Prediction of Autopsy Verified Neuropathological Change of Alzheimer's Disease Using Machine Learning and MRI

Exploring the power of MRI and clinical measures in predicting AD neuropathology

Predicting Alzheimer's disease (AD) pathology prior to clinical diagnosis is important for identifying individuals at high risk of developing AD dementia. However, there remains a gap in leveraging MRI and clinical data to predict AD pathology. This study examines a novel machine learning approach that integrates the combined vascular (white matter hyperintensities, WMHs) and structural brain changes (gray matter, GM) with clinical factors (cognitive scores) to predict post-mortem neuropathology. Participants from the Alzheimer's Disease Neuroimaging Initiative dataset (ADNI) and National Alzheimer's Coordinating Center (NACC) with both post-mortem neuropathology data and antemortem MRI and clinical data were included. Machine learning models were applied towards feature selection of the top seven MRI, clinical, and demographic data to identify the best performing set of variables that could predict postmortem neuropathology outcomes (i.e., neurofibrillary tangles, neuritic plaques, diffuse plaques, senile/amyloid plaques, and amyloid angiopathy). The best-performing neuropathology predictors from ADNI were then validated in NACC to compare results and ensure that the feature selection process did not lead to overfitting. In ADNI, the best-performing model included total and temporal lobe WMHs and achieved r = 0.87(RMSE = 0.62) during cross-validation for neuritic plaques. Overall, post-mortem neuropathology outcomes were predicted up to 14 years before death with high accuracies (~ 90%). Similar results were observed in the NACC dataset. These findings highlight that MRI features are critical to successfully predict AD-related pathology years in advance.

Wnt/β-catenin and notch signaling pathways in cardiovascular disease: Mechanisms and therapeutics approaches

Wnt and Notch signaling pathways play crucial roles in the development and homeostasis of the cardiovascular system. These pathways regulate important cellular processes in cardiomyocytes, endothelial cells, and smooth muscle cells, which are the key cell types involved in the structure and function of the heart and vasculature. During embryonic development, Wnt and Notch signaling coordinate cell fate specification, proliferation, differentiation, and morphogenesis of the heart and blood vessels. In the adult cardiovascular system, these pathways continue to maintain tissue homeostasis and arrange adaptive responses to various physiological and pathological stimuli. Dysregulation of Wnt and Notch signaling has been involved in the pathogenesis of numerous cardiovascular diseases, including atherosclerosis, hypertension, myocardial infarction, and heart failure. Abnormal activation or suppression of these pathways in specific cell types can contribute to endothelial dysfunction, vascular remodeling, cardiomyocyte hypertrophy, impaired cardiac contractility and dead. Understanding the complex interplay between Wnt and Notch signaling in the cardiovascular system has led to the investigation of these pathways as potential therapeutic targets in clinical trials. In conclusion, this review summarizes the current knowledge on the roles of Wnt and Notch signaling in the development and homeostasis of cardiomyocytes, endothelial cells, and smooth muscle cells. It further discusses the dysregulation of these pathways in the context of major cardiovascular diseases and the ongoing clinical investigations targeting Wnt and Notch signaling for therapeutic intervention.

MRI-based mild cognitive impairment and Alzheimer's disease classification using an algorithm of combination of variational autoencoder and other machine learning classifiers

Background

Correctly diagnosing mild cognitive impairment (MCI) and Alzheimer's disease (AD) is important for patient selection in drug discovery. Research outcomes on stage diagnosis using neuroimages combined with cerebrospinal fluid and genetic biomarkers are expensive and time-consuming. Only structural magnetic resonance imaging (sMRI) scans from two internationally recognized datasets are employed as input as well as test and independent validation to determine the classification of dementia by the machine learning algorithm.

Objective

We extract the reduced dimensional latent feature vector from the sMRI scans using a variational autoencoder (VAE). The objective is to classify AD, MCI, and control (CN) using MRI and without any other information.

