the DPP. Resource use and cost are summarized from the perspective of a large health system and society. Research costs are excluded. RESULTS: The direct medical cost of laboratory tests to identify one subject with impaired glucose tolerance (IGT) was $139. Over 3 years, the direct medical costs of the interventions were $79 per participant in the placebo group, $2,542 in the metformin group, and $2,780 in the lifestyle group. The direct medical costs of care outside the DPP were $272 less per participant in the metformin group and $432 less in the lifestyle group compared with the placebo group. Direct nonmedical costs were $9 less per participant in the metformin group and $1,445 greater in the lifestyle group compared with the placebo group. Indirect costs were $230 greater per participant in the metformin group and $174 less in the lifestyle group compared with the placebo group. From the perspective of a health system, the cost of the metformin intervention relative to the placebo intervention was $2,191 per participant and the cost of the lifestyle intervention was $2,269 per participant over 3 years. From the perspective of society, the cost of the metformin intervention relative to the placebo intervention was $2,412 per participant and the cost of the lifestyle intervention was $3,540 per participant over 3 years. CONCLUSIONS: The metformin and lifestyle interventions are associated with modest incremental costs compared with the placebo intervention. The evaluation of costs relative to health benefits will determine the value of these interventions to health systems and society.

Diabetes Mellitus, Type 2↗
PubMed2002

Reduction in the incidence of type 2 diabetes with lifestyle intervention or metformin.

BACKGROUND: Type 2 diabetes affects approximately 8 percent of adults in the United States. Some risk factors--elevated plasma glucose concentrations in the fasting state and after an oral glucose load, overweight, and a sedentary lifestyle--are potentially reversible. We hypothesized that modifying these factors with a lifestyle-intervention program or the administration of metformin would prevent or delay the development of diabetes. METHODS: We randomly assigned 3234 nondiabetic persons with elevated fasting and post-load plasma glucose concentrations to placebo, metformin (850 mg twice daily), or a lifestyle-modification program with the goals of at least a 7 percent weight loss and at least 150 minutes of physical activity per week. The mean age of the participants was 51 years, and the mean body-mass index (the weight in kilograms divided by the square of the height in meters) was 34.0; 68 percent were women, and 45 percent were members of minority groups. RESULTS: The average follow-up was 2.8 years. The incidence of diabetes was 11.0, 7.8, and 4.8 cases per 100 person-years in the placebo, metformin, and lifestyle groups, respectively. The lifestyle intervention reduced the incidence by 58 percent (95 percent confidence interval, 48 to 66 percent) and metformin by 31 percent (95 percent confidence interval, 17 to 43 percent), as compared with placebo; the lifestyle intervention was significantly more effective than metformin. To prevent one case of diabetes during a period of three years, 6.9 persons would have to participate in the lifestyle-intervention program, and 13.9 would have to receive metformin. CONCLUSIONS: Lifestyle changes and treatment with metformin both reduced the incidence of diabetes in persons at high risk. The lifestyle intervention was more effective than metformin.

Adult↗
PubMed2002

A diabetes outcome progression trial (ADOPT): an international multicenter study of the comparative efficacy of rosiglitazone, glyburide, and metformin in recently diagnosed type 2 diabetes.

OBJECTIVE: Therapies with metformin, sulfonylureas, or insulin improve glycemic control in the short term but do not prevent progressive islet beta-cell failure or long-term deterioration in glycemia. Our goal was to evaluate, in patients recently diagnosed with type 2 diabetes (<3 years), the long-term efficacy of monotherapy with rosiglitazone on glycemic control and on the progression of pathophysiological abnormalities associated with type 2 diabetes as compared with metformin or glyburide monotherapy. RESEARCH DESIGN AND METHODS: A Diabetes Outcome Progression Trial (ADOPT) is a randomized, double-blind, parallel-group study consisting of a screening visit, a 4-week placebo run-in, a 4-year treatment period, and an observational follow-up of approximately 3,600 drug-naïve patients with type 2 diabetes diagnosed within the previous 3 years. After run-in, patients will be randomized to rosiglitazone, glyburide, or metformin titrated to the maximum effective daily doses (8 mg rosiglitazone, 15 mg glyburide, or 2 g metformin). The primary outcome is time to monotherapy failure, defined as the time following titration to the maximal effective or tolerated dose when fasting plasma glucose exceeds 180 mg/dl (10 mmol/l). Secondary outcomes include measures of islet beta-cell function, insulin sensitivity, dyslipidemia, changes in urinary albumin excretion, plasminogen activator inhibitor-1 antigen, fibrinogen, and C-reactive protein. Safety and tolerability will also be evaluated. Patient-reported outcomes and resource utilization data will be collected and analyzed. CONCLUSIONS: ADOPT will provide data on the effect of mechanistically differing treatment options on metabolic control, beta-cell function, and markers of macrovascular disease risk in type 2 diabetes.

Albuminuria↗
PubMed2000

Retinopathy and nephropathy in patients with type 1 diabetes four years after a trial of intensive therapy.

BACKGROUND: Among patients with type 1 diabetes mellitus, intensive therapy (with the aim of achieving near-normal blood glucose and glycosylated hemoglobin concentrations [hemoglobin A1c]) markedly reduces the risk of microvascular complications as compared with conventional therapy. To assess whether these benefits persist, we compared the effects of former and intensive conventional therapy on the recurrence and severity of retinopathy and nephropathy for four years after the end of the Diabetes Control and Complications Trial (DCCT). METHODS: At the end of the DCCT, the patients in the conventional-therapy group were offered intensive therapy, and the care of all patients was transferred to their own physicians. Retinopathy was evaluated on the basis of centrally graded fundus photographs in 1208 patients during the fourth year after the DCCT ended, and nephropathy was evaluated on the basis of urine specimens obtained from 1302 patients during the third or fourth year, approximately half of whom were from each treatment group. RESULTS: The difference in the median glycosylated hemoglobin values between the conventional-therapy and intensive-therapy groups during the 6.5 years of the DCCT (average, 9.1 percent and 7.2 percent, respectively) narrowed during follow-up (median during 4 years, 8.2 percent and 7.9 percent, respectively, P<0.001). Nevertheless, the proportion of patients who had worsening retinopathy, including proliferative retinopathy, macular edema, and the need for laser therapy, was lower in the intensive-therapy group than in the conventional-therapy group (odds reduction, 72 percent to 87 percent, P<0.001). The proportion of patients with an increase in urinary albumin excretion was significantly lower in the intensive-therapy group. CONCLUSIONS: The reduction in the risk of progressive retinopathy and nephropathy resulting from intensive therapy in patients with type 1 diabetes persists for at least four years, despite increasing hyperglycemia.

Adolescent↗