Remdesivir for the Prevention of Invasive Mechanical Ventilation or Death in Coronavirus Disease 2019 (COVID-19): A Post Hoc Analysis of the Adaptive COVID-19 Treatment Trial-1 Cohort Data.

This post hoc analysis of the Adaptive Coronavirus Disease 2019 (COVID-19) Treatment Trial-1 (ACTT-1) shows a treatment effect of remdesivir (RDV) on progression to invasive mechanical ventilation (IMV) or death. Additionally, we create a risk profile that better predicts progression than baseline oxygen requirement alone. The highest risk group derives the greatest treatment effect from RDV.

Deconstructing the Treatment Effect of Remdesivir in the Adaptive Coronavirus Disease 2019 (COVID-19) Treatment Trial-1: Implications for Critical Care Resource Utilization.

BACKGROUND: The Adaptive Coronavirus Disease 2019 (COVID-19) Treatment Trial-1 (ACTT-1) found that remdesivir therapy hastened recovery in patients hospitalized with COVID-19, but the pathway for this improvement was not explored. We investigated how the dynamics of clinical progression changed along 4 pathways: recovery, improvement in respiratory therapy requirement, deterioration in respiratory therapy requirement, and death. METHODS: We analyzed trajectories of daily ordinal severity scores reflecting oxygen requirements of 1051 patients hospitalized with COVID-19 who participated in ACTT-1. We developed competing risks models that estimate the effect of remdesivir therapy on cumulative incidence of clinical improvement and deterioration, and multistate models that utilize the entirety of each patient's clinical course to characterize the effect of remdesivir on progression along the 4 pathways above. RESULTS: Based on a competing risks analysis, remdesivir reduced clinical deterioration (hazard ratio [HR], 0.73; 95% confidence interval [CI]: .59-.91) and increased clinical improvement (HR, 1.22; 95% CI: 1.08, 1.39) relative to baseline. Our multistate models indicate that remdesivir inhibits worsening to ordinal scores of greater clinical severity among patients on room air or low-flow oxygen (HR, 0.74; 95% CI: .57-.94) and among patients receiving mechanical ventilation or high-flow oxygen/noninvasive positive-pressure ventilation (HR, 0.73; 95% CI: .53-1.00) at baseline. We also find that remdesivir reduces expected intensive care respiratory therapy utilization among patients not mechanically ventilated at baseline. CONCLUSIONS: Remdesivir speeds time to recovery by preventing worsening to clinical states that would extend the course of hospitalization and increase intensive respiratory support, thereby reducing the overall demand for hospital care.

Remdesivir for the Treatment of Covid-19 - Final Report.

BACKGROUND: Although several therapeutic agents have been evaluated for the treatment of coronavirus disease 2019 (Covid-19), no antiviral agents have yet been shown to be efficacious. METHODS: We conducted a double-blind, randomized, placebo-controlled trial of intravenous remdesivir in adults who were hospitalized with Covid-19 and had evidence of lower respiratory tract infection. Patients were randomly assigned to receive either remdesivir (200 mg loading dose on day 1, followed by 100 mg daily for up to 9 additional days) or placebo for up to 10 days. The primary outcome was the time to recovery, defined by either discharge from the hospital or hospitalization for infection-control purposes only. RESULTS: A total of 1062 patients underwent randomization (with 541 assigned to remdesivir and 521 to placebo). Those who received remdesivir had a median recovery time of 10 days (95% confidence interval [CI], 9 to 11), as compared with 15 days (95% CI, 13 to 18) among those who received placebo (rate ratio for recovery, 1.29; 95% CI, 1.12 to 1.49; P<0.001, by a log-rank test). In an analysis that used a proportional-odds model with an eight-category ordinal scale, the patients who received remdesivir were found to be more likely than those who received placebo to have clinical improvement at day 15 (odds ratio, 1.5; 95% CI, 1.2 to 1.9, after adjustment for actual disease severity). The Kaplan-Meier estimates of mortality were 6.7% with remdesivir and 11.9% with placebo by day 15 and 11.4% with remdesivir and 15.2% with placebo by day 29 (hazard ratio, 0.73; 95% CI, 0.52 to 1.03). Serious adverse events were reported in 131 of the 532 patients who received remdesivir (24.6%) and in 163 of the 516 patients who received placebo (31.6%). CONCLUSIONS: Our data show that remdesivir was superior to placebo in shortening the time to recovery in adults who were hospitalized with Covid-19 and had evidence of lower respiratory tract infection. (Funded by the National Institute of Allergy and Infectious Diseases and others; ACTT-1 ClinicalTrials.gov number, NCT04280705.).

