A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease

Spasov, S; Passamonti, Luca; Duggento, Andrea; Lió, Píetro; Toschi, Nicola

doi:10.1016/j.neuroimage.2019.01.031

Cited by 283 publications

(159 citation statements)

References 37 publications

Supporting

Mentioning

151

Contrasting

Order By: Relevance

“…Similarly, high cross-validated results were found by other studies who combined structural MRI with clinical and neuropsychological information (i.e. [7,[10][11][12][13][14][15][16][17][18] ): AUROC = 0.902; balanced accuracy = 80.5%) In addition, a recent study [44] presented a highly performing deep learning algorithm (AUROC = 0.925; accuracy = 86%; sensitivity = 87.5%; specificity = 85%) and, to the best of our knowledge, this is the only available study using structural MRI in which a a proper testing of the algorithm was performed. Some particularly promising cross-validated results were also found in some studies which considered also APOE genotyping, together with EEG, ( [45] : AUROC = 0.97; sensitivity = 96.7%; specificity = 86%) or blood biomarkers [7,10,16] : balanced accuracy = 92.5%).…”

Section: Discussionsupporting

confidence: 64%

“…Only a very small number of machine learning algorithms for the prediction of conversion from MCI to AD were subjected to a proper testing protocol, rather than only a cross-validation protocol, which limits the soundness of the evidence of their predictive performance. As such, apart from [42,44] , all the previously mentioned results may be optimistically biased estimates of the generalized performance of such algorithms as a proper testing protocol was not applied.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Ensemble-Based Machine Learning Algorithm To Predict The Conversion From Mild Cognitive Impairment To Alzheimer’s Disease Using Socio-demographic Characteristics, Clinical Information And Neuropsychological Measures

Grassi

Rouleaux

Caldirola

et al. 2019

Preprint

View full text Add to dashboard Cite

Background: Despite the increasing availability in brain health related data, clinically translatable methods to predict the conversion from Mild Cognitive Impairment (MCI) to Alzheimer's disease (AD) are still lacking. Although MCI typically precedes AD, only a fraction of 20-40% of MCI individuals will progress to dementia within 3 years following the initial diagnosis. As currently available and emerging therapies likely have the greatest impact when provided at the earliest disease stage, the prompt identification of subjects at high risk for conversion to full AD is of great importance in the fight against this disease. In this work, we propose a highly predictive machine learning algorithm, based only on non-invasively and easily in-the-clinic collectable predictors, to identify MCI subjects at risk for conversion to full AD. Methods:The algorithm was developed using the open dataset from the Alzheimer's Disease Neuroimaging Initiative (ADNI), employing a sample of 550 MCI subjects whose diagnostic follow-up is available for at least 3 years after the baseline assessment. A restricted set of information regarding sociodemographic and clinical characteristics, neuropsychological test scores was used as predictors and several different supervised machine learning algorithms were developed and ensembled in final algorithm. A site-independent stratified train/test split protocol was used to provide an estimate of the generalized performance of the algorithm. Results:The final algorithm demonstrated an AUROC of 0.88, sensitivity of 77.7%, and a specificity of 79.9% on excluded test data. The specificity of the algorithm was 40.2% for 100% sensitivity. Discussion:The algorithm we developed achieved sound and high prognostic performance to predict AD conversion using easily clinically derived information that makes the algorithm easy to be translated into practice. This indicates beneficial application to improve recruitment in clinical trials and to more selectively prescribe new and newly emerging early interventions to high AD risk patients.Keywords Alzheimer's disease · clinical prediction rule · machine learning · mild cognitive impairment · personalized medicine · precision medicine · neuropsychological tests 1

show abstract

Section: Discussionsupporting

confidence: 64%

Section: Discussionmentioning

confidence: 99%

A Novel Ensemble-Based Machine Learning Algorithm To Predict The Conversion From Mild Cognitive Impairment To Alzheimer’s Disease Using Socio-demographic Characteristics, Clinical Information And Neuropsychological Measures

Grassi

Rouleaux

Caldirola

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…A new technique deep learning-based technique by [12] to primary identify the mild cognitive impairment (MCI) patients with more risk to convert in to AD within 3 years. Using ADNI database they combine the base-line structural MRI, neuropsychological, demographic, and APOe4 genetic data.…”

