Diagnosis of Alzheimer's disease and behavioural variant frontotemporal dementia with machine learning-aided neuropsychological assessment using feature engineering and genetic algorithms

Cognitive dysfunction characteristics of multiple sclerosis with aging

BACKGROUND

We aimed to investigate the characteristics of cognitive impairment in older people with multiple sclerosis (MS).

METHODS

Cross-sectional study that included participants that were examined with a common and comprehensive neuropsychological protocol. The subjects were matched by sociodemographic variables and the following groups were generated for comparisons: young MS versus healthy controls (HC) (n = 246), old MS versus HC (n = 198), young MS vs old MS (n = 226), MS vs Alzheimer's disease (AD)(n = 70), and MS vs Parkinson's disease (PD) (n = 62). The ICCoDiMS criteria were used to define cognitive impairment in MS.

RESULTS

Cognitive impairment was more frequent in young than old patients (70.8 % vs 52.2 %). Attention and speed processing is the most frequent cognitive domain impaired in MS (54.9 % of young MS vs 32.7 % of old MS). The frequency of impairment in attention/processing speed (54.9 % vs 32.7 %) and episodic memory (27.9 % vs 14.3) was higher in the young group than in the old group. There were no statistically significant differences in the distribution of impairment in executive function (46.0 % vs 35.3 %), visuospatial (17.9 % vs 9.5 %), and language (12.4 % vs 17.7 %). In those patients meeting the criteria for cognitive impairment, young MS patients showed lower performance in attention/processing speed tests. Conversely, old MS patients showed lower performance in episodic memory, verbal fluency, and planning. There were no differences in the correlations between SDMT and other neuropsychological tests in young and old patients, which suggests similar cognitive processes underlying SDMT performance in both groups. There were differences between old MS and prodromal AD, especially in episodic memory, while the cognitive profile of old MS was largely shared with PD.

CONCLUSIONS

Our study found that the cognitive profile of MS is defined by a characteristic impairment in attention and processing speed, which is present during the lifespan. The impairment in processing speed is less prominent in old age, whereas the impairment of other cognitive functions becomes more relevant. These findings suggest potential differences in the pathophysiological processes associated with cognitive impairment between young and old ages that warrant further investigation.

Detecting Alzheimer's Disease Stages and Frontotemporal Dementia in Time Courses of Resting-State fMRI Data Using a Machine Learning Approach

Early, accurate diagnosis of neurodegenerative dementia subtypes such as Alzheimer's disease (AD) and frontotemporal dementia (FTD) is crucial for the effectiveness of their treatments. However, distinguishing these conditions becomes challenging when symptoms overlap or the conditions present atypically. Resting-state fMRI (rs-fMRI) studies have demonstrated condition-specific alterations in AD, FTD, and mild cognitive impairment (MCI) compared to healthy controls (HC). Here, we used machine learning to build a diagnostic classification model based on these alterations. We curated all rs-fMRIs and their corresponding clinical information from the ADNI and FTLDNI databases. Imaging data underwent preprocessing, time course extraction, and feature extraction in preparation for the analyses. The imaging features data and clinical variables were fed into gradient-boosted decision trees with fivefold nested cross-validation to build models that classified four groups: AD, FTD, HC, and MCI. The mean and 95% confidence intervals for model performance metrics were calculated using the unseen test sets in the cross-validation rounds. The model built using only imaging features achieved 74.4% mean balanced accuracy, 0.94 mean macro-averaged AUC, and 0.73 mean macro-averaged F1 score. It accurately classified FTD (F1 = 0.99), HC (F1 = 0.99), and MCI (F1 = 0.86) fMRIs but mostly misclassified AD scans as MCI (F1 = 0.08). Adding clinical variables to model inputs raised balanced accuracy to 91.1%, macro-averaged AUC to 0.99, macro-averaged F1 score to 0.92, and improved AD classification accuracy (F1 = 0.74). In conclusion, a multimodal model based on rs-fMRI and clinical data accurately differentiates AD-MCI vs. FTD vs. HC.

