Biomedical subjects

Jen-Pei Liu

Publications and source records attributed to Jen-Pei Liu.

10 recordsLinked to original sources

PubMed2008

On the exact interval estimation for the difference in paired areas under the ROC curves.

An important measure for comparison of accuracy between two diagnostic procedures is the difference in paired areas under the receiver operating characteristic (ROC) curves. Non-parametric and maximum likelihood methods have been proposed for interval estimation for the difference in paired areas under ROC curves. However, these two methods are asymptotic procedures and their performance in finite sample sizes has not been thoroughly investigated. We propose to use the concept of generalized pivotal quantities (GPQs) to construct an exact confidence interval for the difference in paired areas under ROC curves. A simulation study is conducted to empirically investigate the probability coverage and expected length of the three methods for various combinations of sample sizes, values of the area under the ROC curve and correlations. Simulation results demonstrate that the exact confidence interval based on the concept of GPQs provides not only sufficient probability coverage but also reasonable expected length. Numerical examples using published data sets illustrate the proposed method.

Clinical Trials as Topic↗

PubMed2006

Tests of equivalence and non-inferiority for diagnostic accuracy based on the paired areas under ROC curves.

Assessment of equivalence or non-inferiority in accuracy between two diagnostic procedures often involves comparisons of paired areas under the receiver operating characteristic (ROC) curves. With some pre-specified clinically meaningful limits, the current approach to evaluating equivalence is to perform the two one-sided tests (TOST) based on the difference in paired areas under ROC curves estimated by the non-parametric method. We propose to use the standardized difference for assessing equivalence or non-inferiority in diagnostic accuracy based on paired areas under ROC curves between two diagnostic procedures. The bootstrap technique is also suggested for both non-parametric method and the standardized difference approach. A simulation study was conducted empirically to investigate the size and power of the four methods for various combinations of distributions, data types, sample sizes, and different correlations. Simulation results demonstrate that the bootstrap procedure of the standardized difference approach not only can adequately control the type I error rate at the nominal level but also provides equivalent power under both symmetrical and skewed distributions. A numerical example using published data illustrates the proposed methods.

Computer Simulation↗

PubMed2006

An alternative approach to evaluation of poolability for stability studies.

The current method for pooling the data from different batches or factors, suggested by ICH Q1E guidance, is to use analysis of covariance (ANCOVA) for test interaction between slopes and intercepts and factors. Failure to reject the null hypothesis of equality of slopes and equality of intercepts, however, does not prove that slopes and intercepts from different levels of factors are the same, and the data can be pooled for estimation of shelf life. In addition, the ANCOVA approach uses indirect parameters of intercepts and slopes in the regression model for assessment of poolability. The hypothesis for poolability is then formulated on the basis of the concept of equivalence for the means among the distributions of the quantitative attributes at a particular time point. Methods based on the intersection-union procedure are proposed to test the hypothesis of equivalence. A large simulation study was conducted to empirically investigate the size and power of the proposed method for the bracketing and matrixing designs given in the ICH Q1D guidance. Simulation results show that the proposed method can adequately control the size and provides sufficient power when the number of factors considered is fewer than three. A numerical example using the published data illustrates the proposed method.

Computer Simulation↗

PubMed2006

Effects of exercise training on heart rate variability after coronary angioplasty.

BACKGROUND AND PURPOSE: Cardiac autonomic dysfunction is associated with risk of restenosis and cardiovascular mortality in patients after percutaneous transluminal coronary angioplasty (PTCA). Analysis of heart rate variability (HRV) is an important, widely used method for assessing cardiac autonomic regulation. The purpose of this study was to investigate the effect of exercise training on HRV in subjects after PTCA. SUBJECTS AND METHODS: A total of 84 subjects who had undergone PTCA were recruited for this study. The subjects (age [mean+/-SD]=57.0+/-9.3 years) were randomly assigned to either an exercise group to undergo an 8-week outpatient exercise program or a control group to undergo usual care. Heart rate variability was measured for 5 minutes in the supine resting position at baseline and at the end of 8 weeks. RESULTS: The parasympathetically modulated HRV of the subjects in the exercise group increased significantly compared with the HRV of subjects in the control group. The effects of training on HRV were independent of angioplasty type (balloon or stent) and were unrelated to whether the subjects had received previous PTCA. DISCUSSION AND CONCLUSION: Exercise training can increase parasympathetic modulation of cardiac function in people after they have undergone successful PTCA. Our results suggest that analysis of HRV can be extended to assess the effect of exercise training on cardiac autonomic dysfunction in people after coronary angioplasty.

