Background: The current standard for Parkinson's disease (PD) diagnosis is often imprecise and expensive. However, the dysregulation patterns of microRNA (miRNA) hold potential as a reliable and effective non-invasive diagnosis of PD.

Methods: We use data mining to elucidate new miRNA biomarkers and then develop a machine-learning (ML) model to diagnose PD based on these biomarkers.

Results: The best-performing ML model, trained on filtered miRNA dysregulated in PD, was able to identify miRNA biomarkers with 95.65% accuracy. Through analysis of miRNA implicated in PD, thousands of descriptors reliant on gene targets were created that can be used to identify novel biomarkers and strengthen PD diagnosis.

Conclusions: The developed ML model based on miRNAs and their genomic pathway descriptors achieved high accuracies for the prediction of PD.

Download full-text PDF

Source
http://dx.doi.org/10.31083/j.fbl2901004DOI Listing

Publication Analysis

Top Keywords

mirna biomarkers
12
parkinson's disease
8
disease diagnosis
8
mirna
6
diagnosis mirna
4
biomarkers
4
biomarkers deep
4
deep learning
4
learning background
4
background current
4

Similar Publications

The current study was deployed to evaluate the role of metastasis-associated lung adenocarcinoma transcript 1 (MALAT1) and miR-155, along with the inflammatory markers, TNFα and IL-6, and the adhesion molecule, cluster of differentiation 106 (CD106), in Behçet's disease (BD) pathogenesis. The study also assessed MALAT1/miR-155 as promising diagnostic and prognostic biomarkers for BD. The current retrospective case-control study included 74 Egyptian BD patients and 50 age and sex-matched controls.

View Article and Find Full Text PDF

As multiple imaging modalities cannot reliably diagnose cardiac tumors, the molecular approach offers alternative ways to detect rare ones. One such molecular approach is CRISPR-based diagnostics (CRISPR-Dx). CRISPR-Dx enables visual readout, portable diagnostics, and rapid and multiplex detection of nucleic acids such as microRNA (miRNA).

View Article and Find Full Text PDF

Evaluation of Plasma microRNA-222 as a Biomarker for Gastric Cancer.

J Clin Med

December 2024

Department of Surgery, Toho University Sakura Medical Center, 564-1 Shimoshizu, Sakura 285-8741, Chiba, Japan.

The dysregulation of microRNAs (miRNAs) has been detected in patients with gastric cancer (GC), which inspired the use of miRNAs as a novel biomarker for GC. In this study, we investigated the previously reported miRNA dysfunction in cancer tissues as a potential plasma biomarker for GC using quantitative reverse transcriptase polymerase chain reaction (RT-PCR). The published miRNA abnormalities were searched in the microRNA Cancer Association Database.

View Article and Find Full Text PDF

Chronic Gastrointestinal Disorders and miRNA-Associated Disease: An Up-to-Date.

Int J Mol Sci

January 2025

Istituto di Bioimmagini e Sistemi Biologici Complessi (IBSBC), National Research Council (CNR), Segrate, 20054 Milan, Italy.

Chronic gastrointestinal disorders such as inflammatory bowel diseases (IBDs) and irritable bowel syndrome (IBS) impose significant health burdens globally. IBDs, encompassing Crohn's disease and ulcerative colitis, are multifactorial disorders characterized by chronic inflammation of the gastrointestinal tract. On the other hand, IBS is one of the principal gastrointestinal tract functional disorders and is characterized by abdominal pain and altered bowel habits.

View Article and Find Full Text PDF

Gastric cancer (GC) remains the most common malignant tumor of the gastrointestinal tract and one of the leading causes of cancer-related deaths worldwide. Non-coding RNAs (ncRNAs), including microRNAs (miRNAs), are involved in the pathogenesis and progression of GC and, therefore, may be potential diagnostic and prognostic biomarkers. Our work was aimed at investigating the predicted regulation of by miR-129-5p and miR-3613-3p and the clinical value of their aberrant expression in GC.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!