Methods

The extracted feature vectors from MRI scans by VAE are used as input conditions for different advanced machine-learning classifiers. Classification of AD/CN/MCI are conducted using the output of VAE from MRI images and different artificial intelligence/machine learning classifier models in two cohorts.

Results

Using only MRI scans, the primary goal of the study is to test the ability to classify AD from CN and MCI cases. The current study achieved classification accuracies of AD versus CN 75.45% (F1-score = 79.52%), AD versus MCI 81.41% (F1-Score = 87.06%), and autopsy-confirmed AD versus MCI 92.75% (F1-Score = 95.52%) in test sets and AD versus CN 86.16% (F1-score = 92.03%) and AD versus MCI 70.03% (F1-Score = 82.1%) in validation data set.

Conclusions

By overcoming the data leakage problem, the autopsy-confirmed machine learning classification model is tested in two independent cohorts. External validation by an independent cohort improved the quality and novelty of the classification algorithm.

Long non-coding RNAs H19 and NKILA are associated with the risk of death and lacunar stroke in the elderly population

INTRODUCTION

Differential expression of long non-coding RNAs (lncRNAs) is a hallmark of cardiovascular aging, cerebrovascular diseases, and neurodegenerative disorders. This research article investigates the association between a panel of lncRNAs and the risk of death and ischemic stroke in a cohort of non-institutionalized elderly subjects.

METHOD

A total of 361 healthy individuals aged 75 years old, prospectively recruited in the Vienna Transdanube Aging (VITA) cohort, were included. Expression of lncRNAs at baseline was assessed using quantitative polymerase chain reaction PCR with pre-amplification reaction, using 18S for normalization. The primary endpoint was all-cause mortality; the secondary endpoint was the incidence of new ischemic brain lesions. Death was assessed over a 14-year follow-up, and ischemic brain lesions were evaluated by magnetic resonance imaging (MRI) over a 90-month follow-up. Ischemic brain lesions were divided into large brain infarcts (Ø≥ 1.5 cm) or lacunes (Ø< 1.5 cm) RESULTS: The primary endpoint occurred in 53.5 % of the study population. The incidence of the secondary endpoint was 16 %, with a 3.3 % being large brain infarcts, and a 12.7 % lacunes. After adjustment for potential confounders, the lncRNA H19 predicted the incidence of the primary endpoint (HR 1.194, 95 % C.I. 1.012-1.409, p = 0.036), whereas the lncRNA NKILA was associated with lacunar stroke (HR 0.571, 95 % C.I. 0.375-0.868, p = 0.006).

CONCLUSION

In a prospective cohort of non-institutionalized elderly subjects, high levels of lncRNA H19 are associated with a higher risk of death, while low levels of lncRNA NKILA predict an increased risk of lacunar stroke.

Predicting early Alzheimer's with blood biomarkers and clinical features

Alzheimer's disease (AD) is an incurable neurodegenerative disorder that leads to dementia. This study employs explainable machine learning models to detect dementia cases using blood gene expression, single nucleotide polymorphisms (SNPs), and clinical data from Alzheimer's Disease Neuroimaging Initiative (ADNI). Analyzing 623 ADNI participants, we found that the Support Vector Machine classifier with Mutual Information (MI) feature selection, trained on all three data modalities, achieved exceptional performance (accuracy = 0.95, AUC = 0.94). When using gene expression and SNP data separately, we achieved very good performance (AUC = 0.65, AUC = 0.63, respectively). Using SHapley Additive exPlanations (SHAP), we identified significant features, potentially serving as AD biomarkers. Notably, genetic-based biomarkers linked to axon myelination and synaptic vesicle membrane formation could aid early AD detection. In summary, this genetic-based biomarker approach, integrating machine learning and SHAP, shows promise for precise AD diagnosis, biomarker discovery, and offers novel insights for understanding and treating the disease. This approach addresses the challenges of accurate AD diagnosis, which is crucial given the complexities associated with the disease and the need for non-invasive diagnostic methods.