A Randomized, Controlled Trial of Ebola Virus Disease Therapeutics.

BACKGROUND: Although several experimental therapeutics for Ebola virus disease (EVD) have been developed, the safety and efficacy of the most promising therapies need to be assessed in the context of a randomized, controlled trial. METHODS: We conducted a trial of four investigational therapies for EVD in the Democratic Republic of Congo, where an outbreak began in August 2018. Patients of any age who had a positive result for Ebola virus RNA on reverse-transcriptase-polymerase-chain-reaction assay were enrolled. All patients received standard care and were randomly assigned in a 1:1:1:1 ratio to intravenous administration of the triple monoclonal antibody ZMapp (the control group), the antiviral agent remdesivir, the single monoclonal antibody MAb114, or the triple monoclonal antibody REGN-EB3. The REGN-EB3 group was added in a later version of the protocol, so data from these patients were compared with those of patients in the ZMapp group who were enrolled at or after the time the REGN-EB3 group was added (the ZMapp subgroup). The primary end point was death at 28 days. RESULTS: A total of 681 patients were enrolled from November 20, 2018, to August 9, 2019, at which time the data and safety monitoring board recommended that patients be assigned only to the MAb114 and REGN-EB3 groups for the remainder of the trial; the recommendation was based on the results of an interim analysis that showed superiority of these groups to ZMapp and remdesivir with respect to mortality. At 28 days, death had occurred in 61 of 174 patients (35.1%) in the MAb114 group, as compared with 84 of 169 (49.7%) in the ZMapp group (P = 0.007), and in 52 of 155 (33.5%) in the REGN-EB3 group, as compared with 79 of 154 (51.3%) in the ZMapp subgroup (P = 0.002). A shorter duration of symptoms before admission and lower baseline values for viral load and for serum creatinine and aminotransferase levels each correlated with improved survival. Four serious adverse events were judged to be potentially related to the trial drugs. CONCLUSIONS: Both MAb114 and REGN-EB3 were superior to ZMapp in reducing mortality from EVD. Scientifically and ethically sound clinical research can be conducted during disease outbreaks and can help inform the outbreak response. (Funded by the National Institute of Allergy and Infectious Diseases and others; PALM ClinicalTrials.gov number, NCT03719586.).

Increased Metabolic Activity on 18F-Fluorodeoxyglucose Positron Emission Tomography-Computed Tomography in Human Immunodeficiency Virus-Associated Immune Reconstitution Inflammatory Syndrome.

Background: Immune reconstitution inflammatory syndrome (IRIS) represents an unexpected inflammatory response shortly after initiation of antiretroviral therapy (ART) in some human immunodeficiency virus (HIV)-infected patients with underlying neoplasia or opportunistic infections, including tuberculosis. We hypothesized that IRIS is associated with increased glycolysis and that 18F-fluorodeoxyglucose (FDG) positron emission tomography-computed tomography (PET/CT) could help identify high-risk subjects. Methods: In this prospective cohort study, 30 HIV-infected patients (CD4+ count <100 cells/µL) underwent FDG-PET/CT scans at baseline and 4-8 weeks after ART initiation. Ten patients developed IRIS (6 mycobacterial). Results: At baseline, total glycolytic activity, total lesion volume, and maximum standardized uptake values (SUVs) of pathologic FDG uptake (reflective of opportunistic disease burden) were significantly higher in IRIS vs non-IRIS (P = .010, .017, and .029, respectively) and significantly correlated with soluble inflammatory biomarkers (interferon-γ, myeloperoxidase, tumor necrosis factor, interleukin 6, soluble CD14). Baseline bone marrow (BM) and spleen FDG uptake was higher in mycobacterial IRIS specifically. After ART initiation, BM and spleen mean SUV decreased in non-IRIS (P = .004, .013) but not IRIS subjects. Our results were supported by significantly higher glucose transporter 1 (Glut-1) expression of CD4+ cells and monocytes after ART initiation in IRIS/mycobacterial IRIS compared with non-IRIS patients. Conclusions: We conclude that increased pathologic metabolic activity on FDG-PET/CT prior to ART initiation is associated with IRIS development and correlates with inflammatory biomarkers. Abnormally elevated BM and spleen metabolism is associated with mycobacterial IRIS, HIV viremia, and Glut-1 expression on CD4+ cells and monocytes. Clinical Trials Registration: NCT02147405.

Pulmonary Manifestations of the Autoimmune Lymphoproliferative Syndrome. A Retrospective Study of a Unique Patient Cohort.

RATIONALE: Patients with autoimmune lymphoproliferative syndrome (ALPS), a disorder of impaired lymphocyte apoptosis, often undergo radiographic chest imaging to evaluate the presence and progression of lymphadenopathy. These images often lead to parenchymal and interstitial lung findings of unclear clinical significance. OBJECTIVES: To characterize the pulmonary findings associated with ALPS and to determine if lung abnormalities present on computed tomographic (CT) imaging of the chest correlate with infection or functional status. METHODS: Patients with lung abnormalities observed on chest CT scans were retrospectively identified from the largest known ALPS cohort. Lung computed tomography findings were characterized and correlated with medical records, bronchoalveolar lavage, biopsy, and lung function. MEASUREMENTS AND MAIN RESULTS: CT images of the chest were available for 234 (92%) of 255 of the patients with ALPS. Among patients with a chest CT scan, 18 (8%) had lung abnormalities on at least one CT scan. Fourteen (78%) of those 18 were classified as having ALPS with undetermined genetic defect. Most patients (n = 16 [89%]) with lung lesions were asymptomatic. However, two (11%) of them had associated dyspnea and/or desaturation on room air. Immunosuppressive treatment was administered for lung disease in nine (50%) cases, and all were followed for clinical outcomes. CONCLUSIONS: Patients with ALPS can develop chest radiographic findings with protean manifestations that may mimic pulmonary infection. Management of patients with ALPS with incidental lung lesions identified by CT imaging should be guided by clinical correlation. Symptomatic patients may benefit from chest CT imaging and lesion biopsy to exclude infection and guide administration of immunosuppressive therapy.

A sterilizing tuberculosis treatment regimen is associated with faster clearance of bacteria in cavitary lesions in marmosets.

Shortening the lengthy treatment duration for tuberculosis patients is a major goal of current drug development efforts. The common marmoset develops human-like disease pathology and offers an attractive model to better understand the basis for relapse and test regimens for effective shorter duration therapy. We treated Mycobacterium tuberculosis-infected marmosets with two drug regimens known to differ in their relapse rates in human clinical trials: the standard four-drug combination of isoniazid, rifampin, pyrazinamide, and ethambutol (HRZE) that has very low relapse rates and the combination of isoniazid and streptomycin that is associated with higher relapse rates. As early as 2 weeks, the more sterilizing regimen significantly reduced the volume of lung disease by computed tomography (P = 0.035) and also significantly reduced uptake of [(18)F]-2-fluoro-2-deoxyglucose by positron emission tomography (P = 0.049). After 6 weeks of therapy, both treatments caused similar reductions in granuloma bacterial load, but the more sterilizing, four-drug regimen caused greater reduction in bacterial load in cavitary lesions (P = 0.009). These findings, combined with the association in humans between cavitary disease and relapse, suggest that the basis for improved sterilizing activity of the four-drug combination is both its faster disease volume resolution and its stronger sterilizing effect on cavitary lesions. Definitive data from relapse experiments are needed to support this observation.

An audit strategy for time-to-event outcomes measured with error: application to five randomized controlled trials in oncology.

