Dementia subtype prediction models constructed by penalized regression methods for multiclass classification using serum microRNA expression data

Asanomi, Yuya; Shigemizu, Daichi; Akiyama, Shintaro; Sakurai, Takashi; Ozaki, Kouichi; Ochiya, Takahiro; Niida, Shumpei

doi:10.1038/s41598-021-00424-1

Cited by 12 publications

(12 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Out of those seven studies, we left GSE63501 and GSE153284 out of the analysis due to the impossibility of access to the expression data and a lack of standardization, respectively. Therefore, we included five studies in the analysis: GSE157239 [47], GSE16759 [48], and GSE48552 [49] for brain tissue and GSE120584 [50] and GSE46579 [51] for blood samples (Table 1) .…”

Section: Resultsmentioning

confidence: 99%

The role of microRNAs in understanding sex-based differences in Alzheimer’s disease

Llera-Oyola,

Carceller,

Andreu

et al. 2023

Preprint

View full text Add to dashboard Cite

Background: Alzheimer's disease (AD) is the most frequent cause of dementia and its incidence is expected to rise as the life expectancy of the population increases. Sex-based differences in AD development have been described, although there are still uncertainties on the role of biological sex in molecular mechanisms of the disease. The study of sex-specific expression profiles of regulatory elements, such as microRNAs (miRNAs), could contribute to a more accurate diagnosis and treatment of the disease. Methods: We conducted a systematic review identifying five studies of microRNA expression in AD that incorporated the biological sex of the samples published in the Gene Expression Omnibus (GEO) repository. Differential expression analyses were performed for each study, considering both disease and biological sex of patients. Subsequently, results were integrated with a meta-analysis methodology. Finally, functional enrichment of the meta-analyses results was performed to establish an association between altered miRNA expression and relevant terms of the Gene Ontology (GO). Results: Meta-analyses of miRNAs expression in blood samples revealed 16 and 22 miRNAs altered in females and males, respectively. Moreover, 9 miRNAs were commonly overexpressed in both sexes, unveiling common miRNAs dysregulation profiles. In contrast, functional enrichment revealed sex-differences in biological processes altered. In males, most of the affected processes were related to ubiquitination, regulation of different kinase activities and apoptotic processes; but in females were linked to RNA splicing and translation. Meta-analyses of brain samples also revealed some alterations in miRNAs expression (6 in females and 4 in males). The unique miRNA altered in both sexes (miR-767-5p) was underexpressed in both males and females. Nonetheless, the functional enrichment analysis did not reveal any affected biological process. Conclusions: Sex-specific meta-analyses allowed for the detection of differentially expressed miRNAs in females and males. Identification of deregulated miRNAs highlighted the relevance of the sex information in biomedical data. Further studies centered on miRNA regulation should meet criteria for comparability and standardization of information.

show abstract

Section: Resultsmentioning

confidence: 99%

The role of microRNAs in understanding sex-based differences in Alzheimer’s disease

Llera-Oyola,

Carceller,

Andreu

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In the dementia context, penalized approaches have been shown to produce more stable results for correlated data and data for which the number of predictors is much larger than the sample size. 45 Ridge regression performed especially well in the presence of high collinearity in linguistic data. 46 Lasso regression has shown some success in addressing high-dimensional AD data, especially in the context of genetic risk detection, 47 biomarker discovery, 48 and analysis of neuroimaging-based endophenotypes.…”

Section: Regression Approachesmentioning

confidence: 95%

“…To ease this problem, different penalization functions have been proposed, each imposing different constraints. In the dementia context, penalized approaches have been shown to produce more stable results for correlated data and data for which the number of predictors is much larger than the sample size 45 . Ridge regression performed especially well in the presence of high collinearity in linguistic data 46 .…”

Section: Types Of ML Techniques Used In Dementia Researchmentioning

confidence: 99%

Artificial intelligence for dementia research methods optimization

Bucholc,

James,

Khleifat

et al. 2023

Alzheimer's & Dementia

View full text Add to dashboard Cite

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high‐dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well‐documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI‐enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co‐produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care.HIGHLIGHTS Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

show abstract

“…In this study, the miRNA expression profiles were obtained from the Gene Expression Omnibus database under the accession code GSE120584 ( Shigemizu et al, 2019a ; Shigemizu et al, 2019b ; Asanomi et al, 2021 ). These expression profiles include 1,601 samples, which are composed of AD cases, VaD cases, DLB cases, MCI cases, and NC.…”

Section: Methodsmentioning

confidence: 99%

Identifying Key MicroRNA Signatures for Neurodegenerative Diseases With Machine Learning Methods

Guo

Ding

et al. 2022

Front. Genet.

View full text Add to dashboard Cite

Neurodegenerative diseases, including Alzheimer’s disease (AD), Parkinson’s disease, and many other disease types, cause cognitive dysfunctions such as dementia via the progressive loss of structure or function of the body’s neurons. However, the etiology of these diseases remains unknown, and diagnosing less common cognitive disorders such as vascular dementia (VaD) remains a challenge. In this work, we developed a machine-leaning-based technique to distinguish between normal control (NC), AD, VaD, dementia with Lewy bodies, and mild cognitive impairment at the microRNA (miRNA) expression level. First, unnecessary miRNA features in the miRNA expression profiles were removed using the Boruta feature selection method, and the retained feature sets were sorted using minimum redundancy maximum relevance and Monte Carlo feature selection to provide two ranking feature lists. The incremental feature selection method was used to construct a series of feature subsets from these feature lists, and the random forest and PART classifiers were trained on the sample data consisting of these feature subsets. On the basis of the model performance of these classifiers with different number of features, the best feature subsets and classifiers were identified, and the classification rules were retrieved from the optimal PART classifiers. Finally, the link between candidate miRNA features, including hsa-miR-3184-5p, has-miR-6088, and has-miR-4649, and neurodegenerative diseases was confirmed using recently published research, laying the groundwork for more research on miRNAs in neurodegenerative diseases for the diagnosis of cognitive impairment and the understanding of potential pathogenic mechanisms.

show abstract

Dementia subtype prediction models constructed by penalized regression methods for multiclass classification using serum microRNA expression data

Cited by 12 publications

References 39 publications

The role of microRNAs in understanding sex-based differences in Alzheimer’s disease

The role of microRNAs in understanding sex-based differences in Alzheimer’s disease

Artificial intelligence for dementia research methods optimization

Identifying Key MicroRNA Signatures for Neurodegenerative Diseases With Machine Learning Methods

Contact Info

Product

Resources

About