Charting Disease Trajectories from Isolated REM Sleep Behavior Disorder to Parkinson's Disease.

BACKGROUND: Clinical presentation and progression dynamics are variable in patients with Parkinson's disease (PD). Disease course mapping is an innovative disease modelling technique that summarizes the range of possible disease trajectories and estimates dimensions related to onset, sequence, and speed of progression of disease markers. OBJECTIVE: To propose a disease course map for PD and investigate progression profiles in patients with or without rapid eye movement sleep behavioral disorders (RBD). METHODS: Data of 919 PD patients and 88 isolated RBD patients from three independent longitudinal cohorts were analyzed (follow-up duration = 5.1; 95% confidence interval, 1.1-8.1] years). Disease course map was estimated by using eight clinical markers (motor and non-motor symptoms) and four imaging markers (dopaminergic denervation). RESULTS: PD course map showed that the first changes occurred in the contralateral putamen 13 years before diagnosis, followed by changes in motor symptoms, dysautonomia, sleep-all before diagnosis-and finally cognitive decline at the time of diagnosis. The model showed earlier disease onset, earlier non-motor and later motor symptoms, more rapid progression of cognitive decline in PD patients with RBD than PD patients without RBD. This pattern was even more pronounced in patients with isolated RBD with early changes in sleep, followed by cognition and non-motor symptoms and later changes in motor symptoms. CONCLUSIONS: Our findings are consistent with the presence of distinct patterns of progression between patients with and without RBD. Understanding heterogeneity of PD progression is key to decipher the underlying pathophysiology and select homogeneous subgroups of patients for precision medicine. © 2023 International Parkinson and Movement Disorder Society.

Association Between Diseases and Symptoms Diagnosed in Primary Care and the Subsequent Specific Risk of Multiple Sclerosis.

BACKGROUND AND OBJECTIVES: Previous studies have reported a possible prodrome in multiple sclerosis (MS) defined by nonspecific symptoms including mood disorder or genitourinary symptoms and increased health care use detected several years before diagnosis. This study aimed to evaluate agnostically the associations between diseases and symptoms diagnosed in primary care and the risk of MS relative to controls and 2 other autoimmune inflammatory diseases with similar population characteristics, namely lupus and Crohn disease (CD). METHODS: A case-control study was conducted using electronic health records from the Health Improvement Network database in the United Kingdom and France. We agnostically assessed the associations between 113 diseases and symptoms in the 5 years before and after diagnosis in patients with subsequent diagnosis of MS. Individuals with a diagnosis of MS were compared with individuals without MS and individuals with 2 other autoimmune diseases, CD and lupus. RESULTS: The study population consisted of patients with MS (n = 20,174), patients without MS (n = 54,790), patients with CD (n = 30,477), and patients with lupus (n = 7,337). Twelve ICD-10 codes were significantly positively associated with the risk of MS compared with controls without MS. After considering ICD-10 codes suggestive of neurologic symptoms as the first diagnosis of MS, 5 ICD-10 codes remained significantly associated with MS: depression (UK: odds ratio 1.22, 95% CI 1.11-1.34), sexual dysfunction (1.47, 1.11-1.95), constipation (1.5, 1.27-1.78), cystitis (1.21, 1.05-1.39), and urinary tract infections of unspecified site (1.38, 1.18-1.61). However, none of these conditions was selectively associated with MS in comparisons with both lupus and CD. All 5 ICD-10 codes identified were still associated with MS during the 5 years after diagnosis. DISCUSSION: We identified 5 health conditions associated with subsequent MS diagnosis, which may be considered not only prodromal but also early-stage symptoms. However, these health conditions overlap with prodrome of 2 other autoimmune diseases; hence, they lack specificity to MS.

Interaction of sex and onset site on the disease trajectory of amyotrophic lateral sclerosis.

