.. .. Methods,

. .. Model-set-up,

R. .. Experiments, , p.119

. .. Conclusion, B. Samper-gonzalez-jorge, B. Ninon, F. Simona, L. Sabrina et al., Evgeniou Theodoros, and Colliot Olivier, for the ADNI & the AIBL, Reproducible evaluation of classification methods in Alzheimers disease: Framework and application to MRI and PET data, NeuroImage, vol.183, 2018.

C. Papers-?-lu-pascal and C. Olivier, Multilevel Modeling with Structured Penalties for Classification from Imaging Genetics data, 3rd MICCAI Workshop on Imaging Genetics, pp.230-240, 2017.

?. Pascal, C. Olivier, ;. Pascal, and C. Olivier, Multilevel Survival Analysis with Structured Penalties for Imaging Genetics data, Poster at GDR Statistiques & Santé, 2019.

?. Pascal and C. Olivier, A log-logistic survival model from multimodal data for prediction of Alzheimer's Disease. Poster at SAFJR, 2019.

?. Pascal and C. Olivier, Multilevel Modeling with Structured Penalties for Classification from Imaging Genetics data, Poster at ICM -IoN Workshop, 2017.

?. Pascal and C. Olivier, Multilevel Modeling with Structured Penalties for Classification from Imaging Genetics data. Oral presentation at MICGen, 2017.

, Simplified biological pathway leading to Alzheimer's Disease, p.24

, The bounding box represents the hippocampus region (reproduced from, Coronal slides of the T1-weighted MRI for normal brain, MCI brain and AD brain, 2017.

. Ng, PIB-PET scan for Normal brain versus AD brain (reproduced from, p.26, 2007.

D. .. Nucleus,

, Histogram of the number of visits at each month among MCI patients at baseline

. .. , Histogram of the conversion date T * and the censored date C, p.32

. Kaplan-meier, estimator for the survival function for MCI patients from ADNI1 dataset

;. .. Nelson, Aalen estimator for the cumulative hazard function (top) and estimated hazard function h with bandwidth of 6 months (bottom), p.34

, Two topics of research in imaging genetics

, 2 Four categories of analyses in imaging genetics, reproduced from, p.37, 2014.

, Real vs hypothetic distribution (N is the number of subjects, N A (resp. N a ) the number of subjects with allele A (resp. a), N CN (resp. N AD ) the number of subjects who are CN (resp. have AD))

. Perez, 38 2.5 (left) Main PLS eigen-component of V for the phenotype features. (right) Chromosome representativeness among the set of most informative SNPs associated to the main PLS eigen-component of U, Genome wide meta-analysis results in AD with 524,993 SNPs. Manhattan plot showing the p-values obtained in the meta-analysis. The end and beginning of a chromosome is denoted by the change of colour pattern of the SNPs (black, grey and brown dots), p.43, 2014.
URL : https://hal.archives-ouvertes.fr/hal-00306759

. Pathways and . .. Snps, 45 2.11 Illustration of ? learnt using the LASSO regression (top), and the Group LASSO regression where L = 3 (bottom). The LASSO regression selects only some variables, p.48, 2012.

. .. , The problem of overlapping genes/pathways, p.48

. .. P--mkl, , p.50

, Different type of censorships

. .. , Survival and hazard functions for exponential model, p.58

. .. Survival and . Steck, 59 3.4 Order graphs representing the ranking constraints. (a) No censored data and (b) with censored data. The empty circle represents a censored point. The points are arranged in the increasing value of their survival times with the lowest being at the bottom (reproduced from, p.62, 2008.

J. , Illness-death model (reproduced from, 2002.

. .. , The disease status y is predicted from imaging data x I and the parameters ? 0 (x G ), ?(x G ) (which are computed from genetic data x G ), p.73

. W-?-r-|i|×l-,-?-i-?-r-|i|-and-?-g-?-r-l, For brain region i and gene ?, W[i, ?] = max g?G ? |W[i, g]|, ? I [i] = |? I [i]| and ? G [?] = max g?G ? |? G [g]|. Only some brain regions are shown in this figure, p.79

=. .. Wx-g-+-?-i, Intercept ? I and slope W in the function ?(x G ), p.80

W. .. Rows,

W. .. Rows and . Marinescu, 84 5.2 TADPOLE Challenge design. Participants are required to train a predictive model on a training dataset (D1 and/or others) and make forecasts for different datasets (D2, D3) by the submission deadline, 2018.

. Marinescu, D3 is a subset of D2, which in turn is a subset of D1. Other non-ADNI data can also be used for training (reproduced from, Venn diagram of the ADNI datasets for training (D1), p.85, 2018.