Comparative study of machine learning methods for modeling associations between risk factors and future dementia cases

A substantial portion of dementia risk can be attributed to modifiable risk factors that can be affected by lifestyle changes. Identifying the contributors to dementia risk could prove valuable. Recently, machine learning methods have been increasingly applied to healthcare data. Several studies have attempted to predict dementia progression by using such techniques. This study aimed to compare the performance of different machine-learning methods in modeling associations between known cognitive risk factors and future dementia cases. A subset of the AGES-Reykjavik Study dataset was analyzed using three machine-learning methods: logistic regression, random forest, and neural networks. Data were collected twice, approximately five years apart. The dataset included information from 1,491 older adults who underwent a cognitive screening process and were considered to have healthy cognition at baseline. Cognitive risk factors included in the models were based on demographics, MRI data, and other health-related data. At follow-up, participants were re-evaluated for dementia using the same cognitive screening process. Various performance metrics for all three machine learning algorithms were assessed. The study results indicate that a random forest algorithm performed better than neural networks and logistic regression in predicting the association between cognitive risk factors and dementia. Compared to more traditional statistical analyses, machine-learning methods have the potential to provide more accurate predictions about which individuals are more likely to develop dementia than others.

Breaking barriers: a statistical and machine learning-based hybrid system for predicting dementia

Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia. Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew's correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system's efficiency. Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535. Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.

FDG-PET-based neural correlates of Addenbrooke's cognitive examination III scores in Alzheimer's disease and frontotemporal degeneration

Introduction

The Addenbrooke's Cognitive Examination III (ACE-III) is a brief test useful for neuropsychological assessment. Several studies have validated the test for the diagnosis of Alzheimer's disease (AD) and frontotemporal dementia (FTD). In this study, we aimed to examine the metabolic correlates associated with the performance of ACE-III in AD and behavioral variant FTD.

Methods

We enrolled 300 participants in a cross-sectional study, including 180 patients with AD, 60 with behavioral FTD (bvFTD), and 60 controls. An 18F-Fluorodeoxyglucose positron emission tomography study was performed in all cases. Correlation between the ACE-III and its domains (attention, memory, fluency, language, and visuospatial) with the brain metabolism was estimated.

Results

The ACE-III showed distinct neural correlates in bvFTD and AD, effectively capturing the most relevant regions involved in these disorders. Neural correlates differed for each domain, especially in the case of bvFTD. Lower ACE-III scores were associated with more advanced stages in both disorders. The ACE-III exhibited high discrimination between bvFTD vs. HC, and between AD vs. HC. Additionally, it was sensitive to detect hypometabolism in brain regions associated with bvFTD and AD.

Conclusion

Our study contributes to the knowledge of the brain regions associated with ACE-III, thereby facilitating its interpretation, and highlighting its suitability for screening and monitoring. This study provides further validation of ACE-III in the context of AD and FTD.

Early Prediction of Dementia Using Feature Extraction Battery (FEB) and Optimized Support Vector Machine (SVM) for Classification

Dementia is a cognitive disorder that mainly targets older adults. At present, dementia has no cure or prevention available. Scientists found that dementia symptoms might emerge as early as ten years before the onset of real disease. As a result, machine learning (ML) scientists developed various techniques for the early prediction of dementia using dementia symptoms. However, these methods have fundamental limitations, such as low accuracy and bias in machine learning (ML) models. To resolve the issue of bias in the proposed ML model, we deployed the adaptive synthetic sampling (ADASYN) technique, and to improve accuracy, we have proposed novel feature extraction techniques, namely, feature extraction battery (FEB) and optimized support vector machine (SVM) using radical basis function (rbf) for the classification of the disease. The hyperparameters of SVM are calibrated by employing the grid search approach. It is evident from the experimental results that the newly pr oposed model (FEB-SVM) improves the dementia prediction accuracy of the conventional SVM by 6%. The proposed model (FEB-SVM) obtained 98.28% accuracy on training data and a testing accuracy of 93.92%. Along with accuracy, the proposed model obtained a precision of 91.80%, recall of 86.59, F1-score of 89.12%, and Matthew's correlation coefficient (MCC) of 0.4987. Moreover, the newly proposed model (FEB-SVM) outperforms the 12 state-of-the-art ML models that the researchers have recently presented for dementia prediction.