BACKGROUND: Studies showed the impact of sex and onset site (spinal or bulbar) on disease onset and survival in ALS. However, they mainly result from cross-sectional or survival analysis, and the interaction of sex and onset site on the different proxies of disease trajectory has not been fully investigated. METHODS: We selected all patients with repeated observations in the PRO-ACT database. We divided them into four groups depending on their sex and onset site. We estimated a multivariate disease progression model, named ALS Course Map, to investigate the combined temporal changes of the four sub-scores of the revised ALS functional rating scale (ALSFRSr), the forced vital capacity (FVC), and the body mass index (BMI). We then compared the progression rate, the estimated age at onset, and the relative progression of the outcomes across each group. RESULTS: We included 1438 patients from the PRO-ACT database. They were 51% men with spinal onset, 12% men with bulbar onset, 26% women with spinal onset, and 11% women with bulbar onset. We showed a significant influence of both sex and onset site on the ALSFRSr progression. The BMI decreased 8.9 months earlier (95% CI [3.9, 13.8]) in women than men, after correction for the onset site. Among patients with bulbar onset, FVC was impaired 2.6 months earlier (95% CI [0.6, 4.6]) in women. CONCLUSION: Using a multivariable disease modelling approach, we showed that sex and onset site are important drivers of the progression of motor function, BMI, and FVC decline.

Impact of sex and APOE-ε4 genotype on patterns of regional brain atrophy in Alzheimer's disease and healthy aging.

Alzheimer's Disease (AD) is a heterogeneous disease that disproportionately affects women and people with the APOE-ε4 susceptibility gene. We aim to describe the not-well-understood influence of both risk factors on the dynamics of brain atrophy in AD and healthy aging. Regional cortical thinning and brain atrophy were modeled over time using non-linear mixed-effect models and the FreeSurfer software with t1-MRI scans from the Alzheimer's Disease Neuroimaging Initiative (N = 1,502 subjects, 6,728 images in total). Covariance analysis was used to disentangle the effect of sex and APOE genotype on the regional onset age and pace of atrophy, while correcting for educational level. A map of the regions mostly affected by neurodegeneration is provided. Results were confirmed on gray matter density data from the SPM software. Women experience faster atrophic rates in the temporal, frontal, parietal lobes and limbic system and earlier onset in the amygdalas, but slightly later onset in the postcentral and cingulate gyri as well as all regions of the basal ganglia and thalamus. APOE-ε4 genotypes leads to earlier and faster atrophy in the temporal, frontal, parietal lobes, and limbic system in AD patients, but not in healthy patients. Higher education was found to slightly delay atrophy in healthy patients, but not for AD patients. A cohort of amyloid positive patients with MCI showed a similar impact of sex as in the healthy cohort, while APOE-ε4 showed similar associations as in the AD cohort. Female sex is as strong a risk factor for AD as APOE-ε4 genotype regarding neurodegeneration. Women experience a sharper atrophy in the later stages of the disease, although not a significantly earlier onset. These findings may have important implications for the development of targeted intervention.

Multivariate disease progression modeling with longitudinal ordinal data.

Disease modeling is an essential tool to describe disease progression and its heterogeneity across patients. Usual approaches use continuous data such as biomarkers to assess progression. Nevertheless, categorical or ordinal data such as item responses in questionnaires also provide insightful information about disease progression. In this work, we propose a disease progression model for ordinal and categorical data. We built it on the principles of disease course mapping, a technique that uniquely describes the variability in both the dynamics of progression and disease heterogeneity from multivariate longitudinal data. This extension can also be seen as an attempt to bridge the gap between longitudinal multivariate models and the field of item response theory. Application to the Parkinson's progression markers initiative cohort illustrates the benefits of our approach: a fine-grained description of disease progression at the item level, as compared to the aggregated total score, together with improved predictions of the patient's future visits. The analysis of the heterogeneity across individual trajectories highlights known disease trends such as tremor dominant or postural instability and gait difficulties subtypes of Parkinson's disease.

A Comparison Between Early Presentation of Dementia with Lewy Bodies, Alzheimer's Disease, and Parkinson's Disease: Evidence from Routine Primary Care and UK Biobank Data.