.. .. Possible, , vol.87

.. .. D1, , p.88

, Estimators for the survival, cumulative hazard, and hazard functions, p.90

, Cumulative regression functions of A(t)

.. .. D4, , p.92

, Coefficients learnt for the Cox PH model, with confidence intervals, p.99

. .. Model, 100 6.3 Comparison between the survival function estimated using the Kaplan-Meier estimator and the log-logistic regression; and between the cumulative hazard estimated using the Nelson-Aalen estimator and the log-logistic regression

, Coefficients of the parameter vector ? of the logistic regression at fixed time t (left); Cumulative regression functions in the Aalen additive model, p.102

, AUC (middle), C-index (bottom), Assesment of the predictive value for the different models: Balanced Accuracy (top)

, Estimator of Kaplan-Meier of the survival function S(t) = P{T > t|APOE}, vol.104

.. .. ,

S. Effect-of-?-i-x-i-and-?-g-x-g-on, It can be seen that ? I x I only translates the curve of S(t) (for fixed ? G x G ), whereas ? G x G changes both the shape and translation of the curve of S(t)

. .. , 107 6.10 Estimated survival function S for the Kaplan Meier estimate and for the multilevel log-logistic model; Estimated hazard function h for the Nelson-Aalen estimated hazard and for the multilevel log-logistic model, p.109

, Median survival time, estimated survival function S for the Kaplan Meier estimate and for the multilevel log-logistic model

. ?-{50 and . .. 80}, , p.111

, ADNI1 Dataset: baseline survival function and hazard function, p.118

, 29 1.3 Descriptive statistics for variables measured at study entry of ADNI1 participants who are AD or CN at baseline, ? means that this feature is computed on a subset of ADNI1

, Descriptive statistics for variables measured at study entry of ADNI1 participants with mild cognitive impairment (MCI), ? means that this feature is computed on a subset of ADNI1

. .. , Classification results for different modalities and methods, p.78

.. .. Tadpole-timeline, 84 5.2 Descriptive statistics of D1, D2, D3 datasets (reproduced from https:// tadpole.grand-challenge.org/Results/)

. .. , Descriptive statistics of D4 dataset (219 subjects, reproduced from https: //tadpole.grand-challenge.org/Results/), p.92

, Ranking based on mAUC

. .. Bca,

, Number of positif labels and total number of labels throughout time, p.99

. .. , 100 6.3 Coefficients for the Cox model and log-logistic model, p.108

.. .. Auc-for-each-date,

, Results for different modalities and methods (mean value across the test folds ± standard deviation)

O. Aalen, A Model for Nonparametric Regression Analysis of Counting Processes, Mathematical Statistics and Probability Theory, pp.1-25, 1980.

A. , Recognition of Alzheimer's disease and Mild Cognitive Impairment with multimodal image-derived biomarkers and Multiple Kernel Learning, Neurocomputing, vol.220, pp.98-110, 2017.

D. Aiolli, F. Aiolli, and M. Donini, EasyMKL: a scalable multiple kernel learning algorithm, Neurocomputing, vol.169, pp.215-224, 2015.

A. , Cognitive variabilityA marker for incident MCI and AD: An analysis for the, 2016.

, Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring, vol.4, pp.47-55

[. Batmanghelich, Probabilistic Modeling of Imaging, Genetics and Diagnosis, IEEE Transactions on Medical Imaging, vol.35, issue.7, pp.1765-1779, 2016.

T. Beck, A. Beck, and M. Teboulle, Gradient-based algorithms with applications to signal-recovery problems, 2009.

N. Binder and M. Schumacher, Incidence of Dementia over Three Decades in the Framingham Heart Study, New England Journal of Medicine, vol.375, issue.1, pp.92-94, 2016.

. Bøvelstad, Survival prediction from clinico-genomic models -a comparative study, BMC Bioinformatics, vol.10, issue.1, p.413, 2009.

L. E. Chambless and G. Diao, Estimation of timedependent area under the ROC curve for long-term risk prediction, Statistics in Medicine, vol.25, issue.20, pp.3474-3486, 2006.

[. Chekouo, A Bayesian predictive model for imaging genetics with application to schizophrenia, The Annals of Applied Statistics, vol.10, issue.3, pp.1547-1571, 2016.

[. Cheng, , 2015.

, Domain Transfer Learning for MCI Conversion Prediction, IEEE transactions on biomedical engineering, vol.62, issue.7, pp.1805-1817

. Davatzikos, Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification, Neurobiology of Aging, vol.32, issue.12, pp.2322-2341, 2011.

[. Du, , 2014.

