scholarly journals In-depth Insights into Alzheimer's Disease by using Explainable Machine Learning Approach - Existing Hypothesis Confronted

2021 ◽  
Author(s):  
Bojan Bogdanovic ◽  
Tome Eftimov ◽  
Monika Simjanoska
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Negative Influence ◽  
Data Set ◽  
Huge Data ◽  
Depth Analysis ◽  
Shapley Values ◽  
Intelligent Models

Abstract Background: Alzheimer's disease is still a field of research with lots of open questions. The complexity of the disease prevents the early diagnosis before visible symptoms regarding the individual's cognitive capabilities occur. This research presents an in-depth analysis of a huge data set encompassing medical, cognitive and lifestyle's measurements from more than 12,000 individuals. Several hypothesis were established whose validity has been questioned considering the obtained results.Methods: The importance of appropriate experimental design is highly stressed in the research. Thus, a sequence of methods for handling missing data, redundancy, data imbalance, and correlation analysis have been applied for appropriate preprocessing of the data set, and consequently Random Forest and XGBoost models have been trained and evaluated with special attention to the hyperparameters tuning. Both of the models were explained by using the Shapley values produced by the SHAP method.Results: XGBoost produced the best f1-score of 0.84 and as such is considered to be highly competitive among those published in the literature. This achievement, however, was not the main contribution of this paper. This research's goal was to perform global and local interpretability of both the intelligent models and derive valuable conclusions over the established hypothesis. Those methods led to a single scheme which presents either positive, or, negative influence of the values of each of the features whose importance has been confirmed by means of Shapley values. This scheme might be considered as additional source of knowledge for the physicians and other experts whose concern is the exact diagnosis of early stage of Alzheimer's disease.Conclusion: The conclusions derived from the intelligent models interpretability rejected all the established hypothesis. This research clearly showed the importance of Machine learning explainability approach that opens the black box and clearly unveils the relationships among the features and the diagnoses.

A Comparative Study of Alzheimer Detection Techniques

2021 ◽  
Vol 9 (8) ◽  
pp. 2877-2883
Author(s):  
Adwait Patil
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Comparative Study ◽  
Fuzzy System ◽  
Early Stage ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Detection Techniques

Abstract: Alzheimer’s disease is one of the neurodegenerative disorders. It initially starts with innocuous symptoms but gradually becomes severe. This disease is so dangerous because there is no treatment, the disease is detected but typically at a later stage. So it is important to detect Alzheimer at an early stage to counter the disease and for a probable recovery for the patient. There are various approaches currently used to detect symptoms of Alzheimer’s disease (AD) at an early stage. The fuzzy system approach is not widely used as it heavily depends on expert knowledge but is quite efficient in detecting AD as it provides a mathematical foundation for interpreting the human cognitive processes. Another more accurate and widely accepted approach is the machine learning detection of AD stages which uses machine learning algorithms like Support Vector Machines (SVMs) , Decision Tree , Random Forests to detect the stage depending on the data provided. The final approach is the Deep Learning approach using multi-modal data that combines image , genetic data and patient data using deep models and then uses the concatenated data to detect the AD stage more efficiently; this method is obscure as it requires huge volumes of data. This paper elaborates on all the three approaches and provides a comparative study about them and which method is more efficient for AD detection. Keywords: Alzheimer’s Disease (AD), Fuzzy System , Machine Learning , Deep Learning , Multimodal data

scholarly journals Data Analysis With Shapley Values For Automatic Subject Selection in Alzheimer's Disease Data Sets Using Interpretable Machine Learning

2021 ◽  
Author(s):  
Louise Bloch ◽  
Christoph M. Friedrich
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Test Data ◽  
Noisy Data ◽  
Training Data ◽  
Data Sets ◽  
Data Set ◽  
Model Interpretation ◽  
Percentage Points ◽  
Shapley Values

