Accuracy of deep learning model-assisted amyloid positron emission tomography scan in predicting Alzheimer's disease: A Systematic Review and meta-analysis

Shirbandi, Kiarash; Khalafi, Mohammad; Mirza-Aghazadeh-Attari, Mohammad; Tahmasbi, Marziyeh; Shahvandi, Hassan Kiani; Javanmardi, Pouya; Rahim, Fakher

doi:10.1016/j.imu.2021.100710

Cited by 16 publications

(9 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although it is a topic beyond the scope of this paper, quantitative analysis is likely to be complemented by AI-driven analysis techniques in the future. Indeed, various deep learning-based strategies currently exist for amyloid status prediction [ 212 , 213 ] and SUVr quantification [ 214 ], and it will be of great interest to see how techniques such as these develop and contribute to the field.…”

Section: Future Directionsmentioning

confidence: 99%

Quantification of amyloid PET for future clinical use: a state-of-the-art review

Pemberton

Collij

Heeman

et al. 2022

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Amyloid-β (Aβ) pathology is one of the earliest detectable brain changes in Alzheimer’s disease (AD) pathogenesis. The overall load and spatial distribution of brain Aβ can be determined in vivo using positron emission tomography (PET), for which three fluorine-18 labelled radiotracers have been approved for clinical use. In clinical practice, trained readers will categorise scans as either Aβ positive or negative, based on visual inspection. Diagnostic decisions are often based on these reads and patient selection for clinical trials is increasingly guided by amyloid status. However, tracer deposition in the grey matter as a function of amyloid load is an inherently continuous process, which is not sufficiently appreciated through binary cut-offs alone. State-of-the-art methods for amyloid PET quantification can generate tracer-independent measures of Aβ burden. Recent research has shown the ability of these quantitative measures to highlight pathological changes at the earliest stages of the AD continuum and generate more sensitive thresholds, as well as improving diagnostic confidence around established binary cut-offs. With the recent FDA approval of aducanumab and more candidate drugs on the horizon, early identification of amyloid burden using quantitative measures is critical for enrolling appropriate subjects to help establish the optimal window for therapeutic intervention and secondary prevention. In addition, quantitative amyloid measurements are used for treatment response monitoring in clinical trials. In clinical settings, large multi-centre studies have shown that amyloid PET results change both diagnosis and patient management and that quantification can accurately predict rates of cognitive decline. Whether these changes in management reflect an improvement in clinical outcomes is yet to be determined and further validation work is required to establish the utility of quantification for supporting treatment endpoint decisions. In this state-of-the-art review, several tools and measures available for amyloid PET quantification are summarised and discussed. Use of these methods is growing both clinically and in the research domain. Concurrently, there is a duty of care to the wider dementia community to increase visibility and understanding of these methods.

show abstract

Section: Future Directionsmentioning

confidence: 99%

Quantification of amyloid PET for future clinical use: a state-of-the-art review

Pemberton

Collij

Heeman

et al. 2022

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

show abstract

“…Diseases that can be studied through translational Frontiers in Pharmacology frontiersin.org research include neurodegenerative disorders, such as AD, PD, multiple sclerosis, HD, and ALS, and psychiatric disorders, such as major depressive disorder, bipolar disorder, substance abuse disorder, post-traumatic stress disorder, anxiety disorder, schizophrenia, somatic symptom disorder, autism spectrum disorder, and hyperactive ataxia (Kaswan et al, 2021). There are clinician guides for using neuroscience to guide case framework, understand psychotherapeutic techniques, aid in treatment personalization and outcome prediction, and develop novel mechanistically targeted treatments for disorders (Shirbandi et al, 2021). We extensively added recent and updated key findings and additionally showed the applicability of natural products to improve their appropriate usage in neurological disorders, followed by the incorporation of various clinical studies and patents on phytoconstituents for neuronal diseases.…”

Section: Traditional Holistic Approach For the Management Of Neurolog...mentioning

confidence: 99%

“…Neuroinformatics is the study of the neurological system via the development of databases and tools that aims to design and manage web-accessible databases of experimental and computational data and novel software tools that are necessary for understanding the nervous system in diseased and healthy states ( Pu and Li, 2018 ; Usman et al, 2022 ). Brain imaging using positron emission tomography ( Kaswan et al, 2021 ; Ruiz-Olazar et al, 2021 ), functional magnetic resonance imaging ( Stefanovski et al, 2021 ; Li et al, 2022 ), electroencephalography ( Wojcik et al, 2018 ; Shirbandi et al, 2021 ), magnetoencephalography ( Gorina-Careta et al, 2021 ), and other methods; several electrophysiological recording methods; and clinical neurological data are examples of neuroinformatics ( Sharma et al, 2019 ). In an interesting study, 679 flavonoid-based compounds and their 481 relative targets were screened, and their bioinformatic analysis exhibited multiple pharmacological pathways, especially for neuronal diseases.…”

Section: Traditional Holistic Approach For the Management Of Neurolog...mentioning

confidence: 99%

Natural product-based pharmacological studies for neurological disorders

Puri

Kanojia²,

Sharma³

et al. 2022

Front. Pharmacol.