, A novel structure-aware sparse learning algorithm for brain imaging genetics. Medical image computing and computer-assisted intervention: MICCAI, International Conference on Medical Image Computing and Computer-Assisted Intervention, vol.17, pp.329-336

A. ;. Dubois, B. Dubois, and M. L. Albert, Amnestic MCI or prodromal Alzheimer's disease?, The Lancet Neurology, vol.3, issue.4, pp.246-248, 2004.

[. Dubois, Research criteria for the diagnosis of Alzheimer's disease: revising the NINCDS-ADRDA criteria, The Lancet. Neurology, vol.6, issue.8, pp.734-746, 2007.

[. Dubois, Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria, The Lancet. Neurology, vol.13, issue.6, pp.614-629, 2014.

[. Dubois, Preclinical Alzheimer's disease: Definition, natural history, and diagnostic criteria, Alzheimer's & Dementia: The Journal of the Alzheimer's Association, vol.12, issue.3, pp.292-323, 2016.

. Duyckaerts, Classification and basic pathology of Alzheimer disease, Acta Neuropathologica, vol.118, issue.1, pp.5-36, 2009.

[. Graf, Assessment and comparison of prognostic classification schemes for survival data, Statistics in Medicine, vol.18, pp.2529-2545, 1999.

M. Gönen-and-alpaydn-;-gönen and E. Alpaydn, Multiple Kernel Learning Algorithms, Journal of Machine Learning Research, vol.12, pp.2211-2268, 2011.

. Hampel, Perspective on future role of biological markers in clinical therapy trials of Alzheimer's disease: a long-range point of view beyond 2020, Biochemical Pharmacology, vol.88, issue.4, pp.426-449, 2014.

[. Hastie, Statistical Learning with Sparsity -The Lasso and Generalizations, Monographs on Statistics and Applied Probability, vol.143, 2015.

[. Jacob, Group Lasso with Overlap and Graph Lasso, Proceedings of the 26 th International Conference on Machine Learning, 2009.

[. Janssen, Alzheimer's disease due to an intronic presenilin-1 (PSEN1 intron 4) mutationA clinicopathological study, Brain, vol.123, issue.5, pp.894-907, 2000.

[. Joly, A penalized likelihood approach for an illness-death model with interval-censored data: application to age-specific incidence of dementia, Biostatistics, vol.3, issue.3, pp.433-443, 2002.
URL : https://hal.archives-ouvertes.fr/inserm-00182448

[. Kloft, lp-Norm Multiple Kernel Learning, Journal of Machine Learning Research, vol.12, pp.953-997, 2011.

[. Kohannim, Discovery and Replication of Gene Influences on Brain Structure Using LASSO Regression, and Alzheimers Disease Neuroimaging Initiative, vol.6, p.115, 2012.

[. Kohannim, Discovery and Replication of Gene Influences on Brain Structure Using LASSO Regression, and Alzheimers Disease Neuroimaging Initiative, vol.6, p.115, 2012.

L. Laird, N. M. Laird, and C. Lange, Introduction to Statistical Genetics and Background in Molecular Genetics, The Fundamentals of Modern Statistical Genetics, pp.1-13, 2011.

[. Lambert, , 2013.

B. Kunkle, M. L. Dunstan, A. Ruiz, M. T. Bihoreau, S. H. Choi et al.,

L. Yu, M. Tsolaki, P. Bossù, G. Spalletta, P. Proitsi et al., European Alzheimer's Disease Initiative (EADI), Genetic and Environmental Risk in Alzheimer's Disease, Alzheimer's Disease Genetic Consortium, Cohorts for Heart and Aging Research in Genomic Epidemiology

T. B. Harris, L. Fratiglioni, C. Holmes, R. F. De-bruijn, P. Passmore et al.,

L. S. Wang, J. F. Dartigues, R. Mayeux, C. Tzourio, A. Hofman et al.,

M. A. Launer, L. J. Farrer, L. A. Van-duijn, C. M. Van-broeckhoven, C. Moskvina et al.,

S. Seshadri, J. Williams, G. D. Schellenberg, A. , and P. , Meta-analysis of 74,046 individuals identifies 11 new susceptibility loci for Alzheimer's disease, Nature Genetics, vol.45, issue.12, pp.1452-1458, 2013.

[. Leffondré, Intervalcensored time-to-event and competing risk with death: is the illness-death model more accurate than the Cox model?, International Journal of Epidemiology, vol.42, issue.4, pp.1177-1186, 2013.

[. Li, A prognostic model of Alzheimer's disease relying on multiple longitudinal measures and time-toevent data, 2017.

C. ;. Liu, J. Liu, and V. D. Calhoun, A review of multivariate analyses in imaging genetics, Frontiers in Neuroinformatics, vol.8, 2014.