OBJECTIVE: The purpose of this study was to simultaneously contrast prediagnostic clinical characteristics of individuals with a final diagnosis of dementia with Lewy Bodies (DLB), Parkinson's disease (PD), and Alzheimer's disease (AD) compared with controls without neurodegenerative disorders. METHODS: Using the longitudinal THIN database in the United Kingdom, we tested the association of each neurodegenerative disorder with a selected list of symptoms and broad families of treatments, and compared the associations between disorders to detect disease-specific effects. We replicated the main findings in the UK Biobank. RESULTS: We used data of 28,222 patients with PD, 20,214 with AD, 4,682 with DLB, and 20,214 healthy controls. All neurodegenerative disorders were significantly associated with the presence of multiple clinical characteristics before their diagnosis, including sleep disorders, falls, psychiatric symptoms, and autonomic dysfunctions. When comparing patients with DLB with patients with PD and patients with AD patients, falls, psychiatric symptoms, and autonomic dysfunction were all more strongly associated with DLB in the 5 years preceding the first neurodegenerative diagnosis. The use of statins was lower in patients who developed PD and higher in patients who developed DLB compared to patients with AD. In patients with PD, the use of statins was associated with the development of dementia in the 5 years following PD diagnosis. INTERPRETATION: Prediagnostic presentations of falls, psychiatric symptoms, and autonomic dysfunctions were more strongly associated with DLB than PD and AD. This study also suggests that although several associations with medications are similar in neurodegenerative disorders, statin usage is negatively associated with PD but positively with DLB and AD as well as development of dementia in PD. ANN NEUROL 2023;94:259-270.

Forecasting individual progression trajectories in Alzheimer's disease.

The anticipation of progression of Alzheimer's disease (AD) is crucial for evaluations of secondary prevention measures thought to modify the disease trajectory. However, it is difficult to forecast the natural progression of AD, notably because several functions decline at different ages and different rates in different patients. We evaluate here AD Course Map, a statistical model predicting the progression of neuropsychological assessments and imaging biomarkers for a patient from current medical and radiological data at early disease stages. We tested the method on more than 96,000 cases, with a pool of more than 4,600 patients from four continents. We measured the accuracy of the method for selecting participants displaying a progression of clinical endpoints during a hypothetical trial. We show that enriching the population with the predicted progressors decreases the required sample size by 38% to 50%, depending on trial duration, outcome, and targeted disease stage, from asymptomatic individuals at risk of AD to subjects with early and mild AD. We show that the method introduces no biases regarding sex or geographic locations and is robust to missing data. It performs best at the earliest stages of disease and is therefore highly suitable for use in prevention trials.

Forecasting individual progression trajectories in Huntington disease enables more powered clinical trials.

Variability in neurodegenerative disease progression poses great challenges for the evaluation of potential treatments. Identifying the persons who will experience significant progression in the short term is key for the implementation of trials with smaller sample sizes. We apply here disease course mapping to forecast biomarker progression for individual carriers of the pathological CAG repeat expansions responsible for Huntington disease. We used data from two longitudinal studies (TRACK-HD and TRACK-ON) to synchronize temporal progression of 15 clinical and imaging biomarkers from 290 participants with Huntington disease. We used then the resulting HD COURSE MAP to forecast clinical endpoints from the baseline data of 11,510 participants from ENROLL-HD, an external validation cohort. We used such forecasts to select participants at risk for progression and compute the power of trials for such an enriched population. HD COURSE MAP forecasts biomarkers 5 years after the baseline measures with a maximum mean absolute error of 10 points for the total motor score and 2.15 for the total functional capacity. This allowed reducing sample sizes in trial up to 50% including participants with a higher risk for progression ensuring a more homogeneous group of participants.

Comparison of Clinical Profiles and Mortality Outcomes Between Influenza and COVID-19 Patients Invasively Ventilated in the ICU: A Retrospective Study From All Paris Public Hospitals From 2016 to 2021.