Variability in Alzheimer's disease mortality from European vital statistics, 2012-2020

OBJECTIVE

Data regarding the trends in Alzheimer's disease (AD) mortality in the modern European Union (EU-27) member states are lacking. We assess the sex- and age-specific trends in AD mortality in the EU-27 member states between years 2012 and 2020.

METHODS

Data on cause-specific deaths and population numbers by sex for each country of the EU-27 were retrieved through publicly available European Statistical Office (EUROSTAT) dataset from 2012 to 2020. AD-related deaths were ascertained when the ICD-10 code G30 was listed as the primary cause of death in the medical death certificate. To calculate annual trends, we assessed the average annual percent change (AAPC) with relative 95% confidence intervals (CIs) using Joinpoint regression.

RESULTS

During the study period, 751,493 deaths (1.7%, 233,271 males and 518,222 females) occurred in the EU-27 because of AD. Trends in the proportion of AD-related deaths per 1000 total deaths slightly increased from 16.8% to 17.5% (p for trend <0.001). The age-adjusted mortality rate was higher in women over the entire study period. Joinpoint regression analysis revealed a stagnation in age-adjusted AD-related mortality from 2012 to 2020 among EU-27 Member States (AAMR: -0.1% [95% CI: -1.8-1.79], p = 0.94). Stratification by Country showed relevant regional disparities, especially in the Northern and Eastern EU-27 member states.

CONCLUSIONS

Over the last decade, the age-adjusted AD-related mortality rate has plateaued in EU-27. Important disparities still exist between Western and Eastern European countries.

Late-Life High Blood Pressure and Enlarged Perivascular Spaces in the Putaminal Regions of Community-Dwelling Japanese Older Persons

BACKGROUND

Enlarged perivascular spaces (EPVS) of the brain may be involved in dementia, such as Alzheimer's disease and cerebral small vessel disease (CSVD). Hypertension has been reported to be a risk factor for dementia and CSVD, but the association between blood pressure (BP) and perivascular spaces is still unclear. The aim of this study was to determine the association between BP and EPVS volumes and to examine the interactions of relevant factors.

METHODS

A total of 9296 community-dwelling subjects aged ≥65 years participated in a brain magnetic resonance imaging and health status screening examination. Perivascular volume was measured using a software package based on deep learning that was developed in-house. The associations between BP and EPVS volumes were examined by analysis of covariance and multiple regression analysis.

RESULTS

Mean EPVS volumes increased significantly with rising systolic and diastolic BP levels (P for trend = .003, P for trend<.001, respectively). In addition, mean EPVS volumes increased significantly for every 1-mmHg-increment in systolic and diastolic BPs (both P values <.001). These significant associations were still observed in the sensitivity analysis after excluding subjects with dementia.

CONCLUSIONS

The present data suggest that higher systolic and diastolic BP levels are associated with greater EPVS volumes in cognitively normal older people.

Prediction of neuropathologic lesions from clinical data

INTRODUCTION

Post-mortem analysis provides definitive diagnoses of neurodegenerative diseases; however, only a few can be diagnosed during life.

METHODS

This study employed statistical tools and machine learning to predict 17 neuropathologic lesions from a cohort of 6518 individuals using 381 clinical features (Table S1). The multisite data allowed validation of the model's robustness by splitting train/test sets by clinical sites. A similar study was performed for predicting Alzheimer's disease (AD) neuropathologic change without specific comorbidities.

RESULTS

Prediction results show high performance for certain lesions that match or exceed that of research annotation. Neurodegenerative comorbidities in addition to AD neuropathologic change resulted in compounded, but disproportionate, effects across cognitive domains as the comorbidity number increased.

DISCUSSION

Certain clinical features could be strongly associated with multiple neurodegenerative diseases, others were lesion-specific, and some were divergent between lesions. Our approach could benefit clinical research, and genetic and biomarker research by enriching cohorts for desired lesions.