[. Liu, Prediction of Mild Cognitive Impairment Conversion Using a Combination of Independent Component Analysis and the Cox Model, Frontiers in Human Neuroscience, vol.11, p.33, 2017.

[. Lorenzi, Partial least squares modelling for imaginggenetics in Alzheimer's disease: Plausibility and generalization, IEEE 13th International Symposium on Biomedical Imaging (ISBI), pp.838-841, 2016.

[. Mahley, Apolipoprotein E4: A causative factor and therapeutic target in neuropathology, including Alzheimers disease, Proceedings of the National Academy of Sciences, vol.103, issue.15, pp.5641-5643, 2006.

[. Marinescu, TADPOLE Challenge: Prediction of Longitudinal Evolution in Alzheimer's Disease, 2018.

[. Mckhann, Clinical diagnosis of Alzheimer's disease: report of the NINCDS-ADRDA Work Group under the auspices of Department of Health and Human Services Task Force on Alzheimer's Disease, Neurology, vol.34, issue.7, pp.939-944, 1984.

[. Mckhann, The diagnosis of dementia due to Alzheimer's disease: recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease, Alzheimer's & Dementia: The Journal of the Alzheimer's Association, vol.7, issue.3, pp.263-269, 2011.

[. Meier, The group lasso for logistic regression, pp.53-71, 2008.

M. , Y. ;. Ming, Y. Yi, and L. , Model selection and estimation in regression with grouped variables, J. R. Statist. Soc. B, vol.68, pp.49-67, 2006.

. Ng, Visual Assessment Versus Quantitative Assessment of 11c-PIB PET and 18f-FDG PET for Detection of Alzheimer's Disease, 2007.

[. Peng, Structured Sparse Kernel Learning for Imaging Genetics Based Alzheimers Disease Diagnosis, MICCAI 2016, number 9901 in Lecture Notes in Computer Science, pp.70-78, 2016.

[. Perez, Overrepresentation of Glutamate Signaling in Alzheimer's Disease: Network-Based Pathway Enrichment Using Meta-Analysis of Genome-Wide Association Studies, PloS one, vol.9, p.95413, 2014.

[. Rathore, A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer's disease and its prodromal stages, NeuroImage, vol.155, pp.530-548, 2017.

. Samper-gonzalez, Reproducible evaluation of methods for predicting progression to Alzheimer's disease from clinical and neuroimaging data, 2019.

, page 109490V. International Society for Optics and Photonics, vol.10949

. Samper-gonzález, Reproducible evaluation of classification methods in Alzheimer's disease: Framework and application to MRI and PET data, NeuroImage, vol.183, pp.504-521, 2018.

[. Satizabal, Incidence of Dementia over Three Decades in the Framingham Heart Study, New England Journal of Medicine, vol.374, issue.6, pp.523-532, 2016.

. Scheltens, Alzheimer's disease and normal ageing: diagnostic value and neuropsychological correlates, Neurosurgery, and Psychiatry, vol.55, issue.10, pp.967-972, 1992.

[. Silver, Identification of gene pathways implicated in Alzheimer's disease using longitudinal imaging phenotypes with sparse regression, NeuroImage, vol.63, issue.3, pp.1681-1694, 2012.

M. Silver and G. Montana, Fast Identification of Biological Pathways Associated with a Quantitative Trait Using Group Lasso with Overlaps. Statistical applications in genetics and molecular biology, vol.11, p.7, 2012.

[. Sim, Random Forests on Distance Matrices for Imaging Genetics Studies, 2008.

J. C. Platt, D. Koller, Y. Singer, and S. T. Roweis, Advances in Neural Information Processing Systems, vol.20, pp.1209-1216

. Der-laan, Super Learner, 2007.

. Van-houwelingen, Cross-validated Cox regression on microarray gene expression data, pp.3201-3216, 2006.

. Houwelingen, H. C. Putter-;-van-houwelingen, and H. Putter, Dynamic Prediction in Clinical Survival Analysis, volume Monographs on Statistics and Applied Probability 123, 2012.

[. Wang, Identifying quantitative trait loci via group-sparse multitask regression and feature selection: an imaging genetics study of the ADNI cohort, Bioinformatics, vol.28, issue.2, pp.229-237, 2012.

[. Yu, Multiple Imputation for Estimating the Risk of Developing Dementia and Its Impact on Survival, Biometrical journal. Biometrische Zeitschrift, vol.52, issue.5, pp.616-627, 2010.

[. Yu, Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors, Shawe, 2011.

J. Taylor, R. S. Zemel, P. L. Bartlett, F. Pereira, and K. Q. Weinberger, Advances in Neural Information Processing Systems, vol.24, pp.1845-1853