Dataset Information

On the time-varying predictive performance of longitudinal biomarkers: Measure and estimation.

ABSTRACT: In many biomedical studies, participants are monitored at periodic visits until the occurrence of the failure event. Biomarkers are often measured repeatedly during these visits, and such measurements can facilitate updated disease prediction. In this work, we propose a two-dimensional incident dynamic area under curve (AUC), to capture the variability due to both the biomarker assessment time and the prediction time to comprehensively quantify the predictive performance of a longitudinal biomarker. We propose a pseudo partial-likelihood to achieve consistent estimation of the AUC under two realistic scenarios of visit schedules. Variance estimation methods are designed to facilitate inferential procedures. We examine the finite-sample performance of our method through extensive simulations. The methods are applied to a study of chronic myeloid leukemia to evaluate the predictive performance of longitudinally collected gene expression levels.

SUBMITTER: Zhang J

PROVIDER: S-EPMC8751424 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

On the time-varying predictive performance of longitudinal biomarkers: Measure and estimation.

Zhang Jing J Ning Jing J Huang Xuelin X Li Ruosha R

Statistics in medicine 20210622 23

In many biomedical studies, participants are monitored at periodic visits until the occurrence of the failure event. Biomarkers are often measured repeatedly during these visits, and such measurements can facilitate updated disease prediction. In this work, we propose a two-dimensional incident dynamic area under curve (AUC), to capture the variability due to both the biomarker assessment time and the prediction time to comprehensively quantify the predictive performance of a longitudinal biomar ...[more]

PMID: 34159633

Similar Datasets

Project description:The central nervous system (CNS) controls the limb movement by modulating multiple skeletal muscles with synergistic modules and neural oscillations with different frequencies between the activated muscles. Several researchers have found intermuscular coherence existing within the synergistic muscle pairs, and pointed out that the intermuscular synchronization existed when functional forces were generated. However, few studies involved the time-varying characteristics of the intermuscular coherence in each synergy module though all activated muscles keep in a dynamic and varying process. Therefore, this study aims to explore the time-varying coherence amongst synergistic muscles during movements based on the combination of the non-negative matrix factorization (NMF) method and the time-frequency coherence (TFC) method. We applied these methods into the electromyogram (EMG) signals recorded from eight muscles involved in the sequence of the wrist movements [wrist flexion (WF), wrist flexion transmission to wrist extension (MC) and wrist extension (WE)] in 12 healthy people. The results showed three synergistic flexor pairs (FCR-PL, FCR-FDS, and PL-FDS) in the WF stage and three extensor pairs (ECU-ECR, ECU-B, and ECR-B) in both MC and WE stages. Further analysis showed intermuscular coherence between each pairwise synergistic muscles. The intermuscular coherence between the flexor muscle pairs was mainly observed in the beta band (15-35 Hz) during the WF stage, and that amongst the extensor muscle pairs was also observed in the beta band during the WE stage. However, the intermuscular coherence between the extensor muscle pairs mainly on gamma band during the MC stage. Additionally, compared to the flexor muscle pairs, the intermuscular coherence of the extensor muscle pairs were lower in the WF stage, and higher in both MC and WE stages. These results demonstrated the time-varying mechanisms of the synergistic modulation and synchronous oscillation in motor-control system. This study contributes to expanded researches for motor control.

Dataset Information

On the time-varying predictive performance of longitudinal biomarkers: Measure and estimation.

Publications

On the time-varying predictive performance of longitudinal biomarkers: Measure and estimation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets