scholarly journals Mitigating site effects in covariance for machine learning in neuroimaging data

2021 ◽  
Author(s):  
Andrew A. Chen ◽  
Joanne C. Beer ◽  
Nicholas J. Tustison ◽  
Philip A. Cook ◽  
Russell T. Shinohara ◽  
...  
Keyword(s):  
Machine Learning ◽  
Site Effects ◽  
Neuroimaging Data

scholarly journals Quantifying performance of machine learning methods for neuroimaging data

NeuroImage ◽  
2019 ◽  
Vol 199 ◽  
pp. 351-365 ◽  
Author(s):  
Lee Jollans ◽  
Rory Boyle ◽  
Eric Artiges ◽  
Tobias Banaschewski ◽  
Sylvane Desrivières ◽  
...  
Keyword(s):  
Machine Learning ◽  
Learning Methods ◽  
Machine Learning Methods ◽  
Neuroimaging Data

scholarly journals Using Machine Learning to Predict Dementia from Neuropsychiatric Symptom and Neuroimaging Data

2020 ◽  
Vol 75 (1) ◽  
pp. 277-288 ◽  
Author(s):  
Sascha Gill ◽  
Pauline Mouches ◽  
Sophie Hu ◽  
Deepthi Rajashekar ◽  
Frank P. MacMaster ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neuropsychiatric Symptom ◽  
Neuroimaging Data

scholarly journals Accommodating site variation in neuroimaging data using hierarchical and Bayesian models

2021 ◽  
Author(s):  
Johanna M. M. Bayer ◽  
Richard Dinga ◽  
Seyed Mostafa Kia ◽  
Akhil R. Kottaram ◽  
Thomas Wolfers ◽  
...  
Keyword(s):  
Bayesian Model ◽  
Site Effects ◽  
Data Exchange ◽  
Data Sets ◽  
Hierarchical Bayesian ◽  
Hierarchical Bayesian Model ◽  
Data Set ◽  
Neuroimaging Data ◽  
Normative Models ◽  
Age And Sex

AbstractThe potential of normative modeling to make individualized predictions has led to structural neu-roimaging results that go beyond the case-control approach. However, site effects, often con-founded with variables of interest in a complex manner, induce a bias in estimates of normative models, which has impeded the application of normative models to large multi-site neuroimaging data sets. In this study, we suggest accommodating for these site effects by including them as random effects in a hierarchical Bayesian model. We compare the performance of a linear and a non-linear hierarchical Bayesian model in modeling the effect of age on cortical thickness. We used data of 570 healthy individuals from the ABIDE (autism brain imaging data exchange, http://preprocessed-connectomes-project.org/abide/) data set in our experiments. We compare the proposed method to several harmonization techniques commonly used to deal with additive and multiplicative site effects, including regressing out site and harmonizing for site with ComBat, both with and without explicitly preserving variance related to age and sex as biological variation of interest. In addition, we make predictions from raw data, in which site has not been accommodated for. The proposed hierarchical Bayesian method shows the best performance according to multiple metrics. Performance is particularly bad for the regression model and the ComBat model when age and sex are not explicitly modeled. In addition, the predictions of those models are noticeably poorly calibrated, suffering from a loss of more than 90 % of the original variance. From these results we conclude that harmonization techniques like regressing out site and ComBat do not sufficiently accommodate for multi-site effects in pooled neuroimaging data sets. Our results show that the complex interaction between site and variables of interest is likely to be underestimated by those tools. One consequence is that harmonization techniques removed too much variance, which is undesirable and may have unpredictable consequences for subsequent analysis. Our results also show that this can be mostly avoided by explicitly modeling site as part of a hierarchical Bayesian Model. We discuss the potential of z-scores derived from normative models to be used as site corrected variables and of our method as site correction tool.

scholarly journals The Role of Medication Data to Enhance the Prediction of Alzheimer’s Progression Using Machine Learning

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Shaker El-Sappagh ◽  
Tamer Abuhmed ◽  
Bader Alouffi ◽  
Radhya Sahal ◽  
Naglaa Abdelhade ◽  
...  
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Multimodal Data ◽  
Learning Techniques ◽  
Early Progression ◽  
Neuroimaging Data

