×
  • Select the area you would like to search.
  • ACTIVE INVESTIGATIONS Search for current projects using the investigator's name, institution, or keywords.
  • EXPERTS KNOWLEDGE BASE Enter keywords to search a list of questions and answers received and processed by the ADNI team.
  • ADNI PDFS Search any ADNI publication pdf by author, keyword, or PMID. Use an asterisk only to view all pdfs.
Principal Investigator  
Principal Investigator's Name: Ainesh Sewak
Institution: University of Zurich
Department: Biostatistics
Country:
Proposed Analysis: We are working on developing statistical methods for inference on receiver operating characteristic (ROC) curves. We are working in the framework of transformation models [1] with which we can estimate regression parameters semiparametrically. ROC curves and its summary metrics can be incorporated into this framework. As an application of our method we wanted to compare the performance of biomarkers in being able to distinguish people who develop Alzheimer's disease (AD). This data set would be perfect to illustrate a situation where it is essential to adjust for multiple covariates and censoring to provide accurate statistical inference (estimates and confidence intervals) of the ROC curve and its summary measures. We plan on subsetting the participants from ADNI to those who have the biomarkers of interest available at baseline (CSF Abeta, APOE 4 allele). We will construct multivariate regression transformation models using these participants and develop a risk score as in [2]. Using this risk score we will try to distinguish participants who have AD and report the performance using our method developed for ROC curves. [1] Hothorn, Torsten, Lisa Moest, and Peter Buehlmann. "Most likely transformations." Scandinavian Journal of Statistics 45, no. 1 (2018): 110-134. [2] Nuño, Michelle M., and Daniel L. Gillen. "Censoring‐robust time‐dependent receiver operating characteristic curve estimators." Statistics in Medicine (2021).
Additional Investigators