BACKGROUND: Measurement error in time-to-event end points complicates interpretation of treatment effects in clinical trials. Non-differential measurement error is unlikely to produce large bias [1]. When error depends on treatment arm, bias is of greater concern. Blinded-independent central review (BICR) of all images from a trial is commonly undertaken to mitigate differential measurement-error bias that may be present in hazard ratios (HRs) based on local evaluations. Similar BICR and local evaluation HRs may provide reassurance about the treatment effect, but BICR adds considerable time and expense to trials. METHODS: We describe a BICR audit strategy [2] and apply it to five randomized controlled trials to evaluate its use and to provide practical guidelines. The strategy requires BICR on a subset of study subjects, rather than a complete-case BICR, and makes use of an auxiliary-variable estimator. RESULTS: When the effect size is relatively large, the method provides a substantial reduction in the size of the BICRs. In a trial with 722 participants and a HR of 0.48, an average audit of 28% of the data was needed and always confirmed the treatment effect as assessed by local evaluations. More moderate effect sizes and/or smaller trial sizes required larger proportions of audited images, ranging from 57% to 100% for HRs ranging from 0.55 to 0.77 and sample sizes between 209 and 737. LIMITATIONS: The method is developed for a simple random sample of study subjects. In studies with low event rates, more efficient estimation may result from sampling individuals with events at a higher rate. CONCLUSION: The proposed strategy can greatly decrease the costs and time associated with BICR, by reducing the number of images undergoing review. The savings will depend on the underlying treatment effect and trial size, with larger treatment effects and larger trials requiring smaller proportions of audited data.

Missing data and measurement variability in assessing progression-free survival endpoint in randomized clinical trials.

Progression-free survival (PFS) is frequently used as the primary efficacy endpoint in the evaluation of cancer treatment that is considered for marketing approval. Missing or incomplete data problems become more acute with a PFS endpoint (compared with overall survival). In a given clinical trial, it is common to observe incomplete data due to premature treatment discontinuation, missed or flawed assessments, change of treatment, lack of follow-up, and unevaluable data. When incomplete data issues are substantial, interpretation of the data becomes tenuous. Plans to prevent, minimize, or properly analyze incomplete data are critical for generalizability of results from the clinical trial. Variability in progressive disease measurement between radiologists further contributes to data problems with a PFS endpoint. The repercussions of this on phase III clinical trials are complex and depend on several factors, including the magnitude of the variability and whether there is a systematic reader evaluation bias favoring one treatment arm particularly in open-label trials.

Assessment of audit methodologies for bias evaluation of tumor progression in oncology clinical trials.

As progression-free survival (PFS) has become increasingly used as the primary endpoint in oncology phase III trials, the U.S. Food and Drug Administration (FDA) has generally required a complete-case blinded independent central review (BICR) of PFS to assess and reduce potential bias in the investigator or local site evaluation. However, recent publications and FDA analyses have shown a high correlation between local site evaluation and BICR assessments of the PFS treatment effect, which questions whether complete-case BICR is necessary. One potential alternative is to use BICR as an audit tool to detect evaluation bias in the local site evaluation. In this article, the performance characteristics of two audit methods proposed in the literature are evaluated on 26 prospective, randomized phase III registration trials in nonhematologic malignancies. The results support that a BICR audit to assess potential bias in the local site evaluation is a feasible approach. However, implementation and logistical challenges need further consideration and discussion.

Frequency, severity, and prediction of tuberculous meningitis immune reconstitution inflammatory syndrome.