Studies comparing outcomes of ICU patients admitted for either COVID-19 or seasonal influenza are limited. Our objective was to describe baseline clinical profiles, care procedures, and mortality outcomes by infection status (influenza vs COVID-19) of patients who received invasive mechanical ventilation in the ICU. DESIGN: Retrospective observational study. SETTING: Data were extracted from the Assistance Publique-Hopitaux de Paris database from September 1, 2016, to April 20, 2021. It includes data from the 39 university hospitals. PATIENTS: A total of 752 influenza adult patients and 3,465 COVID-19 adult patients received invasive mechanical ventilation in one of the ICUs of the Paris area university hospitals, France. INTERVENTION: The characteristics and outcome by infection status were compared. Factors associated with mortality were assessed using Cox proportional hazard models after controlling for potential confounders, including infection status. MEASUREMENTS AND MAIN RESULTS: The median age at admission to the ICU was 67 (interquartile range [IQR], 57-77) and 63 yr (IQR, 54-71 yr) for influenza and COVID-19 patients, respectively. At ICU admission, COVID-19 patients were more frequently obese, more frequently had diabetes mellitus or high blood pressure, and were less likely to have chronic heart failure, chronic respiratory disease, chronic kidney failure, or active cancer than influenza patients. The overall survival at 90 days was 57% for COVID-19 patients and 66% for influenza patients (p < 0.001). In a multivariable Cox model, higher age, organ transplant, severe acute respiratory syndrome coronavirus 2 infection, and chronic kidney failure were associated with shorter survival, whereas obesity and high blood pressure were associated with longer survival after invasive ventilation. CONCLUSIONS: COVID-19 and influenza patients requiring mechanical ventilation in the ICU differed by many characteristics. COVID-19 patients showed lower survival independently of potential confounders.

Identifying health conditions associated with Alzheimer's disease up to 15 years before diagnosis: an agnostic study of French and British health records.

BACKGROUND: The identification of modifiable risk factors for Alzheimer's disease is paramount for early prevention and the targeting of new interventions. We aimed to assess the associations between health conditions diagnosed in primary care and the risk of incident Alzheimer's disease over time, up to 15 years before a first Alzheimer's disease diagnosis. METHODS: In this agnostic study of French and British health records, data from 20 214 patients with Alzheimer's disease in the UK and 19 458 patients with Alzheimer's disease in France were extracted from The Health Improvement Network database. We considered data recorded from Jan 1, 1996, to March 31, 2020 in the UK and from Jan 4, 1998, to Feb 20, 2019, in France. For each Alzheimer's disease case, a control was randomly assigned after matching for sex and age at last visit. We agnostically tested the associations between 123 different diagnoses of the International Classification of Diseases, 10th revision, extracted from health records, and Alzheimer's disease, by running a conditional logistic regression to account for matching of cases and controls. We focused on three time periods before diagnosis of Alzheimer's disease, to separate risk factors from early symptoms and comorbidities. FINDINGS: Unadjusted odds ratios (ORs) and 95% CIs for the association between Alzheimer's disease and various health conditions were estimated, and p values were corrected for multiple comparisons. In both the British and French studies, ten health conditions were significantly positively associated with increased Alzheimer's disease risk, in a window of exposure from 2-10 years before Alzheimer's disease diagnosis, comprising major depressive disorder (UK OR 1·34, 95% CI 1·23-1·46; France OR 1·73, 1·57-1·91), anxiety (UK OR 1·36, 1·25-1·47; France OR 1·50, 1·36-1·65), reaction to severe stress and adjustment disorders (UK OR 1·40, 1·24-1·59; France OR 1·83, 1·55-2·15), hearing loss (UK OR 1·19, 1·11-1·28; France OR 1·51, 1·21-1·89), constipation (UK OR 1·31, 1·22-1·41; France OR 1·59, 1·44-1·75), spondylosis (UK OR 1·26, 1·14-1·39; France OR 1·62, 1·44-1·81), abnormal weight loss (UK OR 1·47, 1·33-1·63; France OR 1·88, 1·56-2·26), malaise and fatigue (UK OR 1·23, 1·14-1·32; France OR 1·59, 1·46-1·73), memory loss (UK OR 7·63, 6·65-8·76; France OR 4·41, 3·07-6·34), and syncope and collapse (UK OR 1·23, 1·10-1·37; France OR 1·57, 1·26-1·96). Depression was the first comorbid condition associated with Alzheimer's disease, appearing at least 9 years before the first clinical diagnosis, followed by anxiety, constipation, and abnormal weight loss. INTERPRETATION: These results from two independent primary care databases provide new evidence on the temporality of risk factors and early signs of Alzheimer's disease that are observable at the general practitioner level. These results could guide the implementation of new primary and secondary prevention policies. FUNDING: Agence Nationale de la Recherche.

