scholarly journals Advances in Deep Neuropathological Phenotyping of Alzheimer Disease: Past, Present, and Future

2022 ◽  
Author(s):  
Mustafa N Shakir ◽  
Brittany N Dugger
Keyword(s):  
Machine Learning ◽  
Alzheimer Disease ◽  
Neurodegenerative Disorder ◽  
Lewy Body Disease ◽  
Machine Learning Algorithms ◽  
Brain Diseases ◽  
Disease Heterogeneity ◽  
Technological Advances ◽  
Alois Alzheimer

Abstract Alzheimer disease (AD) is a neurodegenerative disorder characterized pathologically by the presence of neurofibrillary tangles and amyloid beta (Aβ) plaques in the brain. The disease was first described in 1906 by Alois Alzheimer, and since then, there have been many advancements in technologies that have aided in unlocking the secrets of this devastating disease. Such advancements include improving microscopy and staining techniques, refining diagnostic criteria for the disease, and increased appreciation for disease heterogeneity both in neuroanatomic location of abnormalities as well as overlap with other brain diseases; for example, Lewy body disease and vascular dementia. Despite numerous advancements, there is still much to achieve as there is not a cure for AD and postmortem histological analyses is still the gold standard for appreciating AD neuropathologic changes. Recent technological advances such as in-vivo biomarkers and machine learning algorithms permit great strides in disease understanding, and pave the way for potential new therapies and precision medicine approaches. Here, we review the history of human AD neuropathology research to include the notable advancements in understanding common co-pathologies in the setting of AD, and microscopy and staining methods. We also discuss future approaches with a specific focus on deep phenotyping using machine learning.

Machine Learning Approaches in Parkinson’s Disease

2021 ◽  
Vol 28 ◽  
Author(s):  
Annamaria Landolfi ◽  
Carlo Ricciardi ◽  
Leandro Donisi ◽  
Giuseppe Cesarelli ◽  
Jacopo Troisi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Learning Algorithms ◽  
Disease Diagnosis ◽  
Machine Learning Algorithms ◽  
Clinical Aspects ◽  
Learning Approaches

Background:: Parkinson’s disease is the second most frequent neurodegenerative disorder. Its diagnosis is challenging and mainly relies on clinical aspects. At present, no biomarker is available to obtain a diagnosis of certainty in vivo. Objective:: The present review aims at describing machine learning algorithms as they have been variably applied to different aspects of Parkinson’s disease diagnosis and characterization. Methods:: A systematic search was conducted on PubMed in December 2019, resulting in 230 publications obtained with the following search query: “Machine Learning” “AND” “Parkinson Disease”. Results:: the obtained publications were divided into 6 categories, based on different application fields: “Gait Analysis - Motor Evaluation”, “Upper Limb Motor and Tremor Evaluation”, “Handwriting and typing evaluation”, “Speech and Phonation evaluation”, “Neuroimaging and Nuclear Medicine evaluation”, “Metabolomics application”, after excluding the papers of general topic. As a result, a total of 166 articles were analyzed, after elimination of papers written in languages other than English or not directly related to the selected topics. Conclusion:: Machine learning algorithms are computer-based statistical approaches which can be trained and are able to find common patterns from big amounts of data. The machine learning approaches can help clinicians in classifying patients according to several variables at the same time.

scholarly journals Brain tumor diagnostic model and dietary effect based on extracellular vesicle microbiome data in serum

2020 ◽  
Vol 52 (9) ◽  
pp. 1602-1613
Author(s):  
Jinho Yang ◽  
Hyo Eun Moon ◽  
Hyung Woo Park ◽  
Andrea McDowell ◽  
Tae-Seop Shin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Brown Rice ◽  
Machine Learning Algorithms ◽  
Metagenomic Data ◽  
Diagnostic Model ◽  
Tissue Samples ◽  
In Vivo Models ◽  
Linear Discriminant ◽  
Difficult Condition