BACKGROUND: Tuberculosis immune reconstitution inflammatory syndrome (IRIS) is a common cause of deterioration in human immunodeficiency virus (HIV)-infected patients receiving tuberculosis treatment after starting antiretroviral therapy (ART). Potentially life-threatening neurological involvement occurs frequently and has been suggested as a reason to defer ART. METHODS: We conducted a prospective study of HIV-infected, ART-naive patients with tuberculous meningitis (TBM). At presentation, patients started tuberculosis treatment and prednisone; ART was initiated 2 weeks later. Clinical and laboratory findings were compared between patients who developed TBM-IRIS (TBM-IRIS patients) and those who did not (non-TBM-IRIS patients). A logistic regression model was developed to predict TBM-IRIS. RESULTS: Forty-seven percent (16/34) of TBM patients developed TBM-IRIS, which manifested with severe features of inflammation. At TBM diagnosis, TBM-IRIS patients had higher cerebrospinal fluid (CSF) neutrophil counts compared with non-TBM-IRIS patients (median, 50 vs 3 cells ×10(6)/L, P = .02). Mycobacterium tuberculosis was cultured from CSF of 15 TBM-IRIS patients (94%) compared with 6 non-TBM-IRIS patients (33%) at time of TBM diagnosis; relative risk of developing TBM-IRIS if CSF was Mycobacterium tuberculosis culture positive = 9.3 (95% confidence interval [CI], 1.4-62.2). The combination of high CSF tumor necrosis factor (TNF)-α and low interferon (IFN)-γ at TBM diagnosis predicted TBM-IRIS (area under the curve = 0.91 [95% CI, .53-.99]). CONCLUSIONS: TBM-IRIS is a frequent, severe complication of ART in HIV-associated TBM and is characterized by high CSF neutrophil counts and Mycobacterium tuberculosis culture positivity at TBM presentation. The combination of CSF IFN-γ and TNF-α concentrations may predict TBM-IRIS and thereby be a means to individualize patients to early or deferred ART.

Inhibition of cowpox virus and monkeypox virus infection by mitoxantrone.

Mitoxantrone, an FDA-approved therapeutic for the treatment of cancer and multiple sclerosis, was previously reported to exhibit antiviral activity against vaccinia virus. To determine whether this activity extends to other orthopoxviruses, mitoxantrone was tested against cowpox and monkeypox. Mitoxantrone demonstrated an EC(50) of 0.25 µM against cowpox and 0.8 µM against monkeypox. Intraperitoneal treatment of cowpox virus-challenged C57Bl/6 mice with 0.5 mg/kg mitoxantrone resulted in 25% survival and a significant increase in survival time. In an effort to improve its efficacy, mitoxantrone was tested for synergistic activity with cidofovir. In vitro tests demonstrated significant synergy between the two drugs against cowpox; however, no synergistic effect on animal survival or median time-to-death was seen in intranasally-infected BALB/c mice. Significantly fewer animals survived when treated with a combination of 0.5 mg/kg mitoxantrone and 100 mg/kg cidofovir than with 100 mg/kg cidofovir alone. This is, to our knowledge, the first report of limited anti-orthopoxvirus activity by mitoxantrone in an animal model.

Evaluation of the polyclonal ELISA HPV serology assay as a biomarker for human papillomavirus exposure.

BACKGROUND: Seropositivity to human papillomavirus (HPV)16 and 18 antibodies is used as a measure of cumulative HPV exposure and as a stratifier of HPV exposure for vaccine efficacy analyses. Overall performance of these assays, as a measure of HPV exposure, has not been evaluated. METHODS: Using data from the enrollment phase of the HPV16/18 vaccine trial in Costa Rica, we evaluated the performance of the polyclonal enzyme-linked immunosorbent assay (ELISA) HPV16 and 18 serological assays as a measure of HPV exposure. Biologic (e.g., HPV infection at the cervix) and behavioral characteristics (e.g., lifetime number of sexual partners) with known associations with current and past HPV infection were used to define cases and controls (HPV exposed vs. not exposed). Prevaccination serum was measured for antibodies against HPV16 and 18 by ELISA; cervical samples were tested for HPV DNA using PCR SPF10/LiPA25. ELISA results were analyzed using receiver-operator characteristic curves; performance was evaluated at the manufacturer set cut point (HPV16 = 8, HPV18 = 7) and at cut points chosen to optimize sensitivity and specificity (HPV16 = 34, HPV18 = 60). RESULTS: Defining cases as type-specific HPV DNA positive with high-grade abnormal cytology (i.e., combined molecular and microscopic markers of infection), HPV16-ELISA gave sensitivity that was lower at the optimal cut point than the manufacturer cut point (62.2 compared with 75.7, respectively; P = 0.44). However, specificity was higher (85.3 compared with 70.4, respectively; P < 0.0001). Similarly, HPV18-ELISA gave sensitivity that was lower at the optimal cut point than the manufacturer cut point (34.5 compared with 51.7, respectively; P = 0.40), with higher specificities (94.9 compared with 72.6, respectively; P < 0.0001). CONCLUSIONS: Modifying cut points did not improve the low sensitivity. The low sensitivity of this assay does not support its use for risk stratification or clinical settings.