Radiomics for Alzheimer's Disease: Fundamental Principles and Clinical Applications

Alzheimer's disease is a neurodegenerative disease with a huge impact on people's quality of life, life expectancy, and morbidity. The ongoing prevalence of the disease, in conjunction with an increased financial burden to healthcare services, necessitates the development of new technologies to be employed in this field. Hence, advanced computational methods have been developed to facilitate early and accurate diagnosis of the disease and improve all health outcomes. Artificial intelligence is now deeply involved in the fight against this disease, with many clinical applications in the field of medical imaging. Deep learning approaches have been tested for use in this domain, while radiomics, an emerging quantitative method, are already being evaluated to be used in various medical imaging modalities. This chapter aims to provide an insight into the fundamental principles behind radiomics, discuss the most common techniques alongside their strengths and weaknesses, and suggest ways forward for future research standardization and reproducibility.

Noncoding RNome as Enabling Biomarkers for Precision Health

Noncoding RNAs (ncRNAs), in the form of structural, catalytic or regulatory RNAs, have emerged to be critical effectors of many biological processes. With the advent of new technologies, we have begun to appreciate how intracellular and circulatory ncRNAs elegantly choreograph the regulation of gene expression and protein function(s) in the cell. Armed with this knowledge, the clinical utility of ncRNAs as biomarkers has been recently tested in a wide range of human diseases. In this review, we examine how critical factors govern the success of interrogating ncRNA biomarker expression in liquid biopsies and tissues to enhance our current clinical management of human diseases, particularly in the context of cancer. We also discuss strategies to overcome key challenges that preclude ncRNAs from becoming standard-of-care clinical biomarkers, including sample pre-analytics standardization, data cross-validation with closer attention to discordant findings, as well as correlation with clinical outcomes. Although harnessing multi-modal information from disease-associated noncoding RNome (ncRNome) in biofluids or in tissues using artificial intelligence or machine learning is at the nascent stage, it will undoubtedly fuel the community adoption of precision population health.

Alzheimer's disease: a scoping review of biomarker research and development for effective disease diagnosis

INTRODUCTION

Alzheimer's disease (AD) is regarded as the foremost reason for neurodegeneration that prominently affects the geriatric population. Characterized by extracellular accumulation of amyloid-beta (Aβ), intracellular aggregation of hyperphosphorylated tau (p-tau), and neuronal degeneration that causes impairment of memory and cognition. Amyloid/tau/neurodegeneration (ATN) classification is utilized for research purposes and involves amyloid, tau, and neuronal injury staging through MRI, PET scanning, and CSF protein concentration estimations. CSF sampling is invasive, and MRI and PET scanning requires sophisticated radiological facilities which limit its widespread diagnostic use. ATN classification lacks effectiveness in preclinical AD.

AREAS COVERED

This publication intends to collate and review the existing biomarker profile and the current research and development of a new arsenal of biomarkers for AD pathology from different biological samples, microRNA (miRNA), proteomics, metabolomics, artificial intelligence, and machine learning for AD screening, diagnosis, prognosis, and monitoring of AD treatments.

EXPERT OPINION

It is an accepted observation that AD-related pathological changes occur over a long period of time before the first symptoms are observed providing ample opportunity for detection of biological alterations in various biological samples that can aid in early diagnosis and modify treatment outcomes.

Neural Network Training with Highly Incomplete Medical Datasets

Neural network training and validation rely on the availability of large high-quality datasets. However, in many cases only incomplete datasets are available, particularly in health care applications, where each patient typically undergoes different clinical procedures or can drop out of a study. Since the data to train the neural networks need to be complete, most studies discard the incomplete datapoints, which reduces the size of the training data, or impute the missing features, which can lead to artefacts. Alas, both approaches are inadequate when a large portion of the data is missing. Here, we introduce GapNet, an alternative deep-learning training approach that can use highly incomplete datasets without overfitting or introducing artefacts. First, the dataset is split into subsets of samples containing all values for a certain cluster of features. Then, these subsets are used to train individual neural networks. Finally, this ensemble of neural networks is combined into a single neural network whose training is fine-tuned using all complete datapoints. Using two highly incomplete real-world medical datasets, we show that GapNet improves the identification of patients with underlying Alzheimer’s disease pathology and of patients at risk of hospitalization due to Covid-19. Compared to commonly used imputation methods, this improvement suggests that GapNet can become a general tool to handle incomplete medical datasets.

