A highly predictive signature of cognition and brain atrophy for progression to Alzheimer's dementia

GigaScience, 8, 2019, 1–16 doi: 10.1093/gigascience/giz055 Research RESEARCH Angela Tam 1,2,* , Christian Dansereau1,4 , Yasser Iturria-Medina3 , Sebastian Urchs1,3 , Pierre Orban1,5,6 , Hanad Sharmarke1 , John Breitner2,7 , † and Pierre Bellec 1,8,* for the Alzheimer’s Disease Neuroimaging Initiative, 1 Centre de Recherche de l’Institut Universitaire de Gériatrie de Montréal, 4545 chemin Queen-Mary, Montréal, QC, H3W 1W4, Canada, 2 Centre for the Studies on Prevention of Alzheimer’s Disease, Douglas Mental Health University Institute Research Centre, 6875 Lasalle Boulevard, Montréal, QC, H4H 1R3, Canada, 3 Montreal Neurological Institute, McGill University, 3801 University Street, Montréal, QC, H3A 2B4, Canada, 4 Département d’informatique et de recherche opérationnelle, Université de Montréal, 2920 chemin de la Tour, Montréal, QC, H3T 1J4, Canada, 5 Centre de Recherche de l’Institut Universitaire en Santé Mentale de Montréal, 7331 rue Hochelaga, Montréal, QC, H1N 3V2, Canada, 6 Département de psychiatrie, Université de Montréal, 2900 boulevard Édouard-Montpetit, Montréal, QC, H3T 1J4, Canada, 7 Department of Psychiatry, McGill University, 1033 Pine Avenue West, Montréal, QC, H3A 1A1, Canada and 8 Département de psychologie, Université de Montréal, 90 avenue Vincent d’Indy, Montréal, QC, H3C 3J7, Canada ∗ Correspondence address. Angela Tam and Pierre Bellec, 4565 Queen-Mary Road, Montreal, QC, H3W 1W5, Canada. E-mail: http://orcid.org/0000-0001-6752-5707 and http://orcid.org/0000-0002-9111-0699 † Data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at http://adni.loni.usc.edu/wp-content/uploads/how to apply/ADNI Acknowledgement List.pdf. Abstract Background: Clinical trials in Alzheimer’s disease need to enroll patients whose cognition will decline over time, if left untreated, in order to demonstrate the efficacy of an intervention. Machine learning models used to screen for patients at risk of progression to dementia should therefore favor specificity (detecting only progressors) over sensitivity (detecting all progressors), especially when the prevalence of progressors is low. Here, we explore whether such high-risk patients can be identified using cognitive assessments and structural neuroimaging by training machine learning tools in a high-specificity regime. Results: A multimodal signature of Alzheimer’s dementia was first extracted from the ADNI1 dataset. We then validated the predictive value of this signature on ADNI1 patients with mild cognitive impairment (N = 235). The signature was optimized to predict progression to dementia over 3 years with low sensitivity (55.1%) but high specificity (95.6%), resulting in only moderate accuracy (69.3%) but high positive predictive value (80.4%, adjusted for a “typical” 33% prevalence rate of true progressors). These results were replicated in ADNI2 (N = 235), with 87.8% adjusted positive predictive value (96.7% specificity, 47.3% sensitivity, 85.1% accuracy). Conclusions: We found that cognitive measures alone could identify high-risk individuals, with structural measurements providing a slight improvement. The signature had Received: 8 October 2018; Revised: 7 March 2019; Accepted: 21 April 2019  C The Author(s) 2019. Published by Oxford University Press. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited. 1 A highly predictive signature of cognition and brain atrophy for progression to Alzheimer’s dementia 2 Signature of future Alzheimer’s dementia comparable receiver operating characteristics to standard machine learning tools, yet a marked improvement in positive predictive value was achieved over the literature by selecting a high-specificity operating point. The multimodal signature can be readily applied for the enrichment of clinical trials. Keywords: Alzheimer’s disease; mild cognitive impairment; machine learning; neuroimaging; cognition Introduction Materials and Methods Data Data used in the preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database [17]. The ADNI was launched in 2003 as a public-private partnership, led by principal investigator Michael W. Weiner, MD. The primary goal of ADNI has been to test whether serial MRI, positron emission tomography (PET), other biological markers, and clinical and neuropsychological assessment can be combined to measure the progression of MCI and early AD. For up-to-date information, see [18]. We took baseline T1-weighted MRI scans from the ADNI1 (228 cognitively normal [CN] participants, 397 with MCI, 192 with AD) and ADNI2 (218 CN, 354 MCI, 103 AD) studies. For a detailed description of MRI acquisition details, see [19]. All participants gave informed consent to participate in these studies, which were approved by the research ethics committees of the institutions involved in data acquisition. Consent was obtained for data sharing and secondary analysis, the latter being approved by the ethics committee at the Centre de Recherche de l’Institut Universitaire de Gériatrie de Montréal. For the MCI groups, each individual must have had ≥36 months of follow-up for inclusion in our analysis. We also further stratified the MCI groups into Alzheimer’s disease (AD), a leading cause of dementia, is marked by the abnormal accumulation of amyloid β (Aβ) and hyperphosphorylated τ proteins in the brain, which leads to widespread neurodegeneration. AD has a long prodromal phase, and it has been difficult to predict which individuals will decline and experience AD dementia. While mild cognitive impairment (MCI) puts individuals at risk, only a fraction (33.6% on average) of patients with MCI will develop dementia within a period of 3 years or more, as shown in a meta-analysis of 41 studies [1]. Identifying patients with MCI who will progress to AD dementia with enough specificity has thus been a challenge for clinical trials [2]. This lack of prognostic power may be due to individual variability. Different clinical phenotypes have been described in which patients will exhibit distinct cognitive deficits [3]. Previous work has also characterized neuropathological subtypes based on the distribution of neurofibrillary tangles [4], which correspond well to distinct patterns of brain atrophy [5]. Different subtypes of brain atrophy have also been associated with different rates of progression to dementia [6]. The implications for prognosis are (...truncated)