View full text Add to dashboard Cite

Central nervous system (CNS) disorders and diseases are expected to rise sharply in the coming years, partly because of the world’s aging population. Medicines for the treatment of the CNS have not been successfully made. Inadequate knowledge about the brain, pharmacokinetic and dynamic errors in preclinical studies, challenges with clinical trial design, complexity and variety of human brain illnesses, and variations in species are some potential scenarios. Neurodegenerative diseases (NDDs) are multifaceted and lack identifiable etiological components, and the drugs developed to treat them did not meet the requirements of those who anticipated treatments. Therefore, there is a great demand for safe and effective natural therapeutic adjuvants. For the treatment of NDDs and other memory-related problems, many herbal and natural items have been used in the Ayurvedic medical system. Anxiety, depression, Parkinson’s, and Alzheimer’s diseases (AD), as well as a plethora of other neuropsychiatric disorders, may benefit from the use of plant and food-derived chemicals that have antidepressant or antiepileptic properties. We have summarized the present level of knowledge about natural products based on topological evidence, bioinformatics analysis, and translational research in this review. We have also highlighted some clinical research or investigation that will help us select natural products for the treatment of neurological conditions. In the present review, we have explored the potential efficacy of phytoconstituents against neurological diseases. Various evidence-based studies and extensive recent investigations have been included, which will help pharmacologists reduce the progression of neuronal disease.

show abstract

“…AI and ML have been used to study metabolic pathways, drug-drug interaction and to predict significant markers in various diseases using multi-omics data [ 19 , 20 , 21 ]. Most of the reported studies in AD use neuroimaging data such as PET imaging and have demonstrated DL to be more accurate than all the platforms tested [ 22 , 23 ]. Systems biology techniques to include epigenetics, genomics, transcriptomics and metabolomics combined with both clinical and imaging data have been used to perform classification, biomarker identification, disease subtyping, disease progression prediction and drug repurposing [ 24 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence and Circulating Cell-Free DNA Methylation Profiling: Mechanism and Detection of Alzheimer’s Disease

Bahado‐Singh

Radhakrishna

Gordevičius³

et al. 2022

Cells

View full text Add to dashboard Cite

Background: Despite extensive efforts, significant gaps remain in our understanding of Alzheimer’s disease (AD) pathophysiology. Novel approaches using circulating cell-free DNA (cfDNA) have the potential to revolutionize our understanding of neurodegenerative disorders. Methods: We performed DNA methylation profiling of cfDNA from AD patients and compared them to cognitively normal controls. Six Artificial Intelligence (AI) platforms were utilized for the diagnosis of AD while enrichment analysis was used to elucidate the pathogenesis of AD. Results: A total of 3684 CpGs were significantly (adj. p-value < 0.05) differentially methylated in AD versus controls. All six AI algorithms achieved high predictive accuracy (AUC = 0.949–0.998) in an independent test group. As an example, Deep Learning (DL) achieved an AUC (95% CI) = 0.99 (0.95–1.0), with 94.5% sensitivity and specificity. Conclusion: We describe numerous epigenetically altered genes which were previously reported to be differentially expressed in the brain of AD sufferers. Genes identified by AI to be the best predictors of AD were either known to be expressed in the brain or have been previously linked to AD. We highlight enrichment in the Calcium signaling pathway, Glutamatergic synapse, Hedgehog signaling pathway, Axon guidance and Olfactory transduction in AD sufferers. To the best of our knowledge, this is the first reported genome-wide DNA methylation study using cfDNA to detect AD.

show abstract

Accuracy of deep learning model-assisted amyloid positron emission tomography scan in predicting Alzheimer's disease: A Systematic Review and meta-analysis

Cited by 16 publications

References 48 publications

Quantification of amyloid PET for future clinical use: a state-of-the-art review

Quantification of amyloid PET for future clinical use: a state-of-the-art review

Natural product-based pharmacological studies for neurological disorders

Artificial Intelligence and Circulating Cell-Free DNA Methylation Profiling: Mechanism and Detection of Alzheimer’s Disease

Contact Info

Product

Resources

About