Open Access

Introduction: It has been shown that Alzheimer’s disease (AD) is accompanied by marked structural brain changes that can be detected several years before clinical diagnosis via structural magnetic resonance (MR) imaging. In this study, we developed a structural MR-based biomarker for in vivo detection of AD using a supervised machine learning approach. Based on an individual’s pattern of brain atrophy a continuous AD score is assigned which measures the similarity with brain atrophy patterns seen in clinical cases of AD. Methods: The underlying statistical model was trained with MR scans of patients and healthy controls from the Alzheimer’s Disease Neuroimaging Initiative (ADNI-1 screening). Validation was performed within ADNI-1 and in an independent patient sample from the Open Access Series of Imaging Studies (OASIS-1). In addition, our analyses included data from a large general population sample of the Study of Health in Pomerania (SHIP-Trend). Results: Based on the proposed AD score we were able to differentiate patients from healthy controls in ADNI-1 and OASIS-1 with an accuracy of 89% (AUC = 95%) and 87% (AUC = 93%), respectively. Moreover, we found the AD score to be significantly associated with cognitive functioning as assessed by the Mini-Mental State Examination in the OASIS-1 sample after correcting for diagnosis, age, sex, age·sex, and total intracranial volume (Cohen’s f2 = 0.13). Additional analyses showed that the prediction accuracy of AD status based on both the AD score and the MMSE score is significantly higher than when using just one of them. In SHIP-Trend we found the AD score to be weakly but significantly associated with a test of verbal memory consisting of an immediate and a delayed word list recall (again after correcting for age, sex, age·sex, and total intracranial volume, Cohen’s f2 = 0.009). This association was mainly driven by the immediate recall performance. Discussion: In summary, our proposed biomarker well differentiated between patients and healthy controls in an independent test sample. It was associated with measures of cognitive functioning both in a patient sample and a general population sample. Our approach might be useful for defining robust MR-based biomarkers for other neurodegenerative diseases, too.

For the goal of individualized medicine, it is critical to have clinical phenotypes at hand which represent the individual pathophysiology. However, for most of the utilized phenotypes, two individuals with the same phenotype assignment may differ strongly in their underlying biological traits. In this paper, we propose a definition for individualization and a corresponding statistical operationalization, delivering thereby a statistical framework in which the usefulness of a variable in the meaningful differentiation of individuals with the same phenotype can be assessed. Based on this framework, we develop a statistical workflow to derive individualized phenotypes, demonstrating that under specific statistical constraints the prediction error of prediction scores contains information about hidden biological traits not represented in the modeled phenotype of interest, allowing thereby internal differentiation of individuals with the same assigned phenotypic manifestation. We applied our procedure to data of the population-based Study of Health in Pomerania to construct a refined definition of obesity, demonstrating the utility of the definition in prospective survival analyses. Summarizing, we propose a framework for the individualization of phenotypes aiding personalized medicine by shifting the focus in the assessment of prediction models from the model fit to the informational content of the prediction error.