Comparison of proportional and differential odds models for mixed-effects analysis of categorical data

ABSTRACT.In this study, we report the development of the first item response theory (IRT) model within a pharmacometrics framework to characterize the disease progression in multiple sclerosis (MS), as measured by Expanded Disability Status Score (EDSS). Data were collected quarterly from a 96-week phase III clinical study by a blinder rater, involving 104,206 item-level observations from 1319 patients with relapsing-remitting MS (RRMS), treated with placebo or cladribine. Observed scores for each EDSS item were modeled describing the probability of a given score as a function of patients' (unobserved) disability using a logistic model. Longitudinal data from placebo arms were used to describe the disease progression over time, and the model was then extended to cladribine arms to characterize the drug effect. Sensitivity with respect to patient disability was calculated as Fisher information for each EDSS item, which were ranked according to the amount of information they contained. The IRT model was able to describe baseline and longitudinal EDSS data on item and total level. The final model suggested that cladribine treatment significantly slows disease-progression rate, with a 20% decrease in disease-progression rate compared to placebo, irrespective of exposure, and effects an additional exposure-dependent reduction in disability progression. Four out of eight items contained 80% of information for the given range of disabilities. This study has illustrated that IRT modeling is specifically suitable for accurate quantification of disease status and description and prediction of disease progression in phase 3 studies on RRMS, by integrating EDSS item-level data in a meaningful manner.

show abstract

“…Cumulative probabilities for a score of M categories were modeled according to following equations (18):…”

Section: Modeling Methodologymentioning

confidence: 99%

Application of Item Response Theory to Modeling of Expanded Disability Status Scale in Multiple Sclerosis

Novakovic

Krekels

Munafo

et al. 2016

AAPS J

View full text Add to dashboard Cite

show abstract

“…The Q-statistic was used to investigate the degree of heterogeneity between the trials, and a P-value 0.10 for the Q-test indicated a lack of heterogeneity among studies. We used the fixed-effects model and the random-effects model based on the Mantel-Haenszel method (Jose et al, 2008) and the DerSimonian and Laird method (Kjellsson et al, 2008), respectively, to combine values from each of the studies. A sensitivity analysis was also performed by omitting each study in turn to identify potential outliers.…”

Section: Methodsmentioning

confidence: 99%

Association of the PSCA rs2294008 C＞T Polymorphism with Gastric Cancer Risk: Evidence from a Meta-Analysis

Yao¹,

Gu²,

Gu³

et al. 2012

Asian Pacific Journal of Cancer Prevention

View full text Add to dashboard Cite

Background: Multiple studies have reported associations between the PSCA rs2294008 C > T polymorphism and GC, but susceptibility has proven inconsistent. Therefore, we estimates the relationship between the rs2294008 C > T polymorphism and GC by meta-analysis. Methods: PubMed, Embase and Web of Science databases were searched and nine independent case-control studies were included in this meta-analysis. Crude ORs with 95% CIs were extracted according to the Mantal-Haenszel method and pooled to assess the strength of the association. Results: We observed that the PSCA rs2294008 C > T polymorphism was significantly correlated with GC risk when all studies were pooled into the meta-analysis. Further subgroup analysis showed the polymorphism to be linked with diffuse and noncardia GC in the allele contrast model, homozygote codominant model, dominant model, and recessive model. However, no connection was apparent for intestinal and cardia GC. In the stratified analysis by ethnicity, significant associations were observed in Asians for the recessive model. Interestingly, the relationship was particularly significant in the Chinese population. Conclusions: Our findings suggest that the PSCA rs2294008 C > T polymorphism is a risk factor for GC, especially in diffuse and noncardia GC and in Chinese.

show abstract

“…An ordered categorical model was used to describe the data (19,22). The probability for a patient i to obtain a score greater or equal to k is expressed as a function of the latent variable ( , ), where represents the motor, non-motor or tremor subscales.…”

Section: Irt Modelmentioning

confidence: 99%

Item Response Theory as an Efficient Tool to Describe a Heterogeneous Clinical Rating Scale in De Novo Idiopathic Parkinson’s Disease Patients

et al. 2017

View full text Add to dashboard Cite

Purpose: This manuscript aims to precisely describe the natural disease progression of Parkinson's disease (PD) patients and evaluate approaches to increase the drug effect detection power.Methods: An item response theory (IRT) longitudinal model was built to describe the natural disease progression of 423 de novo PD patients followed during 48 months while taking into account the heterogeneous nature of the MDS-UPDRS scale. Clinical trial simulations were then used to compare drug effect detection power from IRT and sum of item scores based analysis under different analysis endpoints and drug effects. Results:The IRT longitudinal model accurately describes the evolution of patients with and without PD medications while estimating different progression rates for the subscales. When comparing analysis methods, the IRT-based one consistently provided the highest power. Conclusion:IRT is a powerful tool which enables to capture the heterogeneous nature of the MDS-UPDRS.IRT as a tool to describe a heterogeneous clinical scale 2

show abstract

Comparison of proportional and differential odds models for mixed-effects analysis of categorical data

Cited by 20 publications

References 22 publications

Application of Item Response Theory to Modeling of Expanded Disability Status Scale in Multiple Sclerosis

Application of Item Response Theory to Modeling of Expanded Disability Status Scale in Multiple Sclerosis

Association of the PSCA rs2294008 C＞T Polymorphism with Gastric Cancer Risk: Evidence from a Meta-Analysis

Item Response Theory as an Efficient Tool to Describe a Heterogeneous Clinical Rating Scale in De Novo Idiopathic Parkinson’s Disease Patients

Contact Info

Product

Resources

About