Benchmarking off-the-shelf statistical shape modeling tools in clinical applications.

Statistical shape modeling (SSM) is widely used in biology and medicine as a new generation of morphometric approaches for the quantitative analysis of anatomical shapes. Technological advancements of in vivo imaging have led to the development of open-source computational tools that automate the modeling of anatomical shapes and their population-level variability. However, little work has been done on the evaluation and validation of such tools in clinical applications that rely on morphometric quantifications(e.g., implant design and lesion screening). Here, we systematically assess the outcome of widely used, state-of-the-art SSM tools, namely ShapeWorks, Deformetrica, and SPHARM-PDM. We use both quantitative and qualitative metrics to evaluate shape models from different tools. We propose validation frameworks for anatomical landmark/measurement inference and lesion screening. We also present a lesion screening method to objectively characterize subtle abnormal shape changes with respect to learned population-level statistics of controls. Results demonstrate that SSM tools display different levels of consistencies, where ShapeWorks and Deformetrica models are more consistent compared to models from SPHARM-PDM due to the groupwise approach of estimating surface correspondences. Furthermore, ShapeWorks and Deformetrica shape models are found to capture clinically relevant population-level variability compared to SPHARM-PDM models.

Clinica: An Open-Source Software Platform for Reproducible Clinical Neuroscience Studies.

We present Clinica (www.clinica.run), an open-source software platform designed to make clinical neuroscience studies easier and more reproducible. Clinica aims for researchers to (i) spend less time on data management and processing, (ii) perform reproducible evaluations of their methods, and (iii) easily share data and results within their institution and with external collaborators. The core of Clinica is a set of automatic pipelines for processing and analysis of multimodal neuroimaging data (currently, T1-weighted MRI, diffusion MRI, and PET data), as well as tools for statistics, machine learning, and deep learning. It relies on the brain imaging data structure (BIDS) for the organization of raw neuroimaging datasets and on established tools written by the community to build its pipelines. It also provides converters of public neuroimaging datasets to BIDS (currently ADNI, AIBL, OASIS, and NIFD). Processed data include image-valued scalar fields (e.g., tissue probability maps), meshes, surface-based scalar fields (e.g., cortical thickness maps), or scalar outputs (e.g., regional averages). These data follow the ClinicA Processed Structure (CAPS) format which shares the same philosophy as BIDS. Consistent organization of raw and processed neuroimaging files facilitates the execution of single pipelines and of sequences of pipelines, as well as the integration of processed data into statistics or machine learning frameworks. The target audience of Clinica is neuroscientists or clinicians conducting clinical neuroscience studies involving multimodal imaging, and researchers developing advanced machine learning algorithms applied to neuroimaging data.

Changes in the use of psychotropic drugs during the course of Alzheimer's disease: A large-scale longitudinal study of French medical records.

INTRODUCTION: We aim to understand how patients with Alzheimer's disease (AD) are treated by identifying in a longitudinal fashion the late-life changes in patients' medical history that precede and follow AD diagnosis. METHODS: We use prescription history of 34,782 patients followed between 1996 and 2019 by French general practitioners. We compare patients with an AD diagnosis, patients with mild cognitive impairment (MCI), and patients free of mental disorders. We use a generalized mixed-effects model to study the longitudinal changes in the prescription of eight drug types for a period 15 years before diagnosis and 10 years after. RESULTS: In the decades preceding diagnosis, we find that future AD patients are treated significantly more than MCI patients with most psychotropic drugs and that most studied drugs are increasingly prescribed with age. At the time of diagnosis, all psychotropic drugs except benzodiazepines show a significant increase in prescription, while other drugs are significantly less prescribed. In the 10 years after diagnosis, nearly all categories of drugs are less and less prescribed including antidementia drugs. DISCUSSION: Pre-diagnosis differences between future AD patients and MCI patients may indicate that subtle cognitive changes are recognized and treated as psychiatric symptoms. The disclosure of AD diagnosis drastically changes patients' care, priority being given to the management of psychiatric symptoms. The decrease of all prescriptions in the late stages may reflect treatment discontinuation and simplification of therapeutic procedures. This study therefore provides new insights into the medical practices for management of AD.

