Evaluation of Machine Learning Models for the Prediction of Alzheimer's: In Search of the Best Performance

Borne L., Thienel R., Lupton M.K., Guo C., Mosley P., Behler A., Giorgio J., Adam R., Ceslis A., Bourgeat P., Fazlollahi A., Maruff P., Rowe C.C., Masters C.L., Fripp J., et. al.

AbstractDeficits in memory are seen as a canonical sign of aging and a prodrome to dementia in older adults. However, our understanding of age-related cognition and brain morphology occurring throughout a broader spectrum of adulthood remains limited. We quantified the relationship between cognitive function and brain morphology (sulcal width, SW) using three cross-sectional observational datasets (PISA, AIBL, ADNI) from mid-life to older adulthood, assessing the influence of age, sex, amyloid (Aβ) and genetic risk for dementia. The data comprised cognitive, genetic and neuroimaging measures of a total of 1570 non-clinical mid-life and older adults (mean age 72, range 49–90 years, 1330 males) and 1365 age- and sex-matched adults with mild cognitive impairment (MCI) or Alzheimer’s disease (AD). Among non-clinical adults, we found robust modes of co-variation between regional SW and multidomain cognitive function that differed between the mid-life and older age range. These cortical and cognitive profiles derived from healthy cohorts predicted out-of-sample AD and MCI. Furthermore, Aβ-deposition and educational attainment levels were associated with cognition but not SW. These findings underscoring the complex interplay between factors influencing cognition and brain structure from mid-life onwards, providing valuable insights for future research into neurodegeneration and the development of future screening algorithms.

Zapata-Paulini J., Cabanillas-Carbonell M.

Parkinson's is a neurodegenerative disease that generally affects people over 60 years of age. The disease destroys neurons and increases the accumulation of α-synuclein in many parts of the brain stem, although at present its causes remain unknown. It is therefore a priority to identify a method that can detect the disease, and this is where machine learning models become important. This study aims to perform a comparative analysis of machine learning models focused on the early detection of Parkinson's disease. Logistic regression (LR), support vector machines (SVM), decision trees (DT), extra trees classifiers (ETC), K-nearest neighbors (KNN), random forests (RF), adaptive boosting (AdaBoost) and gradient boosting (GB) algorithms are described and developed to identify the one that offers the best performance. In the training stage, we used the Oxford University dataset for Parkinson's disease detection, which has a total of 23 attributes and 195 records on patient voice recordings. The article is structured into six sections, such as introduction, related work, methodology, results, discussions, and conclusions. The metrics of accuracy, sensitivity, F1 count, and precision were used to measure the models' performance. The results position the KNN model as the best predictor with 95% accuracy, precision, sensitivity, and F1 score.

Park S., Setiawan V.W., Crimmins E.M., White L.R., Wu A.H., Cheng I., Darst B.F., Haiman C.A., Wilkens L.R., Le Marchand L., Lim U.

Background and Objectives Previous studies estimated that modifiable risk factors explain up to 40% of the dementia cases in the United States and that this population-attributable fraction (PAF) differs by race and ethnicity—estimates of future impact based on the risk factor prevalence in contemporary surveys. The aim of this study was to determine the race-specific and ethnicity-specific PAF of late-onset Alzheimer disease and related dementias (ADRDs) based on the risk factor prevalence and associations observed on the same individuals within a prospective cohort. Methods Data were from Multiethnic Cohort Study participants (African American, Japanese American, Latino, Native Hawaiian, and White) enrolled in Medicare Fee-for-Service. We estimated the PAF based on the prevalence of risk factors at cohort baseline and their mutually adjusted association with subsequent ADRD incidence. Risk factors included low educational attainment and midlife exposures to low neighborhood socioeconomic status, unmarried status, history of hypertension, stroke, diabetes or heart disease, smoking, physical inactivity, short or long sleep duration, obesity, and low-quality diet, as well as APOE ε4 for a subset. Results Among 91,881 participants (mean age 59.3 at baseline, 55.0% female participants), 16,507 incident ADRD cases were identified from Medicare claims (1999–2016, mean follow-up 9.3 years). The PAF for nongenetic factors combined was similar in men (24.0% [95% CI 21.3–26.6]) and women (22.8% [20.3–25.2]) but varied across Japanese American (14.2% [11.1–17.2]), White (21.9% [19.0–24.7]), African American (27.8% [22.3–33.0]), Native Hawaiian (29.3% [21.0–36.7]), and Latino (33.3% [27.5–38.5]) groups. The combined PAF was attenuated when accounting for competing risk of death, in both men (10.4%) and women (13.9%) and across racial and ethnic groups (4.7%–25.5%). The combined PAF was also different by age at diagnosis and ADRD subtypes, higher for younger (65–74 years: 43.2%) than older (75–84 years: 32.4%; ≥85 years: 11.3%) diagnoses and higher for vascular or unspecified ADRD than for AD or Lewy body dementia. An additional PAF of 11.8% (9.9–13.6) was associated with APOE ε4, which together with nongenetic risk factors accounted for 30.6% (25.8–35.1) of ADRD. Discussion Known risk factors explained about a third of the ADRD cases but with unequal distributions across racial and ethnic groups.

