Sequential design of phase II-III cancer trials
STATISTICS IN MEDICINE
2012; 31 (18): 1944-1960
Although traditional phase II cancer trials are usually single arm, with tumor response as endpoint, and phase III trials are randomized and incorporate interim analyses with progression-free survival or other failure time as endpoint, this paper proposes a new approach that seamlessly expands a randomized phase II study of response rate into a randomized phase III study of time to failure. This approach is based on advances in group sequential designs and joint modeling of the response rate and time to event. The joint modeling is reflected in the primary and secondary objectives of the trial, and the sequential design allows the trial to adapt to increase in information on response and survival patterns during the course of the trial and to stop early either for conclusive evidence on efficacy of the experimental treatment or for the futility in continuing the trial to demonstrate it, on the basis of the data collected so far.
View details for DOI 10.1002/sim.5346
View details for Web of Science ID 000306471100004
View details for PubMedID 22422502
Clinical trial designs for testing biomarker-based personalized therapies
2012; 9 (2): 141-154
Advances in molecular therapeutics in the past decade have opened up new possibilities for treating cancer patients with personalized therapies, using biomarkers to determine which treatments are most likely to benefit them, but there are difficulties and unresolved issues in the development and validation of biomarker-based personalized therapies. We develop a new clinical trial design to address some of these issues. The goal is to capture the strengths of the frequentist and Bayesian approaches to address this problem in the recent literature and to circumvent their limitations.We use generalized likelihood ratio tests of the intersection null and enriched strategy null hypotheses to derive a novel clinical trial design for the problem of advancing promising biomarker-guided strategies toward eventual validation. We also investigate the usefulness of adaptive randomization (AR) and futility stopping proposed in the recent literature.Simulation studies demonstrate the advantages of testing both the narrowly focused enriched strategy null hypothesis related to validating a proposed strategy and the intersection null hypothesis that can accommodate to a potentially successful strategy. AR and early termination of ineffective treatments offer increased probability of receiving the preferred treatment and better response rates for patients in the trial, at the expense of more complicated inference under small-to-moderate total sample sizes and some reduction in power.The binary response used in the development phase may not be a reliable indicator of treatment benefit on long-term clinical outcomes. In the proposed design, the biomarker-guided strategy (BGS) is not compared to 'standard of care', such as physician's choice that may be informed by patient characteristics. Therefore, a positive result does not imply superiority of the BGS to 'standard of care'. The proposed design and tests are valid asymptotically. Simulations are used to examine small-to-moderate sample properties.Innovative clinical trial designs are needed to address the difficulties and issues in the development and validation of biomarker-based personalized therapies. The article shows the advantages of using likelihood inference and interim analysis to meet the challenges in the sample size needed and in the constantly evolving biomarker landscape and genomic and proteomic technologies.
View details for DOI 10.1177/1740774512437252
View details for Web of Science ID 000302636500001
View details for PubMedID 22397801
Adaptive Trial Designs
ANNUAL REVIEW OF PHARMACOLOGY AND TOXICOLOGY, VOL 52
2012; 52: 101-110
We review adaptive designs for clinical trials, giving special attention to the control of the Type I error in late-phase confirmatory trials, when the trial planner wishes to adjust the final sample size of the study in response to an unblinded analysis of interim estimates of treatment effects. We point out that there is considerable inefficiency in using the adaptive designs that employ conditional power calculations to reestimate the sample size and that maintain the Type I error by using certain weighted test statistics. Although these adaptive designs have little advantage over familiar group-sequential designs, our review also describes recent developments in adaptive designs that are both flexible and efficient. We also discuss the use of Bayesian designs, when the context of use demands control over operating characteristics (Type I and II errors) and correction of the bias of estimated treatment effects.