Abstract Background: The prediction of whether Mild Cognitive Impaired (MCI) subjects will prospectively develop Alzheimer's Disease (AD) is important for the recruitment and monitoring of subjects for therapy studies. Machine Learning (ML) is suitable to improve early AD prediction. The etiology of AD is heterogeneous, which leads to noisy data sets. Additional noise is introduced by multicentric study designs and varying acquisition protocols. This article examines whether an automatic and fair data valuation method based on Shapley values can identify subjects with noisy data. Methods: An ML-workow was developed and trained for a subset of the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort. The validation was executed for an independent ADNI test data set and for the Australian Imaging, Biomarker and Lifestyle Flagship Study of Ageing (AIBL) cohort. The workow included volumetric Magnetic Resonance Imaging (MRI) feature extraction, subject sample selection using data Shapley, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) for model training and Kernel SHapley Additive exPlanations (SHAP) values for model interpretation. This model interpretation enables clinically relevant explanation of individual predictions. Results: The XGBoost models which excluded 116 of the 467 subjects from the training data set based on their Logistic Regression (LR) data Shapley values outperformed the models which were trained on the entire training data set and which reached a mean classification accuracy of 58.54 % by 14.13 % (8.27 percentage points) on the independent ADNI test data set. The XGBoost models, which were trained on the entire training data set reached a mean accuracy of 60.35 % for the AIBL data set. An improvement of 24.86 % (15.00 percentage points) could be reached for the XGBoost models if those 72 subjects with the smallest RF data Shapley values were excluded from the training data set. Conclusion: The data Shapley method was able to improve the classification accuracies for the test data sets. Noisy data was associated with the number of ApoEϵ4 alleles and volumetric MRI measurements. Kernel SHAP showed that the black-box models learned biologically plausible associations.

scholarly journals A Comprehensive Machine Learning Framework for the Exact Prediction of the Age of Onset in Familial and Sporadic Alzheimer’s Disease

Diagnostics ◽  
2021 ◽  
Vol 11 (5) ◽  
pp. 887
Author(s):  
Jorge I. Vélez ◽  
Luiggi A. Samper ◽  
Mauricio Arcos-Holzinger ◽  
Lady G. Espinosa ◽  
Mario A. Isaza-Ruget ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Mean Squared Error ◽  
Age Of Onset ◽  
Late Onset ◽  
Training Data ◽  
Therapeutic Interventions ◽  
Data Set ◽  
Unseen Data

Machine learning (ML) algorithms are widely used to develop predictive frameworks. Accurate prediction of Alzheimer’s disease (AD) age of onset (ADAOO) is crucial to investigate potential treatments, follow-up, and therapeutic interventions. Although genetic and non-genetic factors affecting ADAOO were elucidated by other research groups and ours, the comprehensive and sequential application of ML to provide an exact estimation of the actual ADAOO, instead of a high-confidence-interval ADAOO that may fall, remains to be explored. Here, we assessed the performance of ML algorithms for predicting ADAOO using two AD cohorts with early-onset familial AD and with late-onset sporadic AD, combining genetic and demographic variables. Performance of ML algorithms was assessed using the root mean squared error (RMSE), the R-squared (R2), and the mean absolute error (MAE) with a 10-fold cross-validation procedure. For predicting ADAOO in familial AD, boosting-based ML algorithms performed the best. In the sporadic cohort, boosting-based ML algorithms performed best in the training data set, while regularization methods best performed for unseen data. ML algorithms represent a feasible alternative to accurately predict ADAOO with little human intervention. Future studies may include predicting the speed of cognitive decline in our cohorts using ML.

scholarly journals Supervised Machine Learning Algorithms For Early Diagnosis Of Alzheimer’s Disease

2019 ◽  
Vol 8 (3) ◽  
pp. 7964-7967
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Memory Loss ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Diagnostic Tools ◽  
Longitudinal Mri ◽  
Permanent Brain Damage