Abstract The human microbiome has been recently associated with human health and disease. Brain tumors (BTs) are a particularly difficult condition to directly link to the microbiome, as microorganisms cannot generally cross the blood–brain barrier (BBB). However, some nanosized extracellular vesicles (EVs) released from microorganisms can cross the BBB and enter the brain. Therefore, we conducted metagenomic analysis of microbial EVs in both serum (152 BT patients and 198 healthy controls (HC)) and brain tissue (5 BT patients and 5 HC) samples based on the V3–V4 regions of 16S rDNA. We then developed diagnostic models through logistic regression and machine learning algorithms using serum EV metagenomic data to assess the ability of various dietary supplements to reduce BT risk in vivo. Models incorporating the stepwise method and the linear discriminant analysis effect size (LEfSe) method yielded 12 and 29 significant genera as potential biomarkers, respectively. Models using the selected biomarkers yielded areas under the curves (AUCs) >0.93, and the model using machine learning resulted in an AUC of 0.99. In addition, Dialister and [Eubacterium] rectale were significantly lower in both blood and tissue samples of BT patients than in those of HCs. In vivo tests showed that BT risk was decreased through the addition of sorghum, brown rice oil, and garlic but conversely increased by the addition of bellflower and pear. In conclusion, serum EV metagenomics shows promise as a rich data source for highly accurate detection of BT risk, and several foods have potential for mitigating BT risk.

scholarly journals Machine Learning Prediction of Parkinson's Disease Onset and Subtype Using Germline Variants

2021 ◽  
Author(s):  
Saya R Dennis ◽  
Tanya Simuni ◽  
Yuan Luo
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Disease Onset ◽  
The United States ◽  
Machine Learning Algorithms ◽  
Progression Rate ◽  
High Importance ◽  
Germline Variants

Parkinson's Disease is the second most common neurodegenerative disorder in the United States, and is characterized by a largely irreversible worsening of motor and non-motor symptoms as the disease progresses. A prominent characteristic of the disease is its high heterogeneity in manifestation as well as the progression rate. For sporadic Parkinson's Disease, which comprises ~90% of all diagnoses, the relationship between the patient genome and disease onset or progression subtype remains largely elusive. Machine learning algorithms are increasingly adopted to study the genomics of diseases due to their ability to capture patterns within the vast feature space of the human genome that might be contributing to the phenotype of interest. In our study, we develop two machine learning models that predict the onset as well as the progression subtype of Parkinson's Disease based on subjects' germline mutations. Our best models achieved an ROC of 0.77 and 0.61 for disease onset and subtype prediction, respectively. To the best of our knowledge, our models present state-of-the-art prediction performances of PD onset and subtype solely based on the subjects' germline variants. The genes with high importance in our best-performing models were enriched for several canonical pathways related to signaling, immune system, and protein modifications, all of which have been previously associated with PD symptoms or pathogenesis. These high-importance gene sets provide us with promising candidate genes for future biomedical and clinical research.

scholarly journals Covalent Protein Painting Reveals Structural Changes in the Proteome in Alzheimer Disease

2020 ◽  
Author(s):  
Casimir Bamberger ◽  
Sandra Pankow ◽  
Salvador Martínez-Bartolomé ◽  
Michelle Ma ◽  
Jolene Diedrich ◽  
...  
Keyword(s):  
Alzheimer Disease ◽  
Chemical Modification ◽  
Succinate Dehydrogenase ◽  
Structural Changes ◽  
Amyloid Β ◽  
Lewy Body Disease ◽  
Structural Proteomics ◽  
Amyloid Β Peptide ◽  
Lysine Residues

AbstractThe 3D structures of aberrant protein folds have been visualized in exquisite detail, yet no method has been able to quantitatively measure protein misfolding across a proteome. Here, we present Covalent Protein Painting (CPP), a mass spectrometry-based structural proteomics approach to quantify the accessibility of lysine ε-amines for chemical modification at the surface of natively folded proteins. We used CPP to survey 2,645 lysine residues in the proteome of HEK293T cells in vivo and found that mild heat shock increased rather than decreased lysine accessibility for chemical modification. CPP was able to differentiate patients with Alzheimer disease (AD) or Lewy body disease (LBD) or both from controls based on relative accessibility of lysine residues K147, K137, and K28 in Tubulin-β, Succinate dehydrogenase, and amyloid-β peptide, respectively. The alterations of Tubulin-β and Succinate dehydrogenase hint to broader perturbations of the proteome in AD beyond amyloid-β and hyper-phosphorylated tau.

