Machine learning for the life-time risk prediction of Alzheimer's disease: a systematic review

Transforming neurodegenerative disorder care with machine learning: Strategies and applications

Neurodegenerative diseases (NDs), characterized by progressive neuronal degeneration and manifesting in diverse forms such as memory loss and movement disorders, pose significant challenges due to their complex molecular mechanisms and heterogeneous patient presentations. Diagnosis often relies heavily on clinical assessments and neuroimaging, with definitive confirmation frequently requiring post-mortem autopsy. However, the emergence of Artificial Intelligence (AI) and Machine Learning (ML) offers a transformative potential. These technologies can enable the development of non-invasive tools for early diagnosis, biomarker identification, personalized treatment strategies, patient subtyping and stratification, and disease risk prediction. This review aims to provide a starting point for researchers, both with and without clinical backgrounds, who are interested in applying ML to NDs. We will discuss available data resources for key diseases like Alzheimer's and Parkinson's, explore how ML can revolutionize neurodegenerative care, and emphasize the importance of integrating multiple high-dimensional data sources to gain deeper insights and inform effective therapeutic strategies.

Development of a k-Nearest Neighbors Model for the Prediction of Late-Onset Alzheimer's Risk by Combining Polygenic Risk Scores and Phenotypic Variables

INTRODUCTION

Alzheimer's disease (AD), and more specifically late-onset Alzheimer's disease (LOAD), represents a considerable challenge in terms of early and timely diagnosis and treatment. Early diagnosis is crucial to improve the efficacy of the therapies and patients' quality of life. The current challenge is to accurately identify at-risk individuals before the manifestations of the first symptoms of AD.

METHODS AND RESULTS

Here, we present an improved model for LOAD risk prediction, which applies the k-nearest neighbors (KNN) algorithm. We have achieved a sensitivity of 0.80 and an area under the curve (AUC) of 0.71, which represents a high performance especially when compared to an AUC of 0.66 reported previously in 2019 using a KNN model.

DISCUSSION

The application of a mathematical model that combines genetic and clinical covariates showed a good prediction of the AD/LOAD risk, with the higher weight being the polygenic genetic risk, APOE haplotype, and age. Compared to previous studies, our model integrates and correlates genetic prediction together with phenotypic information by fine-tuning the parameters of the model in order to achieve the best performance. This algorithm can be used in the general population and does not require the manifestation of any symptoms for its effective application. Thus, we present here an advanced model for risk prediction of LOAD.

Comparing the Artificial Intelligence Detection Models to Standard Diagnostic Methods and Alternative Models in Identifying Alzheimer's Disease in At-Risk or Early Symptomatic Individuals: A Scoping Review

Alzheimer's disease (AD) and other neurodegenerative illnesses place a heavy strain on the world's healthcare systems, particularly among the aging population. With a focus on research from January 2022 to September 2023, this scoping review, which adheres to Preferred Reporting Items for Systematic Reviews and Meta-Analysis extension for Scoping Reviews (PRISMA-Scr) criteria, examines the changing landscape of artificial intelligence (AI) applications for early AD detection and diagnosis. Forty-four carefully chosen articles were selected from a pool of 2,966 articles for the qualitative synthesis. The research reveals impressive advancements in AI-driven approaches, including neuroimaging, genomics, cognitive tests, and blood-based biomarkers. Notably, AI models focusing on deep learning (DL) algorithms demonstrate outstanding accuracy in early AD identification, often even before the onset of clinical symptoms. Multimodal approaches, which combine information from various sources, including neuroimaging and clinical assessments, provide comprehensive insights into the complex nature of AD. The study also emphasizes the critical role that blood-based and genetic biomarkers play in strengthening AD diagnosis and risk assessment. When combined with clinical or imaging data, genetic variations and polygenic risk scores help to improve prediction models. In a similar vein, blood-based biomarkers provide non-invasive instruments for detecting metabolic changes linked to AD. Cognitive and functional evaluations, which include neuropsychological examinations and assessments of daily living activities, serve as essential benchmarks for monitoring the course of AD and directing treatment interventions. When these evaluations are included in machine learning models, the diagnosis accuracy is improved, and treatment monitoring is made more accessible. In addition, including methods that support model interpretability and explainability helps in the thorough understanding and valuable implementation of AI-driven insights in clinical contexts. This review further identifies several gaps in the research landscape, including the need for diverse, high-quality datasets to address data heterogeneity and improve model generalizability. Practical implementation challenges, such as integrating AI systems into clinical workflows and clinician adoption, are highlighted as critical barriers to real-world application. Moreover, ethical considerations, particularly surrounding data privacy and informed consent, must be prioritized as AI adoption in healthcare accelerates. Performance metrics (e.g., sensitivity, specificity, and area under the curve (AUC)) for AI-based approaches are discussed, with a need for clearer reporting and comparative analyses. Addressing these limitations, alongside methodological clarity and critical evaluation of biases, would strengthen the credibility of AI applications in AD detection. By expanding its scope, this study highlights areas for improvement and future opportunities in early detection, aiming to bridge the gap between innovative AI technologies and practical clinical utility.