View details for DOI 10.1146/annurev-pharmtox-010611-134504
View details for Web of Science ID 000301839600006
View details for PubMedID 21838549
Radial Artery Grafts vs Saphenous Vein Grafts in Coronary Artery Bypass Surgery A Randomized Trial
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION
2011; 305 (2): 167-174
Arterial grafts are thought to be better conduits than saphenous vein grafts for coronary artery bypass grafting (CABG) based on experience with using the left internal mammary artery to bypass the left anterior descending coronary artery. The efficacy of the radial artery graft is less clear.To compare 1-year angiographic patency of radial artery grafts vs saphenous vein grafts in patients undergoing elective CABG.Multicenter, randomized controlled trial conducted from February 2003 to February 2009 at 11 Veterans Affairs medical centers among 757 participants (99% men) undergoing first-time elective CABG.The left internal mammary artery was used to preferentially graft the left anterior descending coronary artery whenever possible; the best remaining recipient vessel was randomized to radial artery vs saphenous vein graft.The primary end point was angiographic graft patency at 1 year after CABG. Secondary end points included angiographic graft patency at 1 week after CABG, myocardial infarction, stroke, repeat revascularization, and death.Analysis included 733 patients (366 in the radial artery group, 367 in the saphenous vein group). There was no significant difference in study graft patency at 1 year after CABG (radial artery, 238/266; 89%; 95% confidence interval [CI], 86%-93%; saphenous vein, 239/269; 89%; 95% CI, 85%-93%; adjusted OR, 0.99; 95% CI, 0.56-1.74; P = .98). There were no significant differences in the secondary end points.Among Veterans Affairs patients undergoing first-time elective CABG, the use of a radial artery graft compared with saphenous vein graft did not result in greater 1-year patency.clinicaltrials.gov Identifier: NCT00054847.
View details for Web of Science ID 000286103400022
View details for PubMedID 21224458
A Biosensor Platform for Rapid Antimicrobial Susceptibility Testing Directly From Clinical Samples
JOURNAL OF UROLOGY
2011; 185 (1): 148-153
A significant barrier to efficient antibiotic management of infection is that the standard diagnostic methodologies do not provide results at the point of care. The delays between sample collection and bacterial culture and antibiotic susceptibility reporting have led to empirical use of antibiotics, contributing to the emergence of drug resistant pathogens. As a key step toward the development of a point of care device for determining the antibiotic susceptibility of urinary tract pathogens, we report on a biosensor based antimicrobial susceptibility test.For assay development bacteria were cultured with or without antibiotics, and growth was quantitated by determining viable counts and electrochemical biosensor measurement of bacterial 16S rRNA. To determine antibiotic susceptibility directly from patient samples, urine was cultured on antibiotic plates for 2.5 hours and growth was determined by electrochemical measurement of bacterial 16S rRNA. For assay validation 252 urine samples were collected from patients at the Spinal Cord Injury Service at Veterans Affairs Palo Alto Health Care System. The biosensor based antimicrobial susceptibility test was completed for samples containing gram-negative organisms. Pathogen identification and antibiotic susceptibility results were compared between our assay and standard microbiological analysis.A direct biosensor quantitation of bacterial 16S rRNA can be used to monitor bacterial growth for a biosensor based antimicrobial susceptibility test. Clinical validation of a biosensor based antimicrobial susceptibility test with patient urine samples demonstrated that this test was 94% accurate in 368 pathogen-antibiotic tests compared to standard microbiological analysis.This biosensor based antimicrobial susceptibility test, in concert with our previously described pathogen identification assay, can provide culture and susceptibility information directly from a urine sample within 3.5 hours.