Alzheimer’s is a neurodegenerative disease which can eventually leads to dementia. Mostly occurring in elderly people over the age of 65, it is hard to detect and diagnose correctly. Most common symptoms include memory loss and slow deterioration of cognitive functions. Given that these symptoms are seen often in old people, this hinders the detection of Alzheimer’s disease (AD). Alzheimer’s is currently incurable, but detection of the disease during its early stage is often beneficial to the patient, since there are treatments which can considerably improve the quality of life of the patient. However this can only be done if the patient has been diagnosed at a stage before any permanent brain damage has been done. Most of the current methods for detecting and diagnosing AD are not good enough. It is the need of the hour to develop better and early diagnostic tools. With the improvements in the field of machine learning, we now have the tools needed to drastically improve detection of Alzheimer’s. We examine various machine learning methods and algorithms to find a method which can boost the chances of detecting the disease. We will use the following algorithms: Decision Tree, SVM, Random Forest and Adaboost. The dataset being used is the longitudinal MRI data available included in the OASIS dataset. We will use the aforementioned algorithms on the dataset and compare the accuracies achieved to find an optimal.

scholarly journals Improved Reasoning with Uncertainty Based Significant Feature Subset Selection for Alzheimer’s Disease Detection

2019 ◽  
Vol 8 (3) ◽  
pp. 3123-3131
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Neurodegenerative Disorder ◽  
Early Stage ◽  
Subset Selection ◽  
Feature Subset Selection ◽  
Significant Feature ◽  
Feature Subset ◽  
Shafer Theory

In this modern era neurodegenerative disorder of undefined causes affects the older adults and it becomes most cause of dementia. The Alzheimer’s disease is one of such neurodegenerative disorder which is very complex and hard to predict in the early stage. With evolving advancement in the field of machine learning, it is possible to predict the early stage of AD and diagnosing in initial stages may produce effect result for their further quality and healthy life. But uncertainty in determination of Alzheimer’s is a toughest challenge for the researchers in the field of machine learning. This paper aims to overcome the uncertainty in discovering dementia and non-dementia victims of Alzheimer’s by devising an improved reasoning with uncertainty based prominent feature subset selection using modified fuzzy dempster shafer theory (IRU-DST). For Alzheimer’s disease prediction the dataset is used form OASIS dataset. The performance of the proposed IRU-DST is validated using fuzzy artificial neural network. The simulation results proved the performance of the IRU-DST achieves better results comparing the other sate of arts, by gaining high accuracy rate and it also minimize the error rate considerably with the ability of handling uncertainty.

scholarly journals Exploring the methods on early detection of Alzheimer's disease

2020 ◽  
Vol 9 (1) ◽  
pp. 1754-1758
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Neural Networks ◽  
Alzheimer's Disease ◽  
Early Detection ◽  
Early Stage ◽  
Optimization Techniques ◽  
Maximum Information ◽  
Daily Task ◽  
Comparison Of Techniques

Alzheimer’s disease (AD) is a disorder which is said to be irreversible and affects the behavior and cognitive processes which will eventually affect the memory. This disease beget difficulty in performing the daily task of a patient. It is one of the most common form of dementia affecting people above the age 65 and the risk increases with age. The treatments currently available can only mitigate AD progression but there is no treatment to stop this progression. To bring down the progression of AD early detection becomes necessary. Researchers have found that many machine learning (ML) methods have been useful in detection of AD. Machine learning is a part of artificial intelligence involving probabilistic and optimization techniques such as neural networks that prepares pc's to gain a model from complex datasets. This paper Scrutinizes the developments taken in the field of ML for the possibly early diagnosis of AD. It discusses about various approaches used in recent times for the detection of AD at an early stage. Through this research we found several classification methods such as Recurrent neural networks(RNN), Convolution neural networks(CNN), many more binary and multiclass classifiers along with various methods of preprocessing steps involved in the detection of AD. This paper also throws light on the datasets being used and how these preprocessing steps and different classifiers attribute to increase of accuracy in prediction of AD. Finally, coming to the objective of this paper is to analyze and evaluate these different techniques of ML contributing for the detection AD as early as possible and also to help the researchers to get maximum information and comparison of techniques in one go.

