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

Identification of prognostic RNA editing profiles for clear cell renal carcinoma

Objective

Clear cell renal cell carcinoma (ccRCC) is the most common type of renal cancer and currently lacks effective biomarkers. This research aims to analyze and identify RNA editing profile associated with ccRCC prognosis through bioinformatics and in vitro experiments.

Methods

Transcriptome data and clinical information for ccRCC were retrieved from the TCGA database, and RNA editing files were obtained from the Synapse database. Prognostic models were screened, developed, and assessed using consistency index analysis and independent prognostic analysis, etc. Internal validation models were also constructed for further evaluation. Differential genes were investigated using GO, KEGG, and GSEA enrichment analyses. Furthermore, qPCR was performed to determine gene expression in human renal tubular epithelial cells HK-2 and ccRCC cells A-498, 786-O, and Caki-2.

Results

An RNA editing-based risk score, that effectively distinguishes between high and low-risk populations, has been identified. It includes CHD3| chr17:7815229, MYO19| chr17:34853704, OIP5-AS1| chr15:41590962, MRI1| chr19:13883962, GBP4| chr1:89649327, APOL1| chr22:36662830, FCF1| chr14:75203040 edited sites or genes and could serve as an independent prognostic factor for ccRCC patients. qPCR results showed significant up-regulation of CHD3, MYO19, MRI1, APOL1, and FCF1 in A-498, 786-O, and Caki-2 cells, while the expression of OIP5-AS1 and GBP4 was significantly down-regulated.

Conclusion

RNA editing site-based prognostic models are valuable in differentiating between high and low-risk populations. The seven identified RNA editing sites may be utilized as potential biomarkers for ccRCC.

Exploring the Regulatory Landscape of Dementia: Insights from Non-Coding RNAs

Dementia, a multifaceted neurological syndrome characterized by cognitive decline, poses significant challenges to daily functioning. The main causes of dementia, including Alzheimer's disease (AD), frontotemporal dementia (FTD), Lewy body dementia (LBD), and vascular dementia (VD), have different symptoms and etiologies. Genetic regulators, specifically non-coding RNAs (ncRNAs) such as microRNAs (miRNAs), long non-coding RNAs (lncRNAs), and circular RNAs (circRNAs), are known to play important roles in dementia pathogenesis. MiRNAs, small non-coding RNAs, regulate gene expression by binding to the 3' untranslated regions of target messenger RNAs (mRNAs), while lncRNAs and circRNAs act as molecular sponges for miRNAs, thereby regulating gene expression. The emerging concept of competing endogenous RNA (ceRNA) interactions, involving lncRNAs and circRNAs as competitors for miRNA binding, has gained attention as potential biomarkers and therapeutic targets in dementia-related disorders. This review explores the regulatory roles of ncRNAs, particularly miRNAs, and the intricate dynamics of ceRNA interactions, providing insights into dementia pathogenesis and potential therapeutic avenues.

Alcohol Use Disorder and Dementia: A Review

PURPOSE

By 2040, 21.6% of Americans will be over age 65, and the population of those older than age 85 is estimated to reach 14.4 million. Although not causative, older age is a risk factor for dementia: every 5 years beyond age 65, the risk doubles; approximately one-third of those older than age 85 are diagnosed with dementia. As current alcohol consumption among older adults is significantly higher compared to previous generations, a pressing question is whether drinking alcohol increases the risk for Alzheimer's disease or other forms of dementia.

SEARCH METHODS

Databases explored included PubMed, Web of Science, and ScienceDirect. To accomplish this narrative review on the effects of alcohol consumption on dementia risk, the literature covered included clinical diagnoses, epidemiology, neuropsychology, postmortem pathology, neuroimaging and other biomarkers, and translational studies. Searches conducted between January 12 and August 1, 2023, included the following terms and combinations: "aging," "alcoholism," "alcohol use disorder (AUD)," "brain," "CNS," "dementia," "Wernicke," "Korsakoff," "Alzheimer," "vascular," "frontotemporal," "Lewy body," "clinical," "diagnosis," "epidemiology," "pathology," "autopsy," "postmortem," "histology," "cognitive," "motor," "neuropsychological," "magnetic resonance," "imaging," "PET," "ligand," "degeneration," "atrophy," "translational," "rodent," "rat," "mouse," "model," "amyloid," "neurofibrillary tangles," "α-synuclein," or "presenilin." When relevant, "species" (i.e., "humans" or "other animals") was selected as an additional filter. Review articles were avoided when possible.

SEARCH RESULTS

The two terms "alcoholism" and "aging" retrieved about 1,350 papers; adding phrases-for example, "postmortem" or "magnetic resonance"-limited the number to fewer than 100 papers. Using the traditional term, "alcoholism" with "dementia" resulted in 876 citations, but using the currently accepted term "alcohol use disorder (AUD)" with "dementia" produced only 87 papers. Similarly, whereas the terms "Alzheimer's" and "alcoholism" yielded 318 results, "Alzheimer's" and "alcohol use disorder (AUD)" returned only 40 citations. As pertinent postmortem pathology papers were published in the 1950s and recent animal models of Alzheimer's disease were created in the early 2000s, articles referenced span the years 1957 to 2024. In total, more than 5,000 articles were considered; about 400 are herein referenced.