Early detection of Alzheimer’s disease (AD) progression is crucial for proper disease management. Most studies concentrate on neuroimaging data analysis of baseline visits only. They ignore the fact that AD is a chronic disease and patient’s data are naturally longitudinal. In addition, there are no studies that examine the effect of dementia medicines on the behavior of the disease. In this paper, we propose a machine learning-based architecture for early progression detection of AD based on multimodal data of AD drugs and cognitive scores data. We compare the performance of five popular machine learning techniques including support vector machine, random forest, logistic regression, decision tree, and K-nearest neighbor to predict AD progression after 2.5 years. Extensive experiments are performed using an ADNI dataset of 1036 subjects. The cross-validation performance of most algorithms has been improved by fusing the drugs and cognitive scores data. The results indicate the important role of patient’s taken drugs on the progression of AD disease.

scholarly journals Feeding the machine: Challenges to reproducible predictive modeling in resting-state connectomics

2021 ◽  
pp. 1-44
Author(s):  
Andrew Cwiek ◽  
Sarah M. Rajtmajer ◽  
Bradley Wyble ◽  
Vasant Honavar ◽  
Emily Grossner ◽  
...  
Keyword(s):  
Machine Learning ◽  
Patient Outcomes ◽  
Predictive Models ◽  
Resting State ◽  
Cross Validation ◽  
Functional Neuroimaging ◽  
Imaging Biomarkers ◽  
Brain Disorders ◽  
Neuroimaging Data ◽  
Key Steps

Abstract In this critical review, we examine the application of predictive models, e.g. classifiers, trained using Machine Learning (ML) to assist in interpretation of functional neuroimaging data. Our primary goal is to summarize how ML is being applied and critically assess common practices. Our review covers 250 studies published using ML and resting-state functional MRI (fMRI) to infer various dimensions of the human functional connectome. Results for hold-out (“lockbox”) performance was, on average, ~13% less accurate than performance measured through cross-validation alone, highlighting the importance of lockbox data which was included in only 16% of the studies. There was also a concerning lack of transparency across the key steps in training and evaluating predictive models. The summary of this literature underscores the importance of the use of a lockbox and highlights several methodological pitfalls that can be addressed by the imaging community. We argue that, ideally, studies are motivated both by the reproducibility and generalizability of findings as well as the potential clinical significance of the insights. We offer recommendations for principled integration of machine learning into the clinical neurosciences with the goal of advancing imaging biomarkers of brain disorders, understanding causative determinants for health risks, and parsing heterogeneous patient outcomes.

scholarly journals Deep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox

2021 ◽  
Vol 15 ◽  
Author(s):  
Karl M. Kuntzelman ◽  
Jacob M. Williams ◽  
Phui Cheng Lim ◽  
Ashok Samal ◽  
Prahalada K. Rao ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Pattern Analysis ◽  
Time Frame ◽  
Multivariate Pattern Analysis ◽  
Similar Time ◽  
Learning Techniques ◽  
Neuroimaging Data ◽  
Pros And Cons ◽  
Multivariate Pattern

In recent years, multivariate pattern analysis (MVPA) has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and other neuroimaging methodologies. In a similar time frame, “deep learning” (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data – which we term “deep MVPA,” or dMVPA – and introduce a new software toolbox (the “Deep Learning In Neuroimaging: Exploration, Analysis, Tools, and Education” package, DeLINEATE for short) intended to facilitate dMVPA for neuroscientists (and indeed, scientists more broadly) everywhere.

scholarly journals A machine learning tool for interpreting differences in cognition using brain features

2019 ◽  
Author(s):  
Tiago Azevedo ◽  
Luca Passamonti ◽  
Pietro Lió ◽  
Nicola Toschi
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Machine Learning Algorithms ◽  
Public Repository ◽  
Cognitive Differences ◽  
Health Measures ◽  
Human Connectome Project ◽  
Neuroimaging Data ◽  
Recent Developments ◽  
Surface Based Morphometry

AbstractPredicting variability in cognition traits is an attractive and challenging area of research, where different approaches and datasets have been implemented with mixed results. Some powerful Machine Learning algorithms employed before are difficult to interpret, while other algorithms are easy to interpret but might not be as powerful. To improve understanding of individual cognitive differences in humans, we make use of the most recent developments in Machine Learning in which powerful prediction models can be interpreted with confidence. We used neuroimaging data and a variety of behavioural, cognitive, affective and health measures from 905 people obtained from the Human Connectome Project (HCP). As a main contribution of this paper, we show how one could interpret the neuroanatomical basis of cognition, with recent methods which we believe are not yet fully explored in the field. By reducing neuroimages to a well characterised set of features generated from surface-based morphometry and cortical myelin estimates, we make the interpretation of such models easier as each feature is self-explanatory. The code used in this tool is available in a public repository: https://github.com/tjiagoM/interpreting-cognition-paper-2019

Sign in / Sign up

Export Citation Format

Share Document