A Review of Artificial Intelligence, Big Data, and Blockchain Technology Applications in Medicine and Global Health

Artificial intelligence (AI) programs are applied to methods such as diagnostic procedures, treatment protocol development, patient monitoring, drug development, personalized medicine in healthcare, and outbreak predictions in global health, as in the case of the current COVID-19 pandemic. Machine learning (ML) is a field of AI that allows computers to learn and improve without being explicitly programmed. ML algorithms can also analyze large amounts of data called Big data through electronic health records for disease prevention and diagnosis. Wearable medical devices are used to continuously monitor an individual’s health status and store it in cloud computing. In the context of a newly published study, the potential benefits of sophisticated data analytics and machine learning are discussed in this review. We have conducted a literature search in all the popular databases such as Web of Science, Scopus, MEDLINE/PubMed and Google Scholar search engines. This paper describes the utilization of concepts underlying ML, big data, blockchain technology and their importance in medicine, healthcare, public health surveillance, case estimations in COVID-19 pandemic and other epidemics. The review also goes through the possible consequences and difficulties for medical practitioners and health technologists in designing futuristic models to improve the quality and well-being of human lives.

Artificial intelligence in neurodegenerative diseases: A review of available tools with a focus on machine learning techniques

Neurodegenerative diseases have shown an increasing incidence in the older population in recent years. A significant amount of research has been conducted to characterize these diseases. Computational methods, and particularly machine learning techniques, are now very useful tools in helping and improving the diagnosis as well as the disease monitoring process. In this paper, we provide an in-depth review on existing computational approaches used in the whole neurodegenerative spectrum, namely for Alzheimer's, Parkinson's, and Huntington's Diseases, Amyotrophic Lateral Sclerosis, and Multiple System Atrophy. We propose a taxonomy of the specific clinical features, and of the existing computational methods. We provide a detailed analysis of the various modalities and decision systems employed for each disease. We identify and present the sleep disorders which are present in various diseases and which represent an important asset for onset detection. We overview the existing data set resources and evaluation metrics. Finally, we identify current remaining open challenges and discuss future perspectives.

Plasma hydrogen sulfide: A biomarker of Alzheimer's disease and related dementias

While heart disease remains a common cause of mortality, cerebrovascular disease also increases with age, and has been implicated in Alzheimer's disease and related dementias (ADRD). We have described hydrogen sulfide (H₂S), a signaling molecule important in vascular homeostasis, as a biomarker of cardiovascular disease. We hypothesize that plasma H₂S and its metabolites also relate to vascular and cognitive dysfunction in ADRD. We used analytical biochemical methods to measure plasma H₂S metabolites and MRI to evaluate indicators of microvascular disease in ADRD. Levels of total H₂S and specific metabolites were increased in ADRD versus controls. Cognition and microvascular disease indices were correlated with H₂S levels. Total plasma sulfide was the strongest indicator of ADRD, and partially drove the relationship between cognitive dysfunction and white matter lesion volume, an indicator of microvascular disease. Our findings show that H₂S is dysregulated in dementia, providing a potential biomarker for diagnosis and intervention.

Machine Learning Applied to Diagnosis of Human Diseases: A Systematic Review

Human healthcare is one of the most important topics for society. It tries to find the correct effective and robust disease detection as soon as possible to patients receipt the appropriate cares. Because this detection is often a difficult task, it becomes necessary medicine field searches support from other fields such as statistics and computer science. These disciplines are facing the challenge of exploring new techniques, going beyond the traditional ones. The large number of techniques that are emerging makes it necessary to provide a comprehensive overview that avoids very particular aspects. To this end, we propose a systematic review dealing with the Machine Learning applied to the diagnosis of human diseases. This review focuses on modern techniques related to the development of Machine Learning applied to diagnosis of human diseases in the medical field, in order to discover interesting patterns, making non-trivial predictions and useful in decision-making. In this way, this work can help researchers to discover and, if necessary, determine the applicability of the machine learning techniques in their particular specialties. We provide some examples of the algorithms used in medicine, analysing some trends that are focused on the goal searched, the algorithm used, and the area of applications. We detail the advantages and disadvantages of each technique to help choose the most appropriate in each real-life situation, as several authors have reported. The authors searched Scopus, Journal Citation Reports (JCR), Google Scholar, and MedLine databases from the last decades (from 1980s approximately) up to the present, with English language restrictions, for studies according to the objectives mentioned above. Based on a protocol for data extraction defined and evaluated by all authors using PRISMA methodology, 141 papers were included in this advanced review.