View details for DOI 10.1016/j.juro.2010.09.022
View details for Web of Science ID 000285141900047
View details for PubMedID 21074208
Integrating Tobacco Cessation Into Mental Health Care for Posttraumatic Stress Disorder A Randomized Controlled Trial
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION
2010; 304 (22): 2485-2493
Most smokers with mental illness do not receive tobacco cessation treatment.To determine whether integrating smoking cessation treatment into mental health care for veterans with posttraumatic stress disorder (PTSD) improves long-term smoking abstinence rates.A randomized controlled trial of 943 smokers with military-related PTSD who were recruited from outpatient PTSD clinics at 10 Veterans Affairs medical centers and followed up for 18 to 48 months between November 2004 and July 2009.Smoking cessation treatment integrated within mental health care for PTSD delivered by mental health clinicians (integrated care [IC]) vs referral to Veterans Affairs smoking cessation clinics (SCC). Patients received smoking cessation treatment within 3 months of study enrollment.Smoking outcomes included 12-month bioverified prolonged abstinence (primary outcome) and 7- and 30-day point prevalence abstinence assessed at 3-month intervals. Amount of smoking cessation medications and counseling sessions delivered were tested as mediators of outcome. Posttraumatic stress disorder and depression were repeatedly assessed using the PTSD Checklist and Patient Health Questionnaire 9, respectively, to determine if IC participation or quitting smoking worsened psychiatric status.Integrated care was better than SCC on prolonged abstinence (8.9% vs 4.5%; adjusted odds ratio, 2.26; 95% confidence interval [CI], 1.30-3.91; P = .004). Differences between IC vs SCC were largest at 6 months for 7-day point prevalence abstinence (78/472 [16.5%] vs 34/471 [7.2%], P < .001) and remained significant at 18 months (86/472 [18.2%] vs 51/471 [10.8%], P < .001). Number of counseling sessions received and days of cessation medication used explained 39.1% of the treatment effect. Between baseline and 18 months, psychiatric status did not differ between treatment conditions. Posttraumatic stress disorder symptoms for quitters and nonquitters improved. Nonquitters worsened slightly on the Patient Health Questionnaire 9 relative to quitters (differences ranged between 0.4 and 2.1, P = .03), whose scores did not change over time.Among smokers with military-related PTSD, integrating smoking cessation treatment into mental health care compared with referral to specialized cessation treatment resulted in greater prolonged abstinence.clinicaltrials.gov Identifier: NCT00118534.
View details for Web of Science ID 000285053300022
View details for PubMedID 21139110
Sequential generalized likelihood ratio tests for vaccine safety evaluation
STATISTICS IN MEDICINE
2010; 29 (26): 2698-2708
The evaluation of vaccine safety involves pre-clinical animal studies, pre-licensure randomized clinical trials, and post-licensure safety studies. Sequential design and analysis are of particular interest because they allow early termination of the trial or quick detection that the vaccine exceeds a prescribed bound on the adverse event rate. After a review of the recent developments in this area, we propose a new class of sequential generalized likelihood ratio tests for evaluating adverse event rates in two-armed pre-licensure clinical trials and single-armed post-licensure studies. The proposed approach is illustrated using data from the Rotavirus Efficacy and Safety Trial. Simulation studies of the performance of the proposed approach and other methods are also given.
View details for DOI 10.1002/sim.4036
View details for Web of Science ID 000284023800004
View details for PubMedID 20799244
Effect of Home Testing of International Normalized Ratio on Clinical Events.
NEW ENGLAND JOURNAL OF MEDICINE
2010; 363 (17): 1608-1620
Warfarin anticoagulation reduces thromboembolic complications in patients with atrial fibrillation or mechanical heart valves, but effective management is complex, and the international normalized ratio (INR) is often outside the target range. As compared with venous plasma testing, point-of-care INR measuring devices allow greater testing frequency and patient involvement and may improve clinical outcomes.We randomly assigned 2922 patients who were taking warfarin because of mechanical heart valves or atrial fibrillation and who were competent in the use of point-of-care INR devices to either weekly self-testing at home or monthly high-quality testing in a clinic. The primary end point was the time to a first major event (stroke, major bleeding episode, or death).The patients were followed for 2.0 to 4.75 years, for a total of 8730 patient-years of follow-up. The time to the first primary event was not significantly longer in the self-testing group than in the clinic-testing group (hazard ratio, 0.88; 95% confidence interval, 0.75 to 1.04; P=0.14). The two groups had similar rates of clinical outcomes except that the self-testing group reported more minor bleeding episodes. Over the entire follow-up period, the self-testing group had a small but significant improvement in the percentage of time during which the INR was within the target range (absolute difference between groups, 3.8 percentage points; P<0.001). At 2 years of follow-up, the self-testing group also had a small but significant improvement in patient satisfaction with anticoagulation therapy (P=0.002) and quality of life (P<0.001).As compared with monthly high-quality clinic testing, weekly self-testing did not delay the time to a first stroke, major bleeding episode, or death to the extent suggested by prior studies. These results do not support the superiority of self-testing over clinic testing in reducing the risk of stroke, major bleeding episode, and death among patients taking warfarin therapy. (Funded by the Department of Veterans Affairs Cooperative Studies Program; ClinicalTrials.gov number, NCT00032591.).