Machine Learning for Dementia Prediction: A Systematic Review and Future Research Directions

Nowadays, Artificial Intelligence (AI) and machine learning (ML) have successfully provided automated solutions to numerous real-world problems. Healthcare is one of the most important research areas for ML researchers, with the aim of developing automated disease prediction systems. One of the disease detection problems that AI and ML researchers have focused on is dementia detection using ML methods. Numerous automated diagnostic systems based on ML techniques for early prediction of dementia have been proposed in the literature. Few systematic literature reviews (SLR) have been conducted for dementia prediction based on ML techniques in the past. However, these SLR focused on a single type of data modality for the detection of dementia. Hence, the purpose of this study is to conduct a comprehensive evaluation of ML-based automated diagnostic systems considering different types of data modalities such as images, clinical-features, and voice data. We collected the research articles from 2011 to 2022 using the keywords dementia, machine learning, feature selection, data modalities, and automated diagnostic systems. The selected articles were critically analyzed and discussed. It was observed that image data driven ML models yields promising results in terms of dementia prediction compared to other data modalities, i.e., clinical feature-based data and voice data. Furthermore, this SLR highlighted the limitations of the previously proposed automated methods for dementia and presented future directions to overcome these limitations.

Multi-Disease Validation of the RUDAS for Cognitive Screening in Alzheimer's Disease, Parkinson's Disease, and Multiple Sclerosis

BACKGROUND

The Rowland Universal Dementia Assessment Scale (RUDAS) is a cognitive test with favorable diagnostic properties for detecting dementia and a low influence of education and cultural biases.

OBJECTIVE

We aimed to validate the RUDAS in people with Alzheimer's disease (AD), Parkinson's disease (PD), and multiple sclerosis (MS).

METHODS

We enrolled one hundred and fifty participants (60 with AD, 30 with PD, 60 with MS, and 120 healthy controls (HC)). All clinical groups completed a comprehensive neuropsychological battery, RUDAS, and standard cognitive tests of each disorder: MMSE, SCOPA-COG, and Symbol Digit Modalities Test. Intergroup comparisons between clinical groups and HC and ROC curves were estimated. Random Forest algorithms were trained and validated to detect cognitive impairment using RUDAS and rank the most relevant scores.

RESULTS

The RUDAS scores were lower in patients with AD, and patients with PD and MS showed cognitive impairment compared to healthy controls. Effect sizes were generally large. The total score was the most discriminative, followed by the memory score. Correlations with standardized neuropsychological tests were moderate to high. Random Forest algorithms obtained accuracies over 80-90% using the RUDAS for diagnosing AD and cognitive impairment associated with PD and MS.

CONCLUSION

Our results suggest the RUDAS is a valid test candidate for multi-disease cognitive screening tool in AD, PD, and MS.

Hierarchical Two-Stage Cost-Sensitive Clinical Decision Support System for Screening Prodromal Alzheimer's Disease and Related Dementias

BACKGROUND

The detection of subtle cognitive impairment in a clinical setting is difficult. Because time is a key factor in small clinics and research sites, the brief cognitive assessments that are relied upon often misclassify patients with very mild impairment as normal.

OBJECTIVE

In this study, we seek to identify a parsimonious screening tool in one stage, followed by additional assessments in an optional second stage if additional specificity is desired, tested using a machine learning algorithm capable of being integrated into a clinical decision support system.

