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.
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:
. The query was then searched in four well-known scientific databases: Pubmed, Scopus, Google Scholar and Web of Science.
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.
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.
Parkinson's disease (PD), a progressive neurodegenerative disease, can be misdiagnosed with atypical conditions such as Progressive Supranuclear Paralysis (PSP) due to overlapping clinical features. ...MicroRNAs (miRNAs) are small non-coding RNAs with a key role in post-transcriptional gene regulation. The aim was to identify a set of differential exosomal miRNAs biomarkers, which may aid in diagnosis.
We analyzed the serum level of 188 miRNAs in a discovery set, by using RTqPCR based TaqMan assay, in a small cohort of healthy controls, PD and PSP patients. Subsequently, the differentially expressed miRNAs, between PSP and PD patients, were further tested in a larger and independent cohort of 33 healthy controls, 40 PD and 20 PSP patients. The most accurate diagnostic exosomal miRNAs classifiers were identified in a logistic regression model.
A statistically significant set of three exosomal miRNAs: miR-21-3p, miR-22-3p and miR-223-5p, discriminated PD from HC (area under the curve of 0.75), and a set of three exosomal miRNAs, miR-425-5p, miR-21-3p, and miR-199a-5p, discriminated PSP from PD with good diagnostic accuracy (area under the curve of 0.86). Finally, the classifier that best discriminated PSP from PD consisted of six exosomal miRNAs (area under the curve = 0.91), with diagnostic sensitivity and specificity of 0.89 and 0.90, respectively.
Based on our analysis, these data showed that exosomal miRNAs could act as biomarkers to differentiate between PSP and PD.
•Non-invasive miRNA-based tests could be used for differential diagnosis.•Exosomal microRNAs (miRNAs) in serum are promising biomarker candidates for PSP.•Serum samples were analyzed with RT-qPCR to measure levels of selected miRNAs.•Differential miRNAs were dysregulated between patients groups and healthy controls.
Clinical differentiation of progressive supranuclear palsy (PSP) from Parkinson’s disease (PD) is challenging due to overlapping phenotypes and the late onset of specific atypical signs. Therefore, ...easily assessable diagnostic biomarkers are highly needed. Since PD is a synucleopathy while PSP is a tauopathy, here, we investigated the clinical usefulness of serum oligomeric-α-synuclein (o-α-synuclein) and 181Thr-phosphorylated tau (p-tau181), which are considered as the most important pathological protein forms in distinguishing between these two parkinsonisms. We assessed serum o-α-synuclein and p-tau181 by ELISA and SIMOA, respectively, in 27 PSP patients, 43 PD patients, and 39 healthy controls (HC). Moreover, we evaluated the correlation between serum biomarkers and biological and clinical features of these subjects. We did not find any difference in serum concentrations of p-tau181 and o-α-synuclein nor in the o-α-synuclein/p-tau181 ratio between groups. However, we observed that serum p-tau181 positively correlated with age in HC and PD, while serum o-α-synuclein correlated positively with disease severity in PD and negatively with age in PSP. Finally, the o-α-synuclein/p-tau181 ratio showed a negative correlation with age in PD.
Background
Idiopathic normal pressure hydrocephalus (iNPH) shares clinical and radiological features with progressive supranuclear palsy (PSP) and Alzheimer’s disease (AD). Corpus callosum (CC) ...involvement in these disorders is well established on structural MRI and diffusion tensor imaging (DTI), but alterations overlap and lack specificity to underlying tissue changes.
Objective
We propose a semi-automated approach to assess CC integrity in iNPH based on the spatial distribution of DTI-derived principal diffusion direction orientation (V1).
Methods
We processed DTI data from 121 subjects (Site1: iNPH = 23, PSP = 27, controls = 14; ADNI: AD = 35, controls = 22) to obtain V1, fractional anisotropy (FA) and mean diffusivity (MD) maps. To increase the estimation accuracy of DTI metrics, analyses were restricted to the midsagittal CC portion (± 6 slices from midsagittal plane). Group-wise comparison of normalized altered voxel count in midsagittal CC was performed using Kruskal–Wallis tests, followed by post hoc comparisons (Bonferroni-corrected
p
< 0.05). ROC analysis was used to evaluate the diagnostic power of DTI alterations compared to callosal volume.
Results
We found specific changes of V1 distribution in CC splenium of iNPH compared to AD and PSP, while MD and FA showed patterns of alterations common to all disorders. ROC curves showed that, compared to splenial volume, V1 represented the most accurate marker of iNPH diagnosis versus AD and PSP.
Conclusions
Our results provide evidence that V1 is a powerful biomarker for distinguishing patients with iNPH from patients with AD or PSP. Indeed, our findings also provide more specific insight into the pathophysiological mechanisms that underlie tissue damage across iNPH and its mimics.
Alzheimer’s disease (AD), a neurodegenerative disease, is linked to a variety of internal and external factors present from the early stages of the disease. There are several risk factors related to ...the pathogenesis of AD, among these exosomes and microRNAs (miRNAs) are of particular importance. Exosomes are nanocarriers released from many different cell types, including neuronal cells. Through the transfer of bioactive molecules, they play an important role both in the maintenance of physiological and in pathological conditions. Exosomes could be carriers of potential biomarkers useful for the assessment of disease progression and for therapeutic applications. miRNAs are small noncoding endogenous RNA sequences active in the regulation of protein expression, and alteration of miRNA expression can result in a dysregulation of key genes and pathways that contribute to disease development. Indeed, the involvement of exosomal miRNAs has been highlighted in various neurodegenerative diseases, and this opens the possibility that dysregulated exosomal miRNA profiles may influence AD disease. The advances in exosome-related biomarker detection in AD are summarized. Finally, in this review, we highlight the use of exosomal miRNAs as essential biomarkers in preclinical and clinical studies in Alzheimer’s disease, also taking a look at their potential clinical value.