View details for Web of Science ID 000283242700005
View details for PubMedID 20961244
Electrochemical immunosensor detection of urinary lactoferrin in clinical samples for urinary tract infection diagnosis
BIOSENSORS & BIOELECTRONICS
2010; 26 (2): 649-654
Urine is the most abundant and easily accessible of all body fluids and provides an ideal route for non-invasive diagnosis of human diseases, particularly of the urinary tract. Electrochemical biosensors are well suited for urinary diagnostics due to their excellent sensitivity, low-cost, and ability to detect a wide variety of target molecules including nucleic acids and protein biomarkers. We report the development of an electrochemical immunosensor for direct detection of the urinary tract infection (UTI) biomarker lactoferrin from infected clinical samples. An electrochemical biosensor array with alkanethiolate self-assembled monolayer (SAM) was used. Electrochemical impedance spectroscopy was used to characterize the mixed SAM, consisted of 11-mercaptoundecanoic acid and 6-mercapto-1-hexanol. A sandwich amperometric immunoassay was developed for detection of lactoferrin from urine, with a detection limit of 145 pg/ml. We validated lactoferrin as a biomarker of pyuria (presence of white blood cells in urine), an important hallmark of UTI, in 111 patient-derived urine samples. Finally, we demonstrated multiplex detection of urinary pathogens and lactoferrin through simultaneous detection of bacterial nucleic acid (16S rRNA) and host immune response protein (lactoferrin) on a single sensor array. Our results represent first integrated sensor platform capable of quantitative pathogen identification and measurement of host immune response, potentially providing clinical diagnosis that is not only more expeditious but also more informative than the current standard.
View details for DOI 10.1016/j.bios.2010.07.002
View details for Web of Science ID 000283804400056
View details for PubMedID 20667707
An evaluation of patient self-testing competency of prothrombin time for managing anticoagulation: pre-randomization results of VA Cooperative Study #481-The Home INR Study (THINRS)
JOURNAL OF THROMBOSIS AND THROMBOLYSIS
2010; 30 (3): 263-275
Prior studies suggest patient self-testing (PST) of prothrombin time (PT) can improve the quality of anticoagulation (AC) and reduce complications (e.g., bleeding and thromboembolic events). "The Home INR Study" (THINRS) compared AC management with frequent PST using a home monitoring device to high-quality AC management (HQACM) with clinic-based monitoring on major health outcomes. A key clinical and policy question is whether and which patients can successfully use such devices. We report the results of Part 1 of THINRS in which patients and caregivers were evaluated for their ability to perform PST. Study-eligible patients (n = 3643) were trained to use the home monitoring device and evaluated after 2-4 weeks for PST competency. Information about demographics, medical history, warfarin use, medications, plus measures of numeracy, literacy, cognition, dexterity, and satisfaction with AC were collected. Approximately 80% (2931 of 3643) of patients trained on PST demonstrated competency; of these, 8% (238) required caregiver assistance. Testers who were not competent to perform PST had higher numbers of practice attempts, higher cuvette wastage, and were less able to perform a fingerstick or obtain blood for the cuvette in a timely fashion. Factors associated with failure to pass PST training included increased age, previous stroke history, poor cognition, and poor manual dexterity. A majority of patients were able to perform PST. Successful home monitoring of PT with a PST device required adequate levels of cognition and manual dexterity. Training a caregiver modestly increased the proportion of patients who can perform PST.