scholarly journals Language Impairment in Alzheimer’s Disease—Robust and Explainable Evidence for AD-Related Deterioration of Spontaneous Speech Through Multilingual Machine Learning

2021 ◽  
Vol 13 ◽  
Author(s):  
Hali Lindsay ◽  
Johannes Tröger ◽  
Alexandra König
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Language Processing ◽  
Language Impairment ◽  
Spontaneous Speech ◽  
Semantic Features ◽  
Equal Distribution ◽  
Depth Analysis ◽  
Picture Description

Alzheimer’s disease (AD) is a pervasive neurodegenerative disease that affects millions worldwide and is most prominently associated with broad cognitive decline, including language impairment. Picture description tasks are routinely used to monitor language impairment in AD. Due to the high amount of manual resources needed for an in-depth analysis of thereby-produced spontaneous speech, advanced natural language processing (NLP) combined with machine learning (ML) represents a promising opportunity. In this applied research field though, NLP and ML methodology do not necessarily ensure robust clinically actionable insights into cognitive language impairment in AD and additional precautions must be taken to ensure clinical-validity and generalizability of results. In this study, we add generalizability through multilingual feature statistics to computational approaches for the detection of language impairment in AD. We include 154 participants (78 healthy subjects, 76 patients with AD) from two different languages (106 English speaking and 47 French speaking). Each participant completed a picture description task, in addition to a battery of neuropsychological tests. Each response was recorded and manually transcribed. From this, task-specific, semantic, syntactic and paralinguistic features are extracted using NLP resources. Using inferential statistics, we determined language features, excluding task specific features, that are significant in both languages and therefore represent “generalizable” signs for cognitive language impairment in AD. In a second step, we evaluated all features as well as the generalizable ones for English, French and both languages in a binary discrimination ML scenario (AD vs. healthy) using a variety of classifiers. The generalizable language feature set outperforms the all language feature set in English, French and the multilingual scenarios. Semantic features are the most generalizable while paralinguistic features show no overlap between languages. The multilingual model shows an equal distribution of error in both English and French. By leveraging multilingual statistics combined with a theory-driven approach, we identify AD-related language impairment that generalizes beyond a single corpus or language to model language impairment as a clinically-relevant cognitive symptom. We find a primary impairment in semantics in addition to mild syntactic impairment, possibly confounded by additional impaired cognitive functions.

scholarly journals ANALYSIS OF ALZHEIMER DISEASE PREDICTION USING MACHINE LEARNING TECHNIQUES

2021 ◽  
Vol 9 (1) ◽  
pp. 519-525
Author(s):  
B. Hemalatha, Dr. M. Renukadevi
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Know How ◽  
Positron Emission ◽  
Learning Techniques ◽  
The Many

Alzheimer's Disease (AD) is referred to as one of the highest non-unusual neurodegenerative disorders that inflict eternal harm to the memory-associated brain cells and wonder skills. There is a 99.6 percent failure rate in clinical trials of Alzheimer's disease pills, perhaps due to the fact that AD sufferers cannot be without early-stage complications. This observation analyzed machine learning knowledge of strategies to use empirical statistics to forecast the progression of AD in the years of fate. Diagnosis of AD is often difficult, particularly at an early stage in the disease system, due to the degree of mild cognitive impairment (MCI). However, it is at this point where treatment is much more likely to be successful, so there will be great benefits in enhancing the diagnosis process. Research in this area aims to identify the most complex mechanisms directly related to changes in AD. Various imaging methods are used to diagnose AD, and image modes play a key role in the diagnosis of AD. This paper uses a Positron Emission Tomography (PET) image to detect AD early. The PET image is often used to know how organs and tissues function in the human body. This research study analyses prediction approaches using various kinds of machine learning algorithms to solve AD diagnostic problems. Artificial Neural Networks are one of the many algorithms. Modern research has shown that deep learning is a proficient technique for solving numerous problems of image recognition, but most of these published approaches owe their performance to training on a very large number of data samples.