DISCUSSION AND CONCLUSIONS

Chronic alcohol misuse accelerates brain aging and contributes to cognitive impairments, including those in the mnemonic domain. The consensus among studies from multiple disciplines, however, is that alcohol misuse can increase the risk for dementia, but not necessarily Alzheimer's disease. Key issues to consider include the reversibility of brain damage following abstinence from chronic alcohol misuse compared to the degenerative and progressive course of Alzheimer's disease, and the characteristic presence of protein inclusions in the brains of people with Alzheimer's disease, which are absent in the brains of those with AUD.

Classification performance assessment for imbalanced multiclass data

The evaluation of diagnostic systems is pivotal for ensuring the deployment of high-quality solutions, especially given the pronounced context-sensitivity of certain systems, particularly in fields such as biomedicine. Of notable importance are predictive models where the target variable can encompass multiple values (multiclass), especially when these classes exhibit substantial frequency disparities (imbalance). In this study, we introduce the Imbalanced Multiclass Classification Performance (IMCP) curve, specifically designed for multiclass datasets (unlike the ROC curve), and characterized by its resilience to class distribution variations (in contrast to accuracy or Fβ -score). Moreover, the IMCP curve facilitates individual performance assessment for each class within the diagnostic system, shedding light on the confidence associated with each prediction-an aspect of particular significance in medical diagnosis. Empirical experiments conducted with real-world data in a multiclass context (involving 35 types of tumors) featuring a high level of imbalance demonstrate that both the IMCP curve and the area under the IMCP curve serve as excellent indicators of classification quality.

Biomarker profiling to determine clinical impact of microRNAs in cognitive disorders

Alzheimer's disease (AD) and post-stroke cognitive impairment (PSCI) are the leading causes of progressive dementia related to neurodegenerative and cerebrovascular injuries in elderly populations. Despite decades of research, patients with these conditions still lack minimally invasive, low-cost, and effective diagnostic and treatment methods. MicroRNAs (miRNAs) play a vital role in AD and PSCI pathology. As they are easily obtained from patients, miRNAs are promising candidates for the diagnosis and treatment of these two disorders. In this study, we performed complete sequencing analysis of miRNAs from 24 participants, split evenly into the PSCI, post-stroke non-cognitive impairment (PSNCI), AD, and normal control (NC) groups. To screen for differentially expressed miRNAs (DE-miRNAs) in patients, we predicted their target genes using bioinformatics analysis. Our analyses identified miRNAs that can distinguish between the investigated disorders; several of them were novel and never previously reported. Their target genes play key roles in multiple signaling pathways that have potential to be modified as a clinical treatment. In conclusion, our study demonstrates the potential of miRNAs and their key target genes in disease management. Further in-depth investigations with larger sample sizes will contribute to the development of precise treatments for AD and PSCI.

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

BACKGROUND

The incidence of Alzheimer's disease (AD)-the most frequent cause of dementia-is expected to increase as life expectancies rise across the globe. While sex-based differences in AD have previously been described, there remain uncertainties regarding any association between sex and disease-associated molecular mechanisms. Studying sex-specific expression profiles of regulatory factors such as microRNAs (miRNAs) could contribute to more accurate disease diagnosis and treatment.

METHODS

A systematic review identified six studies of microRNA expression in AD patients that incorporated information regarding the biological sex of samples in the Gene Expression Omnibus repository. A differential microRNA expression analysis was performed, considering disease status and patient sex. Subsequently, results were integrated within a meta-analysis methodology, with a functional enrichment of meta-analysis results establishing an association between altered miRNA expression and relevant Gene Ontology terms.

RESULTS

Meta-analyses of miRNA expression profiles in blood samples revealed the alteration of sixteen miRNAs in female and 22 miRNAs in male AD patients. We discovered nine miRNAs commonly overexpressed in both sexes, suggesting a shared miRNA dysregulation profile. Functional enrichment results based on miRNA profiles revealed sex-based differences in biological processes; most affected processes related to ubiquitination, regulation of different kinase activities, and apoptotic processes in males, but RNA splicing and translation in females. Meta-analyses of miRNA expression profiles in brain samples revealed the alteration of six miRNAs in female and four miRNAs in male AD patients. We observed a single underexpressed miRNA in female and male AD patients (hsa-miR-767-5p); however, the functional enrichment analysis for brain samples did not reveal any specifically affected biological process.

CONCLUSIONS

Sex-specific meta-analyses supported the detection of differentially expressed miRNAs in female and male AD patients, highlighting the relevance of sex-based information in biomedical data. Further studies on miRNA regulation in AD patients should meet the criteria for comparability and standardization of information.

Artificial intelligence for dementia research methods optimization

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.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Identifying Key MicroRNA Signatures for Neurodegenerative Diseases With Machine Learning Methods

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.