Prediction Models for Healthcare Using Machine Learning

2021 ◽  
pp. 70-91
Author(s):  
Ayushe Gangal ◽  
Peeyush Kumar ◽  
Sunita Kumari ◽  
Anu Saini
Keyword(s):  
Machine Learning ◽  
Prediction Models ◽  
Heart Diseases ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Brain Diseases ◽  
Health Issues ◽  
Industry Study ◽  
Learning Techniques

Healthcare is always a sensitive issue for all of us, and it will always remain. Predicting various types of health issues in advance can lead us to a better life. Various types of health problems are there like cancer, heart diseases, diabetes, arthritis, pneumonia, lungs disease, liver disease, and brain disease, which all are at high risk. To reduce the risk of health issues, some suitable models are needed for prediction. Thus, it became as a motivational factor for the authors to survey the existing literature on this topic thoroughly and have consequently to identify suitable machine learning techniques so that improvement can be possible while selecting a prediction model. In this chapter, concept of survey is used to provide the prediction models for healthcare issues along with the challenges associated with each model. This chapter will broadly cover the following: machine learning algorithms used in health industry, study various prediction models for Cancer, Heart diseases, Diabetes and Brain diseases, comparative study of various machine learning algorithms used for prediction.

scholarly journals TSPO PET Imaging: From Microglial Activation to Peripheral Sterile Inflammatory Diseases?

2017 ◽  
Vol 2017 ◽  
pp. 1-17 ◽  
Author(s):  
Bérenger Largeau ◽  
Anne-Claire Dupont ◽  
Denis Guilloteau ◽  
Maria-João Santiago-Ribeiro ◽  
Nicolas Arlicot
Keyword(s):  
Pet Imaging ◽  
Inflammatory Diseases ◽  
Protein A ◽  
Translocator Protein ◽  
Brain Diseases ◽  
Disease Heterogeneity ◽  
Peripheral Tissues ◽  
Positron Emission ◽  
Potential Biomarker

Peripheral sterile inflammatory diseases (PSIDs) are a heterogeneous group of disorders that gathers several chronic insults involving the cardiovascular, respiratory, gastrointestinal, or musculoskeletal system and wherein inflammation is the cornerstone of the pathophysiology. In PSID, timely characterization and localization of inflammatoryfociare crucial for an adequate care for patients. In brain diseases,in vivopositron emission tomography (PET) exploration of inflammation has matured over the last 20 years, through the development of radiopharmaceuticals targeting the translocator protein-18 kDa (TSPO) as molecular biomarkers of activated microglia. Recently, TSPO has been introduced as a possible molecular target for PSIDs PET imaging, making this protein a potential biomarker to address disease heterogeneity, to assist in patient stratification, and to contribute to predicting treatment response. In this review, we summarized the major research advances recently made in the field of TSPO PET imaging in PSIDs. Promising preliminary results have been reported in bowel, cardiovascular, and rheumatic inflammatory diseases, consolidated by preclinical studies. Limitations of TSPO PET imaging in PSIDs, regarding both its large expression in healthy peripheral tissues, unlike in central nervous system, and the production of peripheral radiolabeled metabolites, are also discussed, regarding their possible consequences on TSPO PET signal’s quantification.

scholarly journals Neuro-Based Prognosticative Analytics for Parkinson Disease using Random Forest Approach