A machine learning approach to screen for preclinical Alzheimer's disease.

Combining multimodal biomarkers could help in the early diagnosis of Alzheimer's disease (AD). We included 304 cognitively normal individuals from the INSIGHT-preAD cohort. Amyloid and neurodegeneration were assessed on 18F-florbetapir and 18F-fluorodeoxyglucose PET, respectively. We used a nested cross-validation approach with non-invasive features (electroencephalography [EEG], APOE4 genotype, demographic, neuropsychological and MRI data) to predict: 1/ amyloid status; 2/ neurodegeneration status; 3/ decline to prodromal AD at 5-year follow-up. Importantly, EEG was most strongly predictive of neurodegeneration, even when reducing the number of channels from 224 down to 4, as 4-channel EEG best predicted neurodegeneration (negative predictive value [NPV] = 82%, positive predictive value [PPV] = 38%, 77% specificity, 45% sensitivity). The combination of demographic, neuropsychological data, APOE4 and hippocampal volumetry most strongly predicted amyloid (80% NPV, 41% PPV, 70% specificity, 58% sensitivity) and most strongly predicted decline to prodromal AD at 5 years (97% NPV, 14% PPV, 83% specificity, 50% sensitivity). Thus, machine learning can help to screen patients at high risk of preclinical AD using non-invasive and affordable biomarkers.

Anomaly detection for the individual analysis of brain PET images.

Purpose: In clinical practice, positron emission tomography (PET) images are mostly analyzed visually, but the sensitivity and specificity of this approach greatly depend on the observer's experience. Quantitative analysis of PET images would alleviate this problem by helping define an objective limit between normal and pathological findings. We present an anomaly detection framework for the individual analysis of PET images. Approach: We created subject-specific abnormality maps that summarize the pathology's topographical distribution in the brain by comparing the subject's PET image to a model of healthy PET appearance that is specific to the subject under investigation. This model was generated from demographically and morphologically matched PET scans from a control dataset. Results: We generated abnormality maps for healthy controls, patients at different stages of Alzheimer's disease and with different frontotemporal dementia syndromes. We showed that no anomalies were detected for the healthy controls and that the anomalies detected from the patients with dementia coincided with the regions where abnormal uptake was expected. We also validated the proposed framework using the abnormality maps as inputs of a classifier and obtained higher classification accuracies than when using the PET images themselves as inputs. Conclusions: The proposed method was able to automatically locate and characterize the areas characteristic of dementia from PET images. The abnormality maps are expected to (i) help clinicians in their diagnosis by highlighting, in a data-driven fashion, the pathological areas, and (ii) improve the interpretability of subsequent analyses, such as computer-aided diagnosis or spatiotemporal modeling.

AD Course Map charts Alzheimer's disease progression.

Alzheimer's disease (AD) is characterized by the progressive alterations seen in brain images which give rise to the onset of various sets of symptoms. The variability in the dynamics of changes in both brain images and cognitive impairments remains poorly understood. This paper introduces AD Course Map a spatiotemporal atlas of Alzheimer's disease progression. It summarizes the variability in the progression of a series of neuropsychological assessments, the propagation of hypometabolism and cortical thinning across brain regions and the deformation of the shape of the hippocampus. The analysis of these variations highlights strong genetic determinants for the progression, like possible compensatory mechanisms at play during disease progression. AD Course Map also predicts the patient's cognitive decline with a better accuracy than the 56 methods benchmarked in the open challenge TADPOLE. Finally, AD Course Map is used to simulate cohorts of virtual patients developing Alzheimer's disease. AD Course Map offers therefore new tools for exploring the progression of AD and personalizing patients care.