METHODS

The best primary stage incorporated measures of short-term memory, executive and visuospatial functioning, and self-reported memory and daily living questions, with a total time of 5 minutes. The best secondary stage incorporated a measure of neurobiology as well as additional cognitive assessment and brief informant report questionnaires, totaling 30 minutes including delayed recall. Combined performance was evaluated using 25 sets of models, trained on 1,181 ADNI participants and tested on 127 patients from a memory clinic.

RESULTS

The 5-minute primary stage was highly sensitive (96.5%) but lacked specificity (34.1%), with an AUC of 87.5% and diagnostic odds ratio of 14.3. The optional secondary stage increased specificity to 58.6%, resulting in an overall AUC of 89.7% using the best model combination of logistic regression and gradient-boosted machine.

CONCLUSION

The primary stage is brief and effective at screening, with the optional two-stage technique further increasing specificity. The hierarchical two-stage technique exhibited similar accuracy but with reduced costs compared to the more common single-stage paradigm.

Classification of Alzheimer's disease and frontotemporal dementia using routine clinical and cognitive measures across multicentric underrepresented samples: A cross sectional observational study

Background

Global brain health initiatives call for improving methods for the diagnosis of Alzheimer's disease (AD) and frontotemporal dementia (FTD) in underrepresented populations. However, diagnostic procedures in upper-middle-income countries (UMICs) and lower-middle income countries (LMICs), such as Latin American countries (LAC), face multiple challenges. These include the heterogeneity in diagnostic methods, lack of clinical harmonisation, and limited access to biomarkers.

Methods

This cross-sectional observational study aimed to identify the best combination of predictors to discriminate between AD and FTD using demographic, clinical and cognitive data among 1794 participants [904 diagnosed with AD, 282 diagnosed with FTD, and 606 healthy controls (HCs)] collected in 11 clinical centres across five LAC (ReDLat cohort).

Findings

A fully automated computational approach included classical statistical methods, support vector machine procedures, and machine learning techniques (random forest and sequential feature selection procedures). Results demonstrated an accurate classification of patients with AD and FTD and HCs. A machine learning model produced the best values to differentiate AD from FTD patients with an accuracy = 0.91. The top features included social cognition, neuropsychiatric symptoms, executive functioning performance, and cognitive screening; with secondary contributions from age, educational attainment, and sex.

Interpretation

Results demonstrate that data-driven techniques applied in archival clinical datasets could enhance diagnostic procedures in regions with limited resources. These results also suggest specific fine-grained cognitive and behavioural measures may aid in the diagnosis of AD and FTD in LAC. Moreover, our results highlight an opportunity for harmonisation of clinical tools for dementia diagnosis in the region.

Funding

This work was supported by the Multi-Partner Consortium to Expand Dementia Research in Latin America (ReDLat), funded by NIA/NIH (R01AG057234), Alzheimer's Association (SG-20-725707-ReDLat), Rainwater Foundation, Takeda (CW2680521), Global Brain Health Institute; as well as CONICET; FONCYT-PICT (2017-1818, 2017-1820); PIIECC, Facultad de Humanidades, Usach; Sistema General de Regalías de Colombia (BPIN2018000100059), Universidad del Valle (CI 5316); ANID/FONDECYT Regular (1210195, 1210176, 1210176); ANID/FONDAP (15150012); ANID/PIA/ANILLOS ACT210096; and Alzheimer's Association GBHI ALZ UK-22-865742.