Biechele G., Rauchmann B., Janowitz D., Buerger K., Franzmeier N., Weidinger E., Guersel S., Schuster S., Finze A., Harris S., Lindner S., Albert N.L., Wetzel C., Rupprecht R., Rominger A., et. al.

Abstract Background and objectives 18-kDa translocator protein position-emission-tomography (TSPO-PET) imaging emerged for in vivo assessment of neuroinflammation in Alzheimer’s disease (AD) research. Sex and obesity effects on TSPO-PET binding have been reported for cognitively normal humans (CN), but such effects have not yet been systematically evaluated in patients with AD. Thus, we aimed to investigate the impact of sex and obesity on the relationship between β-amyloid-accumulation and microglial activation in AD. Methods 49 patients with AD (29 females, all Aβ-positive) and 15 Aβ-negative CN (8 female) underwent TSPO-PET ([18F]GE-180) and β-amyloid-PET ([18F]flutemetamol) imaging. In 24 patients with AD (14 females), tau-PET ([18F]PI-2620) was additionally available. The brain was parcellated into 218 cortical regions and standardized-uptake-value-ratios (SUVr, cerebellar reference) were calculated. Per region and tracer, the regional increase of PET SUVr (z-score) was calculated for AD against CN. The regression derived linear effect of regional Aβ-PET on TSPO-PET was used to determine the Aβ-plaque-dependent microglial response (slope) and the Aβ-plaque-independent microglial response (intercept) at the individual patient level. All read-outs were compared between sexes and tested for a moderation effect of sex on associations with body mass index (BMI). Results In AD, females showed higher mean cortical TSPO-PET z-scores (0.91 ± 0.49; males 0.30 ± 0.75; p = 0.002), while Aβ-PET z-scores were similar. The Aβ-plaque-independent microglial response was stronger in females with AD (+ 0.37 ± 0.38; males with AD − 0.33 ± 0.87; p = 0.006), pronounced at the prodromal stage. On the contrary, the Aβ-plaque-dependent microglial response was not different between sexes. The Aβ-plaque-independent microglial response was significantly associated with tau-PET in females (Braak-II regions: r = 0.757, p = 0.003), but not in males. BMI and the Aβ-plaque-independent microglial response were significantly associated in females (r = 0.44, p = 0.018) but not in males (BMI*sex interaction: F(3,52) = 3.077, p = 0.005). Conclusion While microglia response to fibrillar Aβ is similar between sexes, women with AD show a stronger Aβ-plaque-independent microglia response. This sex difference in Aβ-independent microglial activation may be associated with tau accumulation. BMI is positively associated with the Aβ-plaque-independent microglia response in females with AD but not in males, indicating that sex and obesity need to be considered when studying neuroinflammation in AD.

Li D., Jia J., Zeng H., Zhong X., Chen H., Yi C.

Abstract Alzheimer’s disease (AD) is a progressive and degenerative neurological disease characterized by the deterioration of cognitive functions. While a definitive cure and optimal medication to impede disease progression are currently unavailable, a plethora of studies have highlighted the potential advantages of exercise rehabilitation for managing this condition. Those studies show that exercise rehabilitation can enhance cognitive function and improve the quality of life for individuals affected by AD. Therefore, exercise rehabilitation has been regarded as one of the most important strategies for managing patients with AD. Herein, we provide a comprehensive analysis of the currently available findings on exercise rehabilitation in patients with AD, with a focus on the exercise types which have shown efficacy when implemented alone or combined with other treatment methods, as well as the potential mechanisms underlying these positive effects. Specifically, we explain how exercise may improve the brain microenvironment and neuronal plasticity. In conclusion, exercise is a cost-effective intervention to enhance cognitive performance and improve quality of life in patients with mild to moderate cognitive dysfunction. Therefore, it can potentially become both a physical activity and a tailored intervention. This review may aid the development of more effective and individualized treatment strategies to address the challenges imposed by this debilitating disease, especially in low-and middle-income countries.