scholarly journals Personalized Early Stage Alzheimer’s Disease Detection: A Case Study of President Reagan’s Speeches

2020 ◽  
Author(s):  
Ning Wang ◽  
Vishal Peddagangireddy ◽  
Fan Luo ◽  
K.P. Subbalakshmi ◽  
R. Chandramouli
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Mental Healthcare ◽  
Statistical Technique ◽  
Health Issues ◽  
Data Set ◽  
Mental Health Issues

AbstractAlzheimer’s disease (AD)-related global healthcare cost is estimated to be $1 trillion by 2050. Currently, there is no cure for this disease; however, clinical studies show that early diagnosis and intervention helps to extend the quality of life and inform technologies for personalized mental healthcare. Clinical research indicates that the onset and progression of Alzheimer’s disease lead to dementia and other mental health issues. As a result, the language capabilities of patient start to decline.In this paper, we show that machine learning-based unsupervised clustering of and anomaly detection with linguistic biomarkers are promising approaches for intuitive visualization and personalized early stage detection of Alzheimer’s disease. We demonstrate this approach on 10 year’s (1980 to 1989) of President Ronald Reagan’s speech data set. Key linguistic biomarkers that indicate early-stage AD are identified. Experimental results show that Reagan had early onset of Alzheimer’s sometime between 1983 and 1987. This finding is corroborated by prior work that analyzed his interviews using a statistical technique. The proposed technique also identifies the exact speeches that reflect linguistic biomarkers for early stage AD.

A Community-Based Study Identifying Metabolic Biomarkers of Mild Cognitive Impairment and Alzheimer’s Disease Using Artificial Intelligence and Machine Learning

2020 ◽  
Vol 78 (4) ◽  
pp. 1381-1392
Author(s):  
Ali Yilmaz ◽  
Ilyas Ustun ◽  
Zafer Ugur ◽  
Sumeyya Akyol ◽  
William T. Hu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Lipid Metabolism ◽  
Mild Cognitive Impairment ◽  
Proton Nuclear Magnetic Resonance ◽  
Community Based ◽  
Depth Analysis

Background: Currently, there is no objective, clinically available tool for the accurate diagnosis of Alzheimer’s disease (AD). There is a pressing need for a novel, minimally invasive, cost friendly, and easily accessible tool to diagnose AD, assess disease severity, and prognosticate course. Metabolomics is a promising tool for discovery of new, biologically, and clinically relevant biomarkers for AD detection and classification. Objective: Utilizing artificial intelligence and machine learning, we aim to assess whether a panel of metabolites as detected in plasma can be used as an objective and clinically feasible tool for the diagnosis of mild cognitive impairment (MCI) and AD. Methods: Using a community-based sample cohort acquired from different sites across the US, we adopted an approach combining Proton Nuclear Magnetic Resonance Spectroscopy (1H NMR), Liquid Chromatography coupled with Mass Spectrometry (LC-MS) and various machine learning statistical approaches to identify a biomarker panel capable of identifying those patients with AD and MCI from healthy controls. Results: Of the 212 measured metabolites, 5 were identified as optimal to discriminate between controls, and individuals with MCI or AD. Our models performed with AUC values in the range of 0.72–0.76, with the sensitivity and specificity values ranging from 0.75–0.85 and 0.69–0.81, respectively. Univariate and pathway analysis identified lipid metabolism as the most perturbed biochemical pathway in MCI and AD. Conclusion: A comprehensive method of acquiring metabolomics data, coupled with machine learning techniques, has identified a strong panel of diagnostic biomarkers capable of identifying individuals with MCI and AD. Further, our data confirm what other groups have reported, that lipid metabolism is significantly perturbed in those individuals suffering with dementia. This work may provide additional insight into AD pathogenesis and encourage more in-depth analysis of the AD lipidome.

Sign in / Sign up

Export Citation Format

Share Document