The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans.

PURPOSE: The development of computer-aided diagnostic (CAD) methods for lung nodule detection, classification, and quantitative assessment can be facilitated through a well-characterized repository of computed tomography (CT) scans. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI) completed such a database, establishing a publicly available reference for the medical imaging research community. Initiated by the National Cancer Institute (NCI), further advanced by the Foundation for the National Institutes of Health (FNIH), and accompanied by the Food and Drug Administration (FDA) through active participation, this public-private partnership demonstrates the success of a consortium founded on a consensus-based process. METHODS: Seven academic centers and eight medical imaging companies collaborated to identify, address, and resolve challenging organizational, technical, and clinical issues to provide a solid foundation for a robust database. The LIDC/IDRI Database contains 1018 cases, each of which includes images from a clinical thoracic CT scan and an associated XML file that records the results of a two-phase image annotation process performed by four experienced thoracic radiologists. In the initial blinded-read phase, each radiologist independently reviewed each CT scan and marked lesions belonging to one of three categories ("nodule > or =3 mm," "nodule <3 mm," and "non-nodule > or =3 mm"). In the subsequent unblinded-read phase, each radiologist independently reviewed their own marks along with the anonymized marks of the three other radiologists to render a final opinion. The goal of this process was to identify as completely as possible all lung nodules in each CT scan without requiring forced consensus. RESULTS: The Database contains 7371 lesions marked "nodule" by at least one radiologist. 2669 of these lesions were marked "nodule > or =3 mm" by at least one radiologist, of which 928 (34.7%) received such marks from all four radiologists. These 2669 lesions include nodule outlines and subjective nodule characteristic ratings. CONCLUSIONS: The LIDC/IDRI Database is expected to provide an essential medical imaging research resource to spur CAD development, validation, and dissemination in clinical practice.

An audit strategy for progression-free survival.

In randomized clinical trials, the use of potentially subjective endpoints has led to frequent use of blinded independent central review (BICR) and event adjudication committees to reduce possible bias in treatment effect estimators based on local evaluations (LE). In oncology trials, progression-free survival (PFS) is one such endpoint. PFS requires image interpretation to determine whether a patient's cancer has progressed, and BICR has been advocated to reduce the potential for endpoints to be biased by knowledge of treatment assignment. There is current debate, however, about the value of such reviews with time-to-event outcomes such as PFS. We propose a BICR audit strategy as an alternative to a complete-case BICR to provide assurance of the presence of a treatment effect. We develop an auxiliary-variable estimator of the log-hazard ratio that is more efficient than simply using the audited (i.e., sampled) BICR data for estimation. Our estimator incorporates information from the LE on all the cases and the audited BICR cases, and is an asymptotically unbiased estimator of the log-hazard ratio from BICR. The estimator offers considerable efficiency gains that improve as the correlation between LE and BICR increases. A two-stage auditing strategy is also proposed and evaluated through simulation studies. The method is applied retrospectively to a large oncology trial that had a complete-case BICR, showing the potential for efficiency improvements.

Measurement error in the timing of events: effect on survival analyses in randomized clinical trials.

BACKGROUND: Presence of measurement error in the outcome can complicate the interpretation of a randomized clinical trial. The Oncologic Drugs Advisory Committee of the US Food and Drug Administration voted against recommending approval of bevacizumab for the initial treatment of metastatic breast cancer; one of their major concerns was the presence of a large amount of nondifferential measurement error in the evaluation of progression-free survival, the primary outcome of the randomized clinical trial E2100. PURPOSE: To investigate the effects of nondifferential measurement error in time-to-event outcomes on the conclusions of a proportional hazards analysis of a randomized clinical trial. METHODS: Simulations were performed showing effects of measurement error on the estimated treatment effect (hazard ratio) in a clinical trial. In some simulations, the measurement error structure from E2100 data was approximated; for other simulations, larger or smaller measurement error was considered. RESULTS: The bias in estimating the hazard ratio was very small using measurement error and a hazard ratio similar to E2100. Even with a larger nondifferential measurement error, the bias remained small when the hazard ratio was in a range commonly seen in clinical trials. There was no or little effect on the variability of the estimated treatment effect. LIMITATIONS: Because of censoring issues, retrospective evaluation of the measurement error structure from a completed trial is difficult. Although our simulations cover a range of plausible measurement error values, in theory, a trial could have much larger measurement error than we considered. Differential measurement error is only briefly considered. CONCLUSIONS: Nondifferential measurement error due to variability in estimating time-to-event outcomes will typically not be a major concern in randomized clinical trials.