Souchet B., Michaïl A., Billoir B., Braudeau J.

Alzheimer’s disease (AD) was first characterized by Dr. Alois Alzheimer in 1906 by studying a demented patient and discovering cerebral amyloid plaques and neurofibrillary tangles. Subsequent research highlighted the roles of Aβ peptides and tau proteins, which are the primary constituents of these lesions, which led to the amyloid cascade hypothesis. Technological advances, such as PET scans using Florbetapir, have made it possible to visualize amyloid plaques in living patients, thus improving AD’s risk assessment. The National Institute on Aging and the Alzheimer’s Association introduced biological diagnostic criteria in 2011, which underlined the amyloid deposits diagnostic value. However, potential confirmation bias may have led researchers to over-rely on amyloid markers independent of AD’s symptoms, despite evidence of their limited specificity. This review provides a critical examination of the current research paradigm in AD, including, in particular, the predominant focus on amyloid and tau species in diagnostics. We discuss the potential multifaceted consequences of this approach and propose strategies to mitigate its overemphasis in the development of new biomarkers. Furthermore, our study presents comprehensive guidelines aimed at enhancing the creation of biomarkers for accurately predicting AD dementia onset. These innovations are crucial for refining patient selection processes in clinical trial enrollment and for the optimization of therapeutic strategies. Overcoming confirmation bias is essential to advance the diagnosis and treatment of AD and to move towards precision medicine by incorporating a more nuanced understanding of amyloid biomarkers.

Khaleel A.A., Al-Azzawi A.A., Alkhazraji A.M.

<span>Random forest is a machine learning algorithm that mainly built as a classification method to make predictions based on decision trees. Many machine learning approaches used random forest to perform deep analysis on different cancer diseases to understand their complex characterstics and behaviour. However, due to massive and complex data generated from such diseases, it has become difficult to run random forest using single machine. Therefore, advanced tools are highly required to run random forest to analyse such massive data. In this paper, random forest algorithm using Apache Mahout and Hadoop based software defined networking (SDN) are used to conduct the prediction and analysis on large lung cancer datasets. Several experiments are conducted to evaluate the proposed system. Experiments are conducted using nine virtual nodes. Experiments show that the implementation of random forest algorithm using the proposed work outperforms its implementation in traditional environment with regard to the execution time. Comparison between the proposed system using Hadoop based SDN and Hadoop only is performed. Results show that random forest using Hadoop based SDN has less execution time than when using Hadoop only. Furthermore, experiments reveal that the performance of implemented system achieved more efficiency regarding execution time, accuracy and reliability.</span>

Rajayyan S., Mohamed Mustafa S.M.

Dementia is a brain disease that stays in the seventh position of death rate as per the report of the World Health Organization (WHO). Among the various types of dementia, Alzheimer’s disease has more than 70% of cases of dementia. The objective is to predict dementia disease from the open access series of imaging studies (OASIS) dataset using machine learning techniques. Also, the performance of the machine learning model is analyzed to improve the performance of the model using the cuckoo algorithm. In this paper, feature engineering has been focused and the prediction of dementia has been done using the OASIS dataset with the help of data mining techniques. Feature engineering is followed by prediction using the machine learning model Gaussian naïve Bayes (NB), support vector machine, and linear regression. Also, the best prediction model has been selected and done the validation. The evaluation metrics considered for validating the models are accuracy, precision, recall, and F1-Score and the highest values are 95%, 97%, 95%, and 95%. The Gaussian NB has been given these best results. The accuracy of the machine learning models has been increased by eliminating the factors which affect the performance of the models using the cuckoo algorithm.

Roy A., Chakraborty S.