View details for DOI 10.1007/s11239-010-0499-8
View details for Web of Science ID 000282215300002
View details for PubMedID 20628787
Effects of the Thyromimetic Agent Diiodothyropropionic Acid on Body Weight, Body Mass Index, and Serum Lipoproteins: A Pilot Prospective, Randomized, Controlled Study
JOURNAL OF CLINICAL ENDOCRINOLOGY & METABOLISM
2010; 95 (3): 1349-1354
Context: Widespread thyroid hormone actions offer the possibility of developing selective thyromimetic analogs with salutary metabolic properties. Consequently, effects of diiodothyropropionic acid (DITPA) on body weight, serum lipoproteins, and bone metabolism markers were studied in a prospective, controlled, double-blind 24-wk trial, which was primarily designed to assess treatment of stable chronic heart failure. Design: Eighty-six patients (aged 66 +/- 11 yr, mean +/- sd) were randomized (1:2) to placebo or an escalating DITPA dose (90 to 180, 270, and 360 mg/d) over 8 wk until serum TSH was less than 0.02 mU/liter. Patients were studied at 2, 4, 6, 8, 16, and 24 wk and after 4 wk off study drug. Only 21 DITPA-treated and 27 placebo patients completed the full 24 wk of therapy. Results: DITPA therapy lowered serum TSH levels and, to a lesser extent, serum T(3) and T(4), but there were no differences in clinical manifestations of thyrotoxicosis or hypothyroidism. Serum total and low-density lipoprotein cholesterol levels both decreased on DITPA; there was a transient decrease in triglycerides and no change in high-density lipoprotein cholesterol. DITPA therapy was associated with significant reduction in body weight, 12.5 lb at 24 wk. Increases in serum osteocalcin, N-telopeptide, and deoxypyridinoline levels were consistent with increased bone turnover on DITPA. Conclusion: This investigation of DITPA actions demonstrated its efficacy in reducing body weight and lowering total and low-density lipoprotein cholesterol levels. However, DITPA's adverse effects at doses used resulted in a high dropout rate and potentially dangerous skeletal actions were observed.
View details for DOI 10.1210/jc.2009-1209
View details for Web of Science ID 000275197500045
View details for PubMedID 20080837
Defining acute lung disease in children with the oxygenation saturation index
PEDIATRIC CRITICAL CARE MEDICINE
2010; 11 (1): 12-17
To evaluate whether a formula could be derived using oxygen saturation (Spo2) to replace Pao2 that would allow identification of children with acute lung injury and acute respiratory distress syndrome. Definitions of acute lung injury and acute respiratory distress syndrome require arterial blood gases to determine the Pao2/Fio2 ratio of 300 (acute lung injury) and 200 (acute respiratory distress syndrome).Post hoc data analysis of measurements abstracted from two prospective databases of randomized controlled trials.Academic pediatric intensive care units.A total of 255 children enrolled in two large prospective trials of therapeutic intervention for acute lung disease: calfactant and prone positioning.Data were abstracted including Pao2, Paco2, pH, Fio2, and mean airway pressure. Repeated-measures analyses, using linear mixed-effects models, were used to build separate prediction equations for the Spo2/Fio2 ratio, oxygenation index [(Fio2 x Mean Airway Pressure)/Pao2], and oxygen saturation index [(Fio2 x Mean Airway Pressure)/Spo2 ]. A generalization of R was used to measure goodness-of-fit. Generalized estimating equations with a logit link were used to calculate the sensitivity and specificity for the cutoffs of Pao2/Fio2 ratio of 200 and 300 and equivalent values of Spo2/Fio2 ratio, oxygenation index, and oxygen saturation index.An Spo2/Fio2 ratio of 253 and 212 would equal criteria for acute lung injury and acute respiratory distress syndrome, respectively. An oxygenation index of 5.3 would equal acute lung injury criteria, and an oxygenation index of 8.1 would qualify for acute respiratory distress syndrome. An oxygen saturation index, which includes the mean airway pressure and the noninvasive measure of oxygenation, of 6.5 would be equivalent to the acute lung injury criteria, and an oxygen saturation index of 7.8 would equal acute respiratory distress syndrome criteria.Noninvasive methods of assessing oxygenation may be utilized with reasonable sensitivity and specificity to define acute lung injury and acute respiratory distress syndrome, and, with prospective validation, have the potential to increase the number of children enrolled into clinical trials.