Blinded independent central review of progression-free survival in phase III clinical trials: important design element or unnecessary expense?

Progression-free survival is an important end point in advanced disease settings. Blinded independent central review (BICR) of progression in randomized clinical trials has been advocated to control bias that might result from errors in progression assessments. However, although BICR lessens some potential biases, it does not remove all biases from evaluations of treatment effectiveness. In fact, as typically conducted, BICRs may introduce bias because of informative censoring, which results from having to censor unconfirmed locally determined progressions. In this article, we discuss the rationale for BICR and different ways of implementing independent review. We discuss the limitations of these approaches and review published trials that report implementing BICR. We demonstrate the existence of informative censoring using data from a randomized phase II trial. We conclude that double-blinded trials with consistent application of measurement criteria are the best means of ensuring unbiased trial results. When such designs are not practical, BICR is not recommended as a general strategy for reducing bias. However, BICR may be useful as an auditing tool to assess the reliability of marginally positive results.

Lack of generalizability of sensitivity and specificity with treatment effects.

In biomarker development, two types of summary measures are often used to describe marker accuracy. Positive and negative predictive values describe how well a marker predicts clinical states of interest, while sensitivity and specificity describe how well a marker discriminates between the two states. Insofar as predictive values depend heavily on the prevalence of the clinical states and sensitivity and specificity may not, sensitivity and specificity are preferred in early biomarker development. In many applications, an ideal property of a biomarker is fulfillment of the first Prentice criterion. Under this condition, predictive values do not depend on a covariate (such as treatment) because the biomarker captures all relevant information about the clinical state of interest. A similar condition can be defined for sensitivity and specificity which states that these measures do not depend on a covariate (e.g. treatment). This condition, which we refer to as the equal discriminatory accuracy (EDA) condition, is desirable because it allows sensitivity and specificity from one treatment setting (or covariate value) to be applied to a different setting. We demonstrate, however, that the Prentice condition and EDA are incompatible. Further, under a simple proportional hazards model for a time-to-event outcome, EDA will not be satisfied. We present numerical examples as well as examples of a potential marker in late-stage prostate cancer and another for cervical cancer screening. These results demonstrate that evaluating sensitivity and specificity within treatment (or other covariate) groups is necessary even when simple proportional hazards models or the Prentice criterion holds.

On Estimating Diagnostic Accuracy From Studies With Multiple Raters and Partial Gold Standard Evaluation.

We are often interested in estimating sensitivity and specificity of a group of raters or a set of new diagnostic tests in situations in which gold standard evaluation is expensive or invasive. Numerous authors have proposed latent modeling approaches for estimating diagnostic error without a gold standard. Albert and Dodd showed that, when modeling without a gold standard, estimates of diagnostic error can be biased when the dependence structure between tests is misspecified. In addition, they showed that choosing between different models for this dependence structure is difficult in most practical situations. While these results caution against using these latent class models, the difficulties of obtaining gold standard verification remain a practical reality. We extend two classes of models to provide a compromise that collects gold standard information on a subset of subjects but incorporates information from both the verified and nonverified subjects during estimation. We examine the robustness of diagnostic error estimation with this approach and show that choosing between competing models is easier in this context. In our analytic work and simulations, we consider situations in which verification is completely at random as well as settings in which the probability of verification depends on the actual test results. We apply our methodological work to a study designed to estimate the diagnostic error of digital radiography for gastric cancer.