Differentiating clinically progressive supranuclear palsy-parkinsonism (PSP-P) from Parkinson's disease (PD) may be challenging, especially in the absence of vertical supranuclear gaze palsy (VSGP). ...The Magnetic Resonance Parkinsonism Index (MRPI) has been reported to accurately distinguish between PSP and PD, yet few data exist on the usefulness of this biomarker for the differentiation of PSP-P from PD.
Thirty-four patients with PSP-P, 46 with PSP-Richardson's syndrome (PSP-RS), 53 with PD, and 53 controls were enrolled. New consensus criteria for the clinical diagnosis of PSP were used as the reference standard. The MRPI, and a new index termed MRPI 2.0 including the measurement of the third ventricle width (MRPI multiplied by third ventricle width/frontal horns width ratio), were calculated on T1-weighted MR images.
The MRPI differentiated patients with PSP-P from those with PD with sensitivity and specificity of 73.5% and 98.1%, respectively, while the MRPI 2.0 showed higher sensitivity (100%) and similar specificity (94.3%) in differentiating between these two groups. Both biomarkers showed excellent performance in differentiating PSP-P patients with VSGP from those with PD, but the MRPI 2.0 was much more accurate (95.8%) than MRPI in differentiating PSP-P patients with slowness of vertical saccades from PD patients.
The MRPI 2.0 accurately differentiated PSP-P patients from those with PD. This new index was more powerful than MRPI in differentiating PSP patients in the early stage of the disease with slowness of vertical saccades from patients with PD, thus helping clinicians to consolidate the diagnosis based on clinical features, in vivo.
•Distinguishing PSP-P from PD is challenging in the early stages of the disease.•Few data exist on the usefulness of MRPI for diagnosing PSP-P patients.•MRPI 2.0 is a new version of MRPI which includes the 3rd ventricular width.•MRPI 2.0 accurately differentiated patients with PSP-P from those with PD.•MRPI 2.0 accurately diagnosed PSP-P in the absence of vertical ocular palsy.
Tremor is an impairing symptom associated with several neurological diseases. Some of such diseases are neurodegenerative, and tremor characterization may be of help in differential diagnosis. To ...date, electromyography (EMG) is the gold standard for the analysis and diagnosis of tremors. In the last decade, however, several studies have been conducted for the validation of different techniques and new, non-invasive, portable, or even wearable devices have been recently proposed as complementary tools to EMG for a better characterization of tremors. Such devices have proven to be useful for monitoring the efficacy of therapies or even aiding in differential diagnosis. The aim of this review is to present systematically such new solutions, trying to highlight their potentialities and limitations, with a hint to future developments.
Determination of sensitive and specific markers of very early AD progression is intended to aid researchers and clinicians to develop new treatments and monitor their effectiveness, as well as to ...lessen the time and cost of clinical trials. Magnetic Resonance (MR)-related biomarkers have been recently identified by the use of machine learning methods for the in vivo differential diagnosis of AD. However, the vast majority of neuroimaging papers investigating this topic are focused on the difference between AD and patients with mild cognitive impairment (MCI), not considering the impact of MCI patients who will (MCIc) or not convert (MCInc) to AD. Morphological T1-weighted MRIs of 137 AD, 76 MCIc, 134 MCInc, and 162 healthy controls (CN) selected from the Alzheimer's disease neuroimaging initiative (ADNI) cohort, were used by an optimized machine learning algorithm. Voxels influencing the classification between these AD-related pre-clinical phases involved hippocampus, entorhinal cortex, basal ganglia, gyrus rectus, precuneus, and cerebellum, all critical regions known to be strongly involved in the pathophysiological mechanisms of AD. Classification accuracy was 76% AD vs. CN, 72% MCIc vs. CN, 66% MCIc vs. MCInc (nested 20-fold cross validation). Our data encourage the application of computer-based diagnosis in clinical practice of AD opening new prospective in the early management of AD patients.
Previous literature showed a complex interpretation of recall tasks due to the complex relationship between Executive Functions (EF) and Long Term Memory (M). The Test of Memory Strategies (TMS) ...could be useful for assessing this issue, because it evaluates EF and M simultaneously. This study aims to explore the validity of the TMS structure, comparing the models proposed by Vaccaro et al. (2022) and evaluating the measurement invariance according to three countries (Italy, Spain, and Portugal) through Confirmatory Factor Analysis (CFA). Four hundred thirty-one healthy subjects (Age mean = 54.84, sd = 20.43; Education mean = 8.85, sd =4.05; M = 177, F = 259) were recruited in three countries (Italy, Spain, and Portugal).
Measurement invariance across three country groups was evaluated through Structural Equation modeling. Also, convergent and divergent validity were examined through the correlation between TMS and classical neuropsychological tests. CFA outcomes suggested that the best model was the three-dimensional model, in which list 1 and list2 reflect EF, list 3 reflects a mixed factor of EF and M (EFM) and list4 and list5 reflect M. This result is in line with the theory that TMS decreases EF components progressively. TMS was metric invariant to the country, but scalar invariance was not tenable. Finally, the factor scores of TMS showed convergent validity with the classical neuropsychological tests.
The overall results support cross-validation of TMS in the three countries considered.
•The assessment of Executive Functions and Memory separately could yield partial information about each involvement.•The Test of Memory Strategies (TMS) proposes to evaluate Memory and Executive Functions together.•The evaluation of factor structure and measurement invariance across groups is crucial to the validity appraisal of TMS.