View details for DOI 10.1097/PCC.0b013e3181b0653d
View details for Web of Science ID 000273401800003
View details for PubMedID 19561556
- Tests and confidence intervals for secondary endpoints in sequential clinical trials BIOMETRIKA 2009; 96 (4): 903-915
Multiplex Pathogen Identification for Polymicrobial Urinary Tract Infections Using Biosensor Technology: A Prospective Clinical Study
JOURNAL OF UROLOGY
2009; 182 (6): 2735-2741
Rapid diagnosis of urinary tract infection would have a significant beneficial impact on clinical management, particularly in patients with structural or functional urinary tract abnormalities who are highly susceptible to recurrent polymicrobial infections. We examined the analytical validity of an electrochemical biosensor array for rapid molecular diagnosis of urinary tract infection in a prospective clinical study in patients with neurogenic bladder.The electrochemical biosensor array was functionalized with DNA probes against 16S rRNA of the most common uropathogens. Spinal cord injured patients at a Veterans Affairs hospital were recruited into the study. Urine samples were generally tested on the biosensor within 1 to 2 hours of collection. Biosensor results were compared with those obtained using standard clinical microbiology laboratory methods.We successfully developed a 1-hour biosensor assay for multiplex identification of pathogens. From July 2007 to December 2008 we recruited 116 patients, yielding a total of 109 urine samples suitable for analysis and comparison between biosensor assay and standard urine culture. Of the samples 74% were positive, of which 42% were polymicrobial. We identified 20 organisms, of which Escherichia coli, Pseudomonas aeruginosa and Enterococcus species were the most common. Biosensor assay specificity and positive predictive value were 100%. Pathogen detection sensitivity was 89%, yielding a 76% negative predictive value.To our knowledge we report the first prospective clinical study to successfully identify pathogens within a point of care time frame using an electrochemical biosensor platform. Additional efforts to improve the limit of detection and probe design are needed to further enhance assay sensitivity.
View details for DOI 10.1016/j.juro.2009.08.028
View details for Web of Science ID 000271668600072
View details for PubMedID 19837423
Effect of the MTHFR C677T and A1298C Polymorphisms on Survival in Patients With Advanced CKD and ESRD: A Prospective Study
AMERICAN JOURNAL OF KIDNEY DISEASES
2009; 53 (5): 779-789
Abnormalities in the gene regulating methylenetetrahydrofolate reductase (MTHFR) are associated with increased homocysteine levels and increased mortality in normal and chronic kidney disease (CKD) populations.Gene association study.This was a substudy of 677 patients from 21 Veterans Affairs medical centers participating in a randomized clinical trial (Homocysteinemia in Kidney and End-Stage Renal Disease [HOST]) of the effect on all-cause mortality of vitamin-induced lowering of plasma homocysteine levels. Of 677 patients, 213 (31%) were treated by using dialysis (end-stage renal disease [ESRD]) and 464 (69%) had a Cockcroft-Gault estimated creatinine clearance less than 30 mL/min (advanced CKD).Polymorphisms C677T (rs1801133) and A1298C (rs1801131) of the MTHFR gene.Unadjusted and adjusted all-cause mortality.DNA was extracted from blood samples and amplified by means of polymerase chain reaction.The adjusted hazard ratio in a recessive model of the relationship between the C677T polymorphism and all-cause mortality in all patients was 1.47 (95% confidence interval, 1.00 to 2.16; P = 0.05). In patients with ESRD with the mutant TT genotype, the adjusted hazard ratio for mortality in all patients was 2.27 (95% confidence interval, 1.07 to 4.84; P = 0.03); patients with advanced CKD showed a similar, although not significant, trend. The risk of myocardial infarction (P = 0.05) and composite risk of myocardial infarction, stroke, lower-extremity amputation, and mortality (P = 0.02) were greater in patients with ESRD with the mutant T allele at nucleotide 677. The overall relationship between the A1298C polymorphism and mortality was not significant (P = 0.6).Participants were 98% men; DNA samples were not obtained at enrollment in HOST; linkage disequilibrium with another causal polymorphism is a potential confounding factor; and power was reduced by the limited number of participants.These findings provide additional support for the hypothesis that the mutant TT genotype at nucleotide 677 of the gene regulating MTHFR activity may increase the mortality risk in patients with ESRD.
