miRNA SVM Classifier for GBM Bevacizumab Response Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for classifying and detecting glioblastoma multiforme (GBM) bevacizumab (BVZ)-responsive subtypes are inaccurate, leading to ineffective treatment outcomes and adverse side effects, as they rely on traditional biomarkers and lack precise identification of drug response subgroups.
Innovation Solution
A method using a panel of microRNAs (miRNAs) as biomarkers in combination with machine learning algorithms, specifically support vector machines (SVM), to classify and detect GBM BVZ-responsive subtypes based on differential expression of miRNAs and mRNAs, providing a more accurate prediction of treatment responses and avoiding unnecessary treatment-related side effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional biomarkers and classification methods are used for GBM subtyping, then the classification process is simple and quick, but the accuracy of treatment prediction is poor leading to ineffective outcomes
Solution Approach 1:
The patent segments the complex classification problem into multiple components: selecting specific miRNA biomarkers (miR-21, miR-10b, miR-197), choosing appropriate machine learning algorithms (SVM, RF, NN), and optimizing their combination. This segmentation allows the system to achieve high accuracy through coordinated multiple elements rather than relying on a single complex method.
Solution Approach 2:
The patent introduces machine learning algorithms as intermediaries between the miRNA biomarker data and the treatment prediction outcome. These algorithms process the biomarker expression levels and translate them into accurate treatment response predictions, acting as a mediator that bridges the gap between raw data and clinical decision-making.
2Reliability
If bevacizumab treatment is administered to all GBM patients, then treatment coverage is maximized, but adverse side effects increase for non-responsive patients
Solution Approach 1:
The patent performs preliminary classification of GBM patients into BVZ-responsive and BVZ-non-responsive subtypes before administering bevacizumab treatment. By using miRNA biomarkers and machine learning algorithms to predict treatment response in advance, the system enables clinicians to avoid administering bevacizumab to patients who are unlikely to benefit, thereby preventing adverse side effects while maintaining treatment efficacy for responsive patients.
3Measurement precision
If multiple miRNAs are used for classification, then the precision of subtype detection improves, but the difficulty of accurate detection by traditional methods increases
Solution Approach 1:
The patent replaces traditional manual or simple threshold-based detection methods with machine learning algorithms (SVM, random forest, neural networks) that can automatically process and interpret multiple miRNA expression levels. This substitution enables the system to handle the complexity of multiple biomarkers and achieve high detection precision without requiring manual analysis of each miRNA combination.
Data Source
AI summary
The present invention relates to methods for classification, detection, and diagnosis of glioblastoma multiforme (GBM) bevacizumab (BVZ)-responsive and non-responsive subtypes based on selection of a machine learning algorithm and its combination with differential expression DE of microRNAs (miRNAs) and messenger RNAs (mRNAs), particularly a panel of a group of miRNAs to be used as biomarkers, along with clinical characteristics, and related functional pathways for precise diagnosis and further treatment of GBM patients. The present invention discloses that based on miR-21 and miR-10b expression z-scores, approximately 30% of GBM patients were classified as having the BVZ-responsive GBM subtype. The present invention provides that BVZ GBM subtypes can be classified and detected by a combination of SVM classifiers and miRNA panels in existing tissue GBM datasets. The present invention further provides that with certain modifications, the classifier as disclosed in the present invention may be used for the classification and detection of BVZ GBM subtypes for clinical use. Additionally, as one such clinical use, the present invention provides methods for prescreening of GBM patients to prevent aging-related side effects in BVZ-non-responsive subtype of the GBM patients after BVZ treatment, in addition to the side effects of healing complications caused by BVZ treatment.