2020 ◽  
Vol 9 (11) ◽  
pp. 11-15
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Parkinson Disease ◽  
Neurodegenerative Disorder ◽  
Learning Algorithms ◽  
Machine Learning Algorithms ◽  
Single Test ◽  
Specificity And Sensitivity ◽  
The World ◽  
The Given

Parkinson’s malady is the most current neurodegenerative disorder poignant quite ten million folks across the world. There's no single test at which may be administered for diagnosis Parkinson’s malady. Our aim is to analyze machine learning based mostly techniques for Parkinson malady identification in patients. Our machine learning-based technique is employed to accurately predict the malady by speech and handwriting patterns of humans and by predicting leads to the shape of best accuracy and in addition compare the performance of assorted machine learning algorithms from the given hospital dataset with analysis and classification report and additionally determine the result and prove against with best accuracy and exactness, Recall ,F1 Score specificity and sensitivity.

A Comparative Analysis to Visualize the Behavior of Different Machine Learning Algorithms for Normalized and Un-Normalized Data in Predicting Alzheimer’s Disease

2019 ◽  
Vol 16 (9) ◽  
pp. 3840-3848
Author(s):  
Neeraj Kumar ◽  
Jatinder Manhas ◽  
Vinod Sharma
Keyword(s):  
Machine Learning ◽  
Naive Bayes ◽  
Neurodegenerative Disorder ◽  
Learning Algorithms ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Linear Discriminant ◽  
Age Related

Advancement in technology has helped people to live a long and better life. But the increased life expectancy has also elevated the risk of age related disorders, especially the neurodegenerative disorders. Alzheimer’s is one such neurodegenerative disorder, which is also the leading contributor towards dementia in elderly people. Despite of extensive research in this field, scientists have failed to find a cure for the disease till date. This makes early diagnosis of Alzheimer’s very crucial so as to delay its progression and improve the condition of the patient. Various techniques are being employed for diagnosing Alzheimer’s which include neuropsychological tests, medical imaging, blood based biomarkers, etc. Apart from this, various machine learning algorithms have been employed so far to diagnose Alzheimer’s in its early stages. In the current research, authors compared the performance of various machine learning techniques i.e., Linear Discriminant Analysis (LDA), K-Nearest Neighbour (KNN), Naïve Bayes (NB), Support Vector Machines (SVM), Decision Trees (DT), Random Forests (RF) and Multi Layer Perceptron (MLP) on Alzheimer’s dataset. This paper experimentally demonstrated that normalization exhibits a predominant role in enhancing the efficiency of some machine learning algorithms. Therefore it becomes imperative to choose the algorithms as per the available data. In this paper, the efficiency of the given machine learning methods was compared in terms of accuracy and f1-score. Naïve Bayes gave a better overall performance for both accuracy and f1-score and it also remained unaffected with the normalization of data along with LDA, DT and RF. Whereas KNN, SVM and MLP showed a drastic (17% to 86%) improvement in the performance when they are given normalized data as compared to un-normalized data from Alzheimer’s dataset.

scholarly journals Diagnosis of Parkinson’s Disorder through Speech Data using Machine Learning Algorithms

2020 ◽  
Vol 9 (3) ◽  
pp. 69-72
Keyword(s):  
Machine Learning ◽  
Parkinson’S Disease ◽  
Health Care ◽  
Decision Making ◽  
Parkinson's Disease ◽  
Neurodegenerative Disorder ◽  
Machine Learning Algorithms ◽  
Speech Data ◽  
Computer Aided ◽  
Comprehensive Comparison

Parkinson's disease is a neurodegenerative disorder that affects millions of people around the globe. Detecting Parkinson's disease at an earlier stage could help to better diagnose the disease. Machine learning provides potentially large opportunities for computer-aided identification and diagnosis that could minimize unavoidable health care errors and inherent clinical uncertainty, provide guidance, and improve decision-making. In this paper, we explore the feature extraction and prediction algorithms used to predict Parkinson's disease and provide a comprehensive comparison of these algorithms

Sign in / Sign up

Export Citation Format

Share Document