Aged↗

PubMed2005

Tests for equivalence based on odds ratio for matched-pair design.

Currently, methods for evaluation of equivalence under a matched-pair design use either difference in proportions or relative risk as measures of risk association. However, these measures of association are only for cross-sectional studies or prospective investigations, such as clinical trials and they cannot be applied to retrospective research such as case-control studies. As a result, under a matched-pair design, we propose the use of the conditional odds ratio for assessment of equivalence in both prospective and retrospective research. We suggest the use of the asymptotic confidence interval of the conditional odds ratio for evaluation of equivalence. In addition, a score test based on the restricted maximum likelihood estimator (RMLE) is derived to test the hypothesis of equivalence under a matched-pair design. On the other hand, a sample size formula is also provided. A simulation study was conducted to empirically investigate the size and power of the proposed procedures. Simulation results show that the score test not only adequately controls the Type I error but it can also provide sufficient power. A numerical example illustrates the proposed methods.

Computer Simulation↗

PubMed2005

A two-stage design for bridging studies.

The ICH E5 guideline defines a bridging study as a supplementary study conducted in the new region to provide pharmacodynamic or clinical data on efficacy, safety, dosage, and dose regimen to allow extrapolation of the foreign clinical data to the population of the new region. Therefore, a bridging study is usually conducted in the new region only after the test product has been approved for commercial marketing in the original region based on its proven efficacy and safety. One of the current issues for evaluation of bridging studies is a cross-study comparison. Therefore, bias occurs when the study is not internally valid. A two-stage approach is proposed to overcome the issue of internal validity and at the same time to meet the objective of minimizing unnecessary duplication of clinical data required by the ICH E5 guideline. Under the framework of the proposed two-stage design, the bridging study of the new region is a second-stage substudy of the whole trial, and the patients for the bridging substudy are enrolled only after the data obtained in the original region demonstrate a statistically significantly positive treatment effect. Methods for the determination of the sample size for each region and the critical values at each stage are also proposed.

Clinical Trials as Topic↗

PubMed2004

Better prediction of prognosis for patients with nasopharyngeal carcinoma using primary tumor volume.

BACKGROUND: Heterogeneity of primary tumor volume within tumors of the same classification indicates a need to elucidate the effects of primary tumor volume on treatment outcomes in patients with nasopharyngeal carcinoma (NPC). METHODS: From 1994 through 1996, 129 patients with newly diagnosed NPC who were treated with high-dose radiotherapy were enrolled in the study. Computed tomography-derived primary tumor volume was measured using the summation-of-area technique. Correlations between American Joint Committee on Cancer (AJCC) disease stage, primary tumor volume, and disease-specific survival were assessed using a Cox regression model. Cross-validation based on receiver operating characteristic (ROC) curve also was examined. RESULTS: Compared with the AJCC staging system and the TNM classification system, primary tumor volume was better at determining cumulative survival for patients with NPC. Hazard ratios increased with tumor volume, ranging from 6.68 (95% confidence interval [95% CI], 1.89-23.67) for tumor volumes between 20-40 mL, 18.03 (95% CI, 4.80-67.75) for tumor volumes between 40-60 mL, and 26.06 (95% CI, 7.70-88.20) for tumor volumes > 60 mL. With both tumor volume and T classification in the same Cox regression model, only tumor volume remained statistically significant in the prognosis of NPC. The validation results with ROC curves also revealed that, in predicting patient outcome, primary tumor volume (area under the ROC = 83.33%) was superior to disease stage (area under the ROC = 66.53%) and TNM classification (area under the ROC = 58.61%). CONCLUSIONS: The incorporation of primary tumor volume may lead to a further refinement of the current AJCC staging system, particularly for patients with large primary tumor volumes (> 60 mL), who require more aggressive treatment. Cancer 2004.