Automated MRI-Based Deep Learning Model for Detection of Alzheimer’s Disease Process

In the context of neuro-pathological disorders, neuroimaging has been widely accepted as a clinical tool for diagnosing patients with Alzheimer’s disease (AD) and mild cognitive impairment (MCI). The advanced deep learning method, a novel brain imaging technique, was applied in this study to evaluate its contribution to improving the diagnostic accuracy of AD. Three-dimensional convolutional neural networks (3D-CNNs) were applied with magnetic resonance imaging (MRI) to execute binary and ternary disease classification models. The dataset from the Alzheimer’s disease neuroimaging initiative (ADNI) was used to compare the deep learning performances across 3D-CNN, 3D-CNN-support vector machine (SVM) and two-dimensional (2D)-CNN models. The outcomes of accuracy with ternary classification for 2D-CNN, 3D-CNN and 3D-CNN-SVM were [Formula: see text]%, [Formula: see text]% and [Formula: see text]% respectively. The 3D-CNN-SVM yielded a ternary classification accuracy of 93.71%, 96.82% and 96.73% for NC, MCI and AD diagnoses, respectively. Furthermore, 3D-CNN-SVM showed the best performance for binary classification. Our study indicated that ‘NC versus MCI’ showed accuracy, sensitivity and specificity of 98.90%, 98.90% and 98.80%; ‘NC versus AD’ showed accuracy, sensitivity and specificity of 99.10%, 99.80% and 98.40%; and ‘MCI versus AD’ showed accuracy, sensitivity and specificity of 89.40%, 86.70% and 84.00%, respectively. This study clearly demonstrates that 3D-CNN-SVM yields better performance with MRI compared to currently utilized deep learning methods. In addition, 3D-CNN-SVM proved to be efficient without having to manually perform any prior feature extraction and is totally independent of the variability of imaging protocols and scanners. This suggests that it can potentially be exploited by untrained operators and extended to virtual patient imaging data. Furthermore, owing to the safety, noninvasiveness and nonirradiative properties of the MRI modality, 3D-CNN-SMV may serve as an effective screening option for AD in the general population. This study holds value in distinguishing AD and MCI subjects from normal controls and to improve value-based care of patients in clinical practice.

Interpretable classification of Alzheimer's disease pathologies with a convolutional neural network pipeline

Neuropathologists assess vast brain areas to identify diverse and subtly-differentiated morphologies. Standard semi-quantitative scoring approaches, however, are coarse-grained and lack precise neuroanatomic localization. We report a proof-of-concept deep learning pipeline that identifies specific neuropathologies-amyloid plaques and cerebral amyloid angiopathy-in immunohistochemically-stained archival slides. Using automated segmentation of stained objects and a cloud-based interface, we annotate > 70,000 plaque candidates from 43 whole slide images (WSIs) to train and evaluate convolutional neural networks. Networks achieve strong plaque classification on a 10-WSI hold-out set (0.993 and 0.743 areas under the receiver operating characteristic and precision recall curve, respectively). Prediction confidence maps visualize morphology distributions at high resolution. Resulting network-derived amyloid beta (Aβ)-burden scores correlate well with established semi-quantitative scores on a 30-WSI blinded hold-out. Finally, saliency mapping demonstrates that networks learn patterns agreeing with accepted pathologic features. This scalable means to augment a neuropathologist's ability suggests a route to neuropathologic deep phenotyping.