View details for DOI 10.1053/j.ajkd.2008.12.023
View details for Web of Science ID 000265923500010
View details for PubMedID 19272686
Designed extension of survival studies: Application to clinical trials with unrecognized heterogeneity
2007; 17 (4): 1567-1589
View details for Web of Science ID 000250888200017
Maternal perspectives on children's health-related quality of life during the first year after pediatric hematopoietic stem cell transplant
JOURNAL OF PEDIATRIC PSYCHOLOGY
2006; 31 (10): 1100-1115
To assess the longitudinal health-related quality of life (HRQL) of children receiving hematopoietic stem cell transplantation (HSCT).Mothers (N = 160) of HSCT recipients aged 5-20 at six US transplant centers completed the Child Health Ratings Inventories (CHRIs), the Disease Impairment Inventory (DSII)-HSCT module, and the Short Form (SF)-36 at baseline, 3, 6, and 12 months.HRQL domain scores at baseline varied by recipient age and program site. Longitudinal data over the first year post-HSCT revealed lowest functioning at baseline and 3 months, with largest improvement in functioning between the 3 and 6-months assessments and continued improvement from 6 to 12 months. Recipients of unrelated donor transplants had steepest declines in functioning at 3 months and great HSCT-specific issues at 3 and 6 months. Among children who survived the first year, functioning at 12 months was similar across transplant types and surpassed baseline scores. Children who did not survive the first year exhibited deterioration in HRQL in the months before death and trajectories were strikingly different than for survivors.This study offers the first glimpse of the 12-month trajectory of HRQL following pediatric HSCT from mothers' perspectives. This study also highlights the importance of and approaches to addressing missing data in longitudinal research.
View details for DOI 10.1093/jpepsy/jsj078
View details for Web of Science ID 000241955500009
View details for PubMedID 16150874
Modified Haybittle-Peto group sequential designs for testing superiority and non-inferiority hypotheses in clinical trials
STATISTICS IN MEDICINE
2006; 25 (7): 1149-1167
In designing an active controlled clinical trial, one sometimes has to choose between a superiority objective (to demonstrate that a new treatment is more effective than an active control therapy) and a non-inferiority objective (to demonstrate that it is no worse than the active control within some pre-specified non-inferiority margin). It is often difficult to decide which study objective should be undertaken at the planning stage when one does not have actual data on the comparative advantage of the new treatment. By making use of recent advances in the theory of efficient group sequential tests, we show how this difficulty can be resolved by a flexible group sequential design that can adaptively choose between the superiority and non-inferiority objectives during interim analyses. While maintaining the type I error probability at a pre-specified level, the proposed test is shown to have power advantage and/or sample size saving over fixed sample size tests for either only superiority or non-inferiority, and over other group sequential designs in the literature.
View details for DOI 10.1002/sim.2357
View details for Web of Science ID 000236528500005
View details for PubMedID 16189814
Flexible modeling via a hybrid estimation scheme in generalized mixed models for longitudinal data
2006; 62 (1): 159-167
To circumvent the computational complexity of likelihood inference in generalized mixed models that assume linear or more general additive regression models of covariate effects, Laplace's approximations to multiple integrals in the likelihood have been commonly used without addressing the issue of adequacy of the approximations for individuals with sparse observations. In this article, we propose a hybrid estimation scheme to address this issue. The likelihoods for subjects with sparse observations use Monte Carlo approximations involving importance sampling, while Laplace's approximation is used for the likelihoods of other subjects that satisfy a certain diagnostic check on the adequacy of Laplace's approximation. Because of its computational tractability, the proposed approach allows flexible modeling of covariate effects by using regression splines and model selection procedures for knot and variable selection. Its computational and statistical advantages are illustrated by simulation and by application to longitudinal data from a fecundity study of fruit flies, for which overdispersion is modeled via a double exponential family.