The association between genetic variations and morphology-based brain networks changes in Alzheimer's disease

Alzheimer's disease (AD) is a highly heritable disease. The morphological changes of cortical cortex (such as, cortical thickness and surface area) in AD always accompany by the change of the functional connectivity to other brain regions and influence the short- and long-range brain network connections, causing functional deficits of AD. In this study, the first hypothesis is that genetic variations might affect morphology-based brain networks, leading to functional deficits; the second hypothesis is that protein-protein interaction (PPI) between the candidate proteins and known interacting proteins to AD might exist and influence AD. 600 470 variants and structural magnetic resonance imaging scans from 175 AD patients and 214 healthy controls were obtained from the Alzheimer's Disease Neuroimaging Initiative-1 database. A co-sparse reduced-rank regression model was fit to study the relationship between non-synonymous mutations and morphology-based brain networks. After that, PPIs between selected genes and BACE1, an enzyme that was known to be related to AD, are explored by using molecular dynamics (MD) simulation and co-immunoprecipitation (Co-IP) experiments. Eight genes affecting morphology-based brain networks were identified. The results of MD simulation showed that the PPI between TGM4 and BACE1 was the strongest among them and its interaction was verified by Co-IP. Hence, gene variations influence morphology-based brain networks in AD, leading to functional deficits. This finding, validated by MD simulation and Co-IP, suggests that the effect is robust.

A Systematic Review of Genetics- and Molecular-Pathway-Based Machine Learning Models for Neurological Disorder Diagnosis

The process of identification and management of neurological disorder conditions faces challenges, prompting the investigation of novel methods in order to improve diagnostic accuracy. In this study, we conducted a systematic literature review to identify the significance of genetics- and molecular-pathway-based machine learning (ML) models in treating neurological disorder conditions. According to the study's objectives, search strategies were developed to extract the research studies using digital libraries. We followed rigorous study selection criteria. A total of 24 studies met the inclusion criteria and were included in the review. We classified the studies based on neurological disorders. The included studies highlighted multiple methodologies and exceptional results in treating neurological disorders. The study findings underscore the potential of the existing models, presenting personalized interventions based on the individual's conditions. The findings offer better-performing approaches that handle genetics and molecular data to generate effective outcomes. Moreover, we discuss the future research directions and challenges, emphasizing the demand for generalizing existing models in real-world clinical settings. This study contributes to advancing knowledge in the field of diagnosis and management of neurological disorders.

Assessment of Lifetime Risk for Cardiovascular Disease: Time to Move Forward

Over the past decades, there has been a notable increase in the risk of Cardiovascular Disease (CVD), even among younger individuals. Policymakers and the health community have revised CVD prevention programs to include younger people in order to take these new circumstances into account. A variety of CVD risk assessment tools have been developed in the past years with the aim of identifying potential CVD candidates at the population level; however, they can hardly discriminate against younger individuals at high risk of CVD.Therefore, in addition to the traditional 10-year CVD risk assessment, lifetime CVD risk assessment has recently been recommended by the American Heart Association/American College of Cardiology and the European Society of Cardiology prevention guidelines, particularly for young individuals. Methodologically, the benefits of these lifetime prediction models are the incorporation of left truncation observed in survival curves and the risk of competing events which are not considered equivalent in the common survival analysis. Thus, lifetime risk data are easily understandable and can be utilized as a risk communication tool for Public Health surveillance. However, given the peculiarities behind these estimates, structural harmonization should be conducted in order to create a sex-, race-specific tool that is sensitive to accurately identifying individuals who are at high risk of CVD. In this review manuscript, we present the most commonly used lifetime CVD risk tools, elucidate several methodological and critical points, their limitations, and the rationale behind their integration into everyday clinical practice.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Evaluating the Classification Accuracy of Expression Quantitative Trait Loci Calculated Polygenic Risk Scores in Alzheimer's Disease