GA-MADRID: design and validation of a machine learning tool for the diagnosis of Alzheimer’s disease and frontotemporal dementia using genetic algorithms

Artificial Intelligence aids early diagnosis and development of new treatments, which is key to slow down the progress of the diseases, which to date have no cure. The patients’ evaluation is carried out through diagnostic techniques such as clinical assessments neuroimaging techniques, which provide high-dimensionality data. In this work, a computational tool is presented that deals with the data provided by the clinical diagnostic techniques. This is a Python-based framework implemented with a modular design and fully extendable. It integrates (i) data processing and management of missing values and outliers; (ii) implementation of an evolutionary feature engineering approach, developed as a Python package, called PyWinEA using Mono-objective and Multi-objetive Genetic Algorithms (NSGAII); (iii) a module for designing predictive models based on a wide range of machine learning algorithms; (iv) a multiclass decision stage based on evolutionary grammars and Bayesian networks. Developed under the eXplainable Artificial Intelligence and open science perspective, this framework provides promising advances and opens the door to the understanding of neurodegenerative diseases from a data-centric point of view. In this work, we have successfully evaluated the potential of the framework for early and automated diagnosis with neuroimages and neurocognitive assessments from patients with Alzheimer’s disease (AD) and frontotemporal dementia (FTD).

Graphical abstract

Neural basis of visuospatial tests in behavioral variant frontotemporal dementia

Background

Recent models of visuospatial functioning suggest the existence of three main circuits emerging from the dorsal (“where”) route: parieto-prefrontal pathway, parieto-premotor, and parieto-medial temporal. Neural underpinnings of visuospatial task performance and the sparing of visuospatial functioning in bvFTD are unclear. We hypothesized different neural and cognitive mechanisms in visuospatial tasks performance in bvFTD and AD.

Methods

Two hundred and sixteen participants were enrolled for this study: 72 patients with bvFTD dementia and 144 patients with AD. Visual Object and Space Perception Battery Position Discrimination and Number Location (VOSP-PD and VOSP-NL) and Rey-Osterrieth Complex Figure (ROCF) were administered to examine visuospatial functioning, together with a comprehensive neuropsychological battery. FDG-PET was acquired to evaluate brain metabolism. Voxel-based brain mapping analyses were conducted to evaluate the brain regions associated with visuospatial function in bvFTD and AD.

Results

Patients with AD performed worst in visuospatial tasks in mild dementia, but not at prodromal stage. Attention and executive functioning tests showed higher correlations in bvFTD than AD with ROCF, but not VOSP subtests. Visuospatial performance in patients with bvFTD was associated with bilateral frontal regions, including the superior and medial frontal gyri, supplementary motor area, insula and middle cingulate gyrus.

Conclusion

These findings support the role of prefrontal and premotor regions in visuospatial processing through the connection with the posterior parietal cortex and other posterior cortical regions. Visuospatial deficits should be interpreted with caution in patients with bvFTD, and should not be regarded as hallmarks of posterior cortical dysfunction.

An Intelligent Learning System for Unbiased Prediction of Dementia Based on Autoencoder and Adaboost Ensemble Learning

Dementia is a neurological condition that primarily affects older adults and there is still no cure or therapy available to cure it. The symptoms of dementia can appear as early as 10 years before the beginning of actual diagnosed dementia. Hence, machine learning (ML) researchers have presented several methods for early detection of dementia based on symptoms. However, these techniques suffer from two major flaws. The first issue is the bias of ML models caused by imbalanced classes in the dataset. Past research did not address this issue well and did not take preventative precautions. Different ML models were developed to illustrate this bias. To alleviate the problem of bias, we deployed a synthetic minority oversampling technique (SMOTE) to balance the training process of the proposed ML model. The second issue is the poor classification accuracy of ML models, which leads to a limited clinical significance. To improve dementia prediction accuracy, we proposed an intelligent learning system that is a hybrid of an autoencoder and adaptive boost model. The autoencoder is used to extract relevant features from the feature space and the Adaboost model is deployed for the classification of dementia by using an extracted subset of features. The hyperparameters of the Adaboost model are fine-tuned using a grid search algorithm. Experimental findings reveal that the suggested learning system outperforms eleven similar systems which were proposed in the literature. Furthermore, it was also observed that the proposed learning system improves the strength of the conventional Adaboost model by 9.8% and reduces its time complexity. Lastly, the proposed learning system achieved classification accuracy of 90.23%, sensitivity of 98.00% and specificity of 96.65%.