View details for DOI 10.1111/j.1541-0420.2005.00391.x
View details for Web of Science ID 000236315400021
View details for PubMedID 16542242
A new approach to modeling covariate effects and individualization in population pharmacokinetics-pharmacodynamics
JOURNAL OF PHARMACOKINETICS AND PHARMACODYNAMICS
2006; 33 (1): 49-74
By combining Laplace's approximation and Monte Carlo methods to evaluate multiple integrals, this paper develops a new approach to estimation in nonlinear mixed effects models that are widely used in population pharmacokinetics and pharmacodynamics. Estimation here involves not only estimating the model parameters from Phase I and II studies but also using the fitted model to estimate the concentration versus time curve or the drug effects of a subject who has covariate information but sparse measurements. Because of its computational tractability, the proposed approach can model the covariate effects nonparametrically by using (i) regression splines or neural networks as basis functions and (ii) AIC or BIC for model selection. Its computational and statistical advantages are illustrated in simulation studies and in Phase I trials.
View details for DOI 10.1007/s10928-005-9000-2
View details for Web of Science ID 000236842900003
View details for PubMedID 16402288
Power, sample size and adaptation considerations in the design of group sequential clinical trials
2004; 91 (3): 507-528
View details for Web of Science ID 000224077700001
A hybrid estimator in nonlinear and generalised linear mixed effects models
2003; 90 (4): 859-879
View details for Web of Science ID 000187321500008
Nonparametric estimation in nonlinear mixed effects models
2003; 90 (1): 1-13
View details for Web of Science ID 000181996800001
Tests for genetic association using family data
2002; 22 (2): 128-145
We use likelihood-based score statistics to test for association between a disease and a diallelic polymorphism, based on data from arbitrary types of nuclear families. The Nonfounder statistic extends the transmission disequilibrium test (TDT) to accommodate affected and unaffected offspring, missing parental genotypes, phenotypes more general than qualitative traits, such as censored survival data and quantitative traits, and residual correlation of phenotypes within families. The Founder statistic compares observed or inferred parental genotypes to those expected in the general population. Here the genotypes of affected parents and those with many affected offspring are weighted more heavily than unaffected parents and those with few affected offspring. We illustrate the tests by applying them to data on a polymorphism of the SRD5A2 gene in nuclear families with multiple cases of prostate cancer. We also use simulations to compare the power of these family-based statistics to that of the score statistic based on Cox's partial likelihood for censored survival data, and find that the family-based statistics have considerably more power when there are many untyped parents. The software program FGAP for computing test statistics is available at http://www.stanford.edu/dept/HRP/epidemiology/FGAP.
View details for Web of Science ID 000173390200003
View details for PubMedID 11788959
Allele-sharing among affected relatives: non-parametric methods for identifying genes
STATISTICAL METHODS IN MEDICAL RESEARCH
2001; 10 (1): 27-55
Non-parametric linkage analysis examines similarities among affected relatives in alleles of one or more genetic markers (pieces of DNA at known locations on a chromosome). The objective is to evaluate departures from the null hypothesis that the markers are not near a disease gene. Under the null hypothesis, Mendel's laws give the probabilities that a set of relatives exhibits a particular allele-sharing pattern, and the null hypothesis is rejected if the extent of allele sharing among affected relatives exceeds Mendelian expectation. Because the rationale for allele-sharing methods is intuitively plausible and easily grasped, geneticists have used these methods for more than 30 years, well before the advent of the large sets of polymorphic markers that have made linkage analysis so fruitful today. Here we describe methods for assessing whether the extent of marker allele sharing among affected relatives exceeds Mendelian expectation. We first quantify the notion of allele sharing and the probabilities of allele sharing in various sets of relatives. Then we describe allele sharing methods for affected sibs and more general sets of relatives. We also discuss related issues of test size and power. We conclude with a brief discussion of areas in need of further research.
View details for Web of Science ID 000168123300003
View details for PubMedID 11329690