Support vector machine (SVM) is a powerful machine learning technique relying on the structural risk minimization principle. The applications of SVM in structural reliability analysis (SRA) are enormous in the recent past. There are review articles on machine learning-based methods that partly discussed the development of SVM for SRA applications along with other machine learning methods. However, there is no dedicated review on SVM for SRA applications. Thus, a review article on the implementation of various SVM approaches for SRA applications will be useful. The present article provides a synthesis and roadmap to the growing and diverse literature, specifically the classification and regression-based support vector algorithms in SRA applications. In doing so, different advanced variants of SVM in SRA applications and hyperparameter tuning algorithms are also briefly discussed. Following the detailed review studies, future opportunities and challenges in the area of applications are summarized. The review in general reveals that the SVM in SRA applications is getting thrust as it has an excellent capability of handling high-dimensional problems utilizing relatively lesser training data. The review article is expected to enhance the state-of-the-art developments of support vector algorithms for SRA applications.

Uddin K.M., Alam M.J., Jannat-E-Anawar, Uddin M.A., Aryal S.

Alzheimer's disease (AD) is one of the leading causes of dementia among older people. In addition, a considerable portion of the world's population suffers from metabolic problems, such as Alzheimer's disease and diabetes. Alzheimer's disease affects the brain in a degenerative manner. As the elderly population grows, this illness can cause more people to become inactive by impairing their memory and physical functionality. This might impact their family members and the financial, economic, and social spheres. Researchers have recently investigated different machine learning and deep learning approaches to detect such diseases at an earlier stage. Early diagnosis and treatment of AD help patients to recover from it successfully and with the least harm. This paper proposes a machine learning model that comprises GaussianNB, Decision Tree, Random Forest, XGBoost, Voting Classifier, and GradientBoost to predict Alzheimer's disease. The model is trained using the open access series of imaging studies (OASIS) dataset to evaluate the performance in terms of accuracy, precision, recall, and F1 score. Our findings showed that the voting classifier attained the highest validation accuracy of 96% for the AD dataset. Therefore, ML algorithms have the potential to drastically lower Alzheimer's disease annual mortality rates through accurate detection.

Kreuzberger D., Kühl N., Hirschl S.

Dhakal S., Azam S., Hasib K.M., Karim A., Jonkman M., Haque A.S.

Dementia is a chronic and degenerative condition, which has become a major health concern among the elderly. With ever-continuing cases of dementia, it has become a very challenging task in the 21st century to provide care for patients with dementia. This paper proposes a framework for the prediction of dementia using the data collected from the OASIS (Open Access Series of Imaging Studies) project which was made available by the Washington University Alzheimer's Disease Research Centre. Different techniques have been implemented for data imputation, pre-processing and data transformation to create suitable data for training the model. Machine learning approaches like Adaboost (AB), Decision Tree (DT), Extra Tree (ET), Gradient Boost (GB), K-Nearest Neighbour (KNN), Logistic Regression (LR), Naïve Bayes (NB), Random Forest (RF), and SVM (Support Vector Machine) has been used for a combination of features. These techniques have been applied to the full set of features and features selected from Least Absolute Shrinkage and Selection Operator (LASSO) techniques. A comparison between the accuracy, precision, and other metrics based on the results of the classification algorithms has been provided. The experimental results show that the highest accuracy of 96.77% was obtained by Support Vector Machine (SVM) with full features. The proposed methodology is promising and if developed and deployed can be helpful for the rapid assessment of Alzheimer's Disease (AD).

Javeed A., Dallora A.L., Berglund J.S., Idrisoglu A., Ali L., Rauf H.T., Anderberg P.

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.

Hua H., Li Y., Wang T., Dong N., Li W., Cao J.

Recent years have witnessed the widespread popularity of Internet of things (IoT). By providing sufficient data for model training and inference, IoT has promoted the development of artificial intelligence (AI) to a great extent. Under this background and trend, the traditional cloud computing model may nevertheless encounter many problems in independently tackling the massive data generated by IoT and meeting corresponding practical needs. In response, a new computing model called edge computing (EC) has drawn extensive attention from both industry and academia. With the continuous deepening of the research on EC, however, scholars have found that traditional (non-AI) methods have their limitations in enhancing the performance of EC. Seeing the successful application of AI in various fields, EC researchers start to set their sights on AI, especially from a perspective of machine learning, a branch of AI that has gained increased popularity in the past decades. In this article, we first explain the formal definition of EC and the reasons why EC has become a favorable computing model. Then, we discuss the problems of interest in EC. We summarize the traditional solutions and hightlight their limitations. By explaining the research results of using AI to optimize EC and applying AI to other fields under the EC architecture, this article can serve as a guide to explore new research ideas in these two aspects while enjoying the mutually beneficial relationship between AI and EC.