Cohort Studies↗

PubMed2004

A Bayesian noninferiority approach to evaluation of bridging studies.

A bridging study defined by The International Conference on Harmonization E5 is usually conducted in the new region only after the test product has been approved for commercial marketing in the original region due to its proven efficacy and safety. In this paper, we address the issue of analysis of clinical data generated by the bridging study conducted in the new region to evaluate the similarity for extrapolation of the foreign clinical data to the population of the new region. Information on efficacy, safety, dosage, and dose regimen of the original region cannot be concurrently obtained from the local bridging studies but are available in the trials conducted in the original region. A Bayesian noninferiority approach is therefore proposed to incorporate the data generated in the original region to evaluate bridging evidence by the local bridging studies and assess similarity between the new and original regions. Methods for sample size determination for the bridging study are also proposed.

Bayes Theorem↗

PubMed2003

A group sequential approach to evaluation of bridging studies.

The International Conference on Harmonization (ICH) E5 guideline defines a bridging study as a supplementary study conducted in the new region to provide pharmacodynamic or clinical data on efficacy, safety, dosage, and dose regimen to allow extrapolation of the foreign clinical data to the population of the new region. Therefore, a bridging study is usually conducted in the new region only after the test product has been approved for commercial marketing in the original region due to its proven efficacy and safety. The issue of analysis of clinical data generated by the bridging study conducted in the new region to evaluate the similarity for extrapolation of the foreign clinical data to the population of the new region is the information on efficacy, safety, dosage, and dose regimen of the original region that cannot be concurrently obtained from the local bridging studies but is available in the trials conducted in the original region. A group sequential approach is therefore proposed to overcome the issue of internal validity. In particular, we use the region as a group sequence to enroll the patients from the original region first and then to enroll patients from the new region subsequently. Methods for sample size determination for the bridging study in the new region are also proposed.

Biopharmaceutics↗

PubMed2003

A randomized trial comparing intravesical instillations of mitoxantrone and doxorubicin in patients with superficial bladder cancer.

BACKGROUND: This randomized trial was conducted to compare the efficacy and side effects of intravesical mitoxantrone instillation with those of doxorubicin in superficial bladder cancer following transurethral resection. METHODS: Sixty-three patients were randomized into mitoxantrone and doxorubicin groups. Most of the patients enrolled were elderly people (mean age, 71 years). The instilled doses of doxorubicin and mitoxantrone were 30 and 14 mg, respectively. Disease recurrence and side effects were compared using Fisher's exact test. The interval to recurrence was shown by Kaplan-Meier survivorship curves, and the log-rank test was used to compare the time to recurrence. RESULTS: The median follow-up period was 36 months. Thirty-three patients received mitoxantrone, whereas 30 patients used doxorubicin. The recurrence rate in the doxorubicin group was 30% (95% CI: 19.8%-38.8%), while it was 27.3% (95% CI: 17.5%-36.8%) in the mitoxantrone group. The median recurrence-free survival in the mitoxantrone group and in the doxorubicin group was 22 and 20 months, respectively (p=0.580). Higher recurrence rates were found for Grade III and multiple primary tumors. There was no significant difference in response rates (p=0.784). The incidence of side effects was 20% in the doxorubicin group and 21.2% in the mitoxantrone group. However, the difference was not significant (p>0.99). CONCLUSIONS: The results revealed that the efficacy and side effects of mitoxantrone were similar to those of doxorubicin. Especially for patients with pulmonary tuberculosis or aged patients with primary bladder tumors, mitoxantrone and doxorubicin may be the tolerable and effective intravesical agents.

Administration, Intravesical↗