Understanding the Variability in Graph Data Sets through Statistical Modeling on the Stiefel Manifold.

Network analysis provides a rich framework to model complex phenomena, such as human brain connectivity. It has proven efficient to understand their natural properties and design predictive models. In this paper, we study the variability within groups of networks, i.e., the structure of connection similarities and differences across a set of networks. We propose a statistical framework to model these variations based on manifold-valued latent factors. Each network adjacency matrix is decomposed as a weighted sum of matrix patterns with rank one. Each pattern is described as a random perturbation of a dictionary element. As a hierarchical statistical model, it enables the analysis of heterogeneous populations of adjacency matrices using mixtures. Our framework can also be used to infer the weight of missing edges. We estimate the parameters of the model using an Expectation-Maximization-based algorithm. Experimenting on synthetic data, we show that the algorithm is able to accurately estimate the latent structure in both low and high dimensions. We apply our model on a large data set of functional brain connectivity matrices from the UK Biobank. Our results suggest that the proposed model accurately describes the complex variability in the data set with a small number of degrees of freedom.

Reproducible Evaluation of Diffusion MRI Features for Automatic Classification of Patients with Alzheimer's Disease.

Diffusion MRI is the modality of choice to study alterations of white matter. In past years, various works have used diffusion MRI for automatic classification of Alzheimer's disease. However, classification performance obtained with different approaches is difficult to compare because of variations in components such as input data, participant selection, image preprocessing, feature extraction, feature rescaling (FR), feature selection (FS) and cross-validation (CV) procedures. Moreover, these studies are also difficult to reproduce because these different components are not readily available. In a previous work (Samper-González et al. 2018), we propose an open-source framework for the reproducible evaluation of AD classification from T1-weighted (T1w) MRI and PET data. In the present paper, we first extend this framework to diffusion MRI data. Specifically, we add: conversion of diffusion MRI ADNI data into the BIDS standard and pipelines for diffusion MRI preprocessing and feature extraction. We then apply the framework to compare different components. First, FS has a positive impact on classification results: highest balanced accuracy (BA) improved from 0.76 to 0.82 for task CN vs AD. Secondly, voxel-wise features generally gives better performance than regional features. Fractional anisotropy (FA) and mean diffusivity (MD) provided comparable results for voxel-wise features. Moreover, we observe that the poor performance obtained in tasks involving MCI were potentially caused by the small data samples, rather than by the data imbalance. Furthermore, no extensive classification difference exists for different degree of smoothing and registration methods. Besides, we demonstrate that using non-nested validation of FS leads to unreliable and over-optimistic results: 5% up to 40% relative increase in BA. Lastly, with proper FR and FS, the performance of diffusion MRI features is comparable to that of T1w MRI. All the code of the framework and the experiments are publicly available: general-purpose tools have been integrated into the Clinica software package ( www.clinica.run ) and the paper-specific code is available at: https://github.com/aramis-lab/AD-ML .

Gaussian Graphical Model Exploration and Selection in High Dimension Low Sample Size Setting.

Gaussian graphical models (GGM) are often used to describe the conditional correlations between the components of a random vector. In this article, we compare two families of GGM inference methods: the nodewise approach and the penalised likelihood maximisation. We demonstrate on synthetic data that, when the sample size is small, the two methods produce graphs with either too few or too many edges when compared to the real one. As a result, we propose a composite procedure that explores a family of graphs with a nodewise numerical scheme and selects a candidate among them with an overall likelihood criterion. We demonstrate that, when the number of observations is small, this selection method yields graphs closer to the truth and corresponding to distributions with better KL divergence with regards to the real distribution than the other two. Finally, we show the interest of our algorithm on two concrete cases: first on brain imaging data, then on biological nephrology data. In both cases our results are more in line with current knowledge in each field.

Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review.

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15% of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.