Section: F Deep Autoencoder (Da)mentioning

confidence: 99%

Alzheimer’s Disease Diagnosis using Deep Learning Techniques

Salehi¹,

Baglat²,

Gupta³

2020

IJEAT

View full text Add to dashboard Cite

Deep learning is one of the machine learning approach which has shown promising results and performance as compare to traditional algorithms of machine learning in terms of high dimensional data of MRI brain image. In this article the application of deep learning in medical field is addressed. A thorough review of various algorithms of deep learning for diagnosis of Alzheimer's disease is done, in which this disease is a progressive brain disorder that destroy the brain memory gradually, it is a common disease in older adults which is caused by dementia. It has been obtained in most research papers that the most widely used and represented algorithm is Convolutional Neural Networks (CNN) when it deals with brain image analysis. After study of various related papers for diagnosing of AD, we have come to this point and suggested that the AD prediction at earlier stages can be increased by using an advance deep learning techniques in different dataset (ADNI, OASIS) combining to one.

show abstract

“…This study differs from previous studies on predictive modelling in the fact that we are interested in predicting the evolution of specific neuroradiological MRI features (i.e., WMH in T2-FLAIR), not the progression of a disease as a whole and/or its effect. For example, previous studies have proposed methods for predicting the progression from mild cognitive impairment to Alzheimer's disease (Spasov et al, 2019) and progression of cognitive decline in Alzheimer's disease patients (Choi et al, 2018). Instead, our proposed DEP model generates three outcomes: 1) prediction of WMH volumetric changes (i.e., either progressing or regressing), 2) estimation of WMH spatial changes, and 3) spatial distribution of white matter evolution at the voxellevel precision.…”

Section: Introductionmentioning

confidence: 99%

Automatic Spatial Estimation of White Matter Hyperintensities Evolution in Brain MRI using Disease Evolution Predictor Deep Neural Networks

Rachmadi

Valdés-Hernández²,

Makin³

et al. 2019

Preprint

View full text Add to dashboard Cite

AbstractPrevious studies have indicated that white matter hyperintensities (WMH), the main radiological feature of small vessel disease, may evolve (i.e., shrink, grow) or stay stable over a period of time. Predicting these changes are challenging because it involves some unknown clinical risk factors that leads to a non-deterministic prediction task. In this study, we propose a deep learning model to predict the evolution of WMH from baseline to follow-up (i.e., 1-year later), namely “Disease Evolution Predictor” (DEP) model, which can be adjusted to become a non-deterministic model. The DEP model receives a baseline image as input and produces a map called “Disease Evolution Map” (DEM), which represents the evolution of WMH from baseline to follow-up. Two DEP models are proposed, namely DEP-UResNet and DEP-GAN, which are representatives of the supervised (i.e., need expert-generated manual labels to generate the output) and unsupervised (i.e., do not require manual labels produced by experts) deep learning algorithms respectively. To simulate the non-deterministic and unknown parameters involved in WMH evolution, we modulate a Gaussian noise array to the DEP model as auxiliary input. This forces the DEP model to imitate a wider spectrum of alternatives in the prediction results. The alternatives of using other types of auxiliary input instead, such as baseline WMH and stroke lesion loads are also proposed and tested. Based on our experiments, the fully supervised machine learning scheme DEP-UResNet regularly performed better than the DEP-GAN which works in principle without using any expert-generated label (i.e., unsupervised). However, a semi-supervised DEP-GAN model, which uses probability maps produced by a supervised segmentation method in the learning process, yielded similar performances to the DEP-UResNet and performed best in the clinical evaluation. Furthermore, an ablation study showed that an auxiliary input, especially the Gaussian noise, improved the performance of DEP models compared to DEP models that lacked the auxiliary input regardless of the model’s architecture. To the best of our knowledge, this is the first extensive study on modelling WMH evolution using deep learning algorithms, which deals with the non-deterministic nature of WMH evolution.

show abstract

A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer's disease

Cited by 283 publications

References 37 publications

A Novel Ensemble-Based Machine Learning Algorithm To Predict The Conversion From Mild Cognitive Impairment To Alzheimer’s Disease Using Socio-demographic Characteristics, Clinical Information And Neuropsychological Measures

A Novel Ensemble-Based Machine Learning Algorithm To Predict The Conversion From Mild Cognitive Impairment To Alzheimer’s Disease Using Socio-demographic Characteristics, Clinical Information And Neuropsychological Measures

Alzheimer’s Disease Diagnosis using Deep Learning Techniques

Automatic Spatial Estimation of White Matter Hyperintensities Evolution in Brain MRI using Disease Evolution Predictor Deep Neural Networks

Contact Info

Product

Resources

About