Search

Amyloid- β (A β ) is the target in many clinical trials for Alzheimer's disease (AD). Preclinical AD patients are heterogeneous with regards to different backgrounds and diagnosis. Accurately predicting A β status of participants by using machine learning (ML) models based on easily accessible data, could improve the effectiveness of AD clinical trials. We will develop optimal ML models for each subpopulation stratified by sex and disease stages using sub scores from screening neurological tests. Data from the AD Neuroimaging Initiative (ADNI) were used to build the ML models, for three groups: individuals with significant memory concern, early mild cognitive impairment (MCI), and late MCI. Data were further separated into 6 groups by disease stage (3 levels) and sex (2 categories). The outcome was defined as the A β status confirmed by the PET imaging, and the features include demographic data, newly identified risk factors, screening tests, and the domain scores from screening tests. Monte Carlo simulation studies were used together with k-fold cross-validation technique to compute model performance metric. We also develop a new feature selection method based on the stochastic ordering to avoiding searching all possible combinations of features. Accuracy of the identified optimal model for SMC male was over 90% by using domain scores, and accuracy for LMCI female was above 86%. Domain scores can improve the ML model prediction as compared to the total scores. Accurate ML prediction models can identify the proper population for AD clinical trials. [ABSTRACT FROM AUTHOR]

Bilateral data are frequently occur in medical research. Asymptotic approaches are traditionally used to construct confidence intervals for proportion difference. However, they are often have unsatisfactory performance with regards to coverage, with the actual coverage below the nominal level or being too conservative. For these reasons, we propose developing exact one-sided limits for proportion difference in a parallel study with bilateral data to guarantee the coverage probability when sample size is small to medium. A statistical quantity has to be used for sample space ordering in the exact limit calculation. Four asymptotic limits are utilized as statistical quantities: the Wald limits under the independence or dependence assumptions for variance estimates, the Wald limits with the difference estimate under the dependence assumption, and the bootstrap percentile limits. We compare the performance of these exact limits with regards to average length and the limits of all possible samples. A real example from a randomized clinical trial in otolaryngology is used to illustrate the application of the proposed exact limits. [ABSTRACT FROM AUTHOR]