Polygenic risk scores (PRS) hold promise for the early identification of those at risk from neurodegenerative disorders such as Alzheimer's Disease (AD), allowing for intervention to occur prior to neuronal damage. The current selection of informative single nucleotide polymorphisms (SNPs) to generate the risk scores is based on the modelling of large genome-wide association data using significance thresholds. However, the biological relevance of these SNPs is largely unknown. This study, in contrast, aims to identify SNPs with biological relevance to AD and then assess them for their ability to accurately classify cases and controls. Samples selected from the Brains for Dementia Research (BDR) were used to produce gene expression data to identify potential expression quantitative trait loci (eQTLs) relevant to AD. These SNPs were then incorporated into a PRS model to classify AD and controls in the full BDR cohort. Models derived from these eQTLs demonstrate modest classification potential with an accuracy between 61% and 67%. Although the model accuracy is not as high as some values in the literature based on significance thresholds from genome-wide association studies, these models may reflect a more biologically relevant model, which may provide novel targets for therapeutic intervention.

Predicting the Risk of Alzheimer's Disease and Related Dementia in Patients with Mild Cognitive Impairment Using a Semi-Competing Risk Approach

Alzheimer's disease (AD) and AD-related dementias (AD/ADRD) are a group of progressive neurodegenerative diseases. The progression of AD can be conceptualized as a continuum in which patients progress from normal cognition to preclinical AD (i.e., no symptoms but biological changes in the brain) to mild cognitive impairment (MCI) due to AD (i.e., mild symptoms but not interfere with daily activities), followed by increasing severity of dementia due to AD. Early detection and prediction models for the transition of MCI to AD/ADRD are needed, and efforts have been made to build predictions of MCI conversion to AD/ADRD. However, most existing studies developing such prediction models did not consider the competing risks of death, which may result in biased risk estimates. In this study, we aim to develop a prediction model for AD/ADRD among patients with MCI considering the competing risks of death using a semi-competing risk approach.

Harnessing the potential of machine learning and artificial intelligence for dementia research

Progress in dementia research has been limited, with substantial gaps in our knowledge of targets for prevention, mechanisms for disease progression, and disease-modifying treatments. The growing availability of multimodal data sets opens possibilities for the application of machine learning and artificial intelligence (AI) to help answer key questions in the field. We provide an overview of the state of the science, highlighting current challenges and opportunities for utilisation of AI approaches to move the field forward in the areas of genetics, experimental medicine, drug discovery and trials optimisation, imaging, and prevention. Machine learning methods can enhance results of genetic studies, help determine biological effects and facilitate the identification of drug targets based on genetic and transcriptomic information. The use of unsupervised learning for understanding disease mechanisms for drug discovery is promising, while analysis of multimodal data sets to characterise and quantify disease severity and subtype are also beginning to contribute to optimisation of clinical trial recruitment. Data-driven experimental medicine is needed to analyse data across modalities and develop novel algorithms to translate insights from animal models to human disease biology. AI methods in neuroimaging outperform traditional approaches for diagnostic classification, and although challenges around validation and translation remain, there is optimism for their meaningful integration to clinical practice in the near future. AI-based models can also clarify our understanding of the causality and commonality of dementia risk factors, informing and improving risk prediction models along with the development of preventative interventions. The complexity and heterogeneity of dementia requires an alternative approach beyond traditional design and analytical approaches. Although not yet widely used in dementia research, machine learning and AI have the potential to unlock current challenges and advance precision dementia medicine.

Inter-Hospital Advanced and Mild Alzheimer's Disease Classification Based on Electroencephalogram Measurements via Classical Machine Learning Algorithms

BACKGROUND

In pursuit of diagnostic tools capable of targeting distinct stages of Alzheimer's disease (AD), this study explores the potential of electroencephalography (EEG) combined with machine learning (ML) algorithms to identify patients with mild or moderate AD (ADM) and advanced AD (ADA).

OBJECTIVE

This study aims to assess the classification accuracy of six classical ML algorithms using a dataset of 668 patients from multiple hospitals.

METHODS

The dataset comprised measurements obtained from 668 patients, distributed among control, ADM, and ADA groups, collected from five distinct hospitals between 2011 and 2022. For classification purposes, six classical ML algorithms were employed: support vector machine, Bayesian linear discriminant analysis, decision tree, Gaussian Naïve Bayes, K-nearest neighbor and random forest.

RESULTS

The RF algorithm exhibited outstanding performance, achieving a remarkable balanced accuracy of 93.55% for ADA classification and 93.25% for ADM classification. The consistent reliability in distinguishing ADA and ADM patients underscores the potential of the EEG-based approach for AD diagnosis.

CONCLUSIONS

By leveraging a dataset sourced from multiple hospitals and encompassing a substantial patient cohort, coupled with the straightforwardness of the implemented models, it is feasible to attain notably robust results in AD classification.