Random Forest Algorithm for the Classification of Neuroimaging Data in Alzheimer's Disease: A Systematic Review

Abstract

Objective: Machine learning classification has been the most important computational development in the last years to satisfy the primary need of clinicians for automatic early diagnosis and prognosis. Nowadays, Random Forest (RF) algorithm has been successfully applied for reducing high dimensional and multi-source data in many scientific realms. Our aim was to explore the state of the art of the application of RF on single and multi-modal neuroimaging data for the prediction of Alzheimer's disease.Methods: A systematic review following PRISMA guidelines was conducted on this field of study. In particular, we constructed an advanced query using boolean operators as follows: (“random forest” OR “random forests”) AND neuroimaging AND (“alzheimer's disease” OR alzheimer's OR alzheimer) AND (prediction OR classification). The query was then searched in four well-known scientific databases: Pubmed, Scopus, Google Scholar and Web of Science.Results: Twelve articles—published between the 2007 and 2017—have been included in this systematic review after a quantitative and qualitative selection. The lesson learnt from these works suggest that when RF was applied on multi-modal data for prediction of Alzheimer's disease (AD) conversion from the Mild Cognitive Impairment (MCI), it produces one of the best accuracies to date. Moreover, the RF has important advantages in terms of robustness to overfitting, ability to handle highly non-linear data, stability in the presence of outliers and opportunity for efficient parallel processing mainly when applied on multi-modality neuroimaging data, such as, MRI morphometric, diffusion tensor imaging, and PET images.Conclusions: We discussed the strengths of RF, considering also possible limitations and by encouraging further studies on the comparisons of this algorithm with other commonly used classification approaches, particularly in the early prediction of the progression from MCI to AD.

Peripheral mitochondrial function correlates with clinical severity in idiopathic Parkinson's disease

“…The heterogeneity in clinical presentation, the dispersion we observed in mitochondrial physiology, and their correlation lend support to the hypothesis that there may be subgroups of different mitochondrial phenotypes correlating with the symptomatology in the general population of idiopathic PD patients. To test this possibility, we used machine‐learning methodology and recursive partitioning to build a CART, which have been successfully used in applications such as clinical subtypes classification and neuroimaging data analysis to predict Alzheimer's disease …”

“…To test this possibility, we used machine-learning methodology and recursive partitioning to build a CART, 25 which have been successfully used in applications such as clinical subtypes classification 26 and neuroimaging data analysis to predict Alzheimer's disease. 27 All available parameters-that is, demographic variables (ie, age, age at onset, duration of the disease, and gender), the equivalent of levodopa medication, respirometry, and acidification parameters-were used in the CART process as input variables to predict either the SENS-PD or the MDS-UPDRS III (ie, response variables). Intrinsic to CART modeling is a selection step that eliminates in an unbiased fashion redundancy among the input variables to identify the most significant parameters.…”

Machine learning for bioinformatics and neuroimaging

“…A disadvantage of the RF is its sensitivity to the input parameters (Huang & Boutros, 2016). RFs have been widely applied both in bioinformatics (Qi, 2012) and in neuroimaging (Sarica, Cerasa, & Quattrone, 2017).…”

“…The experimental results suggested that linear kernels are preferable in this application and that SVMs seem to be robust against different preprocessing strategies, although the most evident effect is observed with the detrending of input time series. Another popular classifier is RF (Sarica et al, 2017). Fratello et al (2017) propose a multiview approach (see Box 1) for the classification of subjects affected by neurodegenerative diseases, specifically Amyotrophic Lateral Sclerosis and Parkinson's Disease.…”

A Machine Learning Model to Predict the Onset of Alzheimer Disease using Potential Cerebrospinal Fluid (CSF) Biomarkers

“…Multidimensionality of aforementioned clinical diagnostic factors makes it difficult for us to analyze and infer the information from the same. In this regard, a review describing a computer-based diagnostic method using Random Forest (RF) algorithms on medical imaging data have demonstrated high reliability in classifying early stage MCI patients which later progresses to advanced stages of AD [4]. Similarly, multi-kernel Support Vector Machine (SVM) was employed to predict future clinical symptoms of MCI patients using both baseline and longitudinal multimodal biomarkers data [5].…”