The innovation aims to identify serum protein markers for accurately distinguishing between healthy individuals and those infected with malaria, particularly Plasmodium falciparum (FM) and Plasmodium vivax (VM). Using advanced proteomic techniques and statistical analysis, the study identified specific proteins and developed prediction models with high accuracy rates for discriminating between FM, VM, and healthy controls. Novel findings include the discovery of previously unreported serum proteins associated with malaria pathogenesis. The invention entails methods and devices for leveraging host protein expression to enhance malaria diagnosis. This innovation offers significant advantages, including the ability to differentiate between different malaria infections, including those with low parasitemia, using host protein expression.
Figure (1) Flow diagram illustrating the classification of Falciparum Malaria (FM), Vivax Malaria (VM), and Healthy Controls (HC) using multivariate statistical analysis and machine learning algorithms based on differentially expressed serum proteins identified in.
The current diagnostic methods for malaria often lack the accuracy and specificity needed to distinguish between different types of malaria infections (such as Plasmodium falciparum and Plasmodium vivax) and healthy individuals. Additionally, existing approaches may not adequately detect low levels of parasitemia. Consequently, there is a pressing need for improved diagnostic techniques that can reliably differentiate between healthy subjects and malaria patients, accurately identify the type of malaria infection, and detect infections with very low parasitemia levels.
- Host Protein-Based Detection: This method measures the expression of specific host proteins, leveraging the host's immune response to malaria, unlike conventional tests that detect parasite proteins or antigens.
- Comprehensive Protein Panel: It identifies a panel of multiple host proteins, including Serum Amyloid A, paraoxonase, apolipoproteins (A-I, A-IV, E), haptoglobin, hemopexin, Retinol Binding Protein, and complement C4. This multi-protein approach offers a more robust and accurate classification than single-marker diagnostics.
- Detection of Low Parasitemia: The identified classifier proteins can discriminate malaria patients even with very low parasitemia levels, addressing a significant limitation of current diagnostic tools.
- High Accuracy in Classification: The method achieves up to 100% accuracy with Decision Trees and 95.83% with Support Vector Machines (SVM) in blinded predictions. It effectively distinguishes between healthy controls (HC), falciparum malaria (FM), and vivax malaria (VM) patients with high sensitivity and specificity.
- Advanced Statistical Models: Incorporates machine learning algorithms like PLS-DA, SVM, Decision Trees, and Naïve Bayes to classify samples based on protein expression, supporting the system’s predictive power and adaptability.
- Diagnostic Device: The prototype diagnostic device consists of a compact apparatus equipped with sensors for detecting host protein expression levels. It includes components such as microcontrollers, biosensors, and signal processing units. The device operates on standard electrical input voltage (e.g., 5V DC) and may require specific chemical reagents or assay kits for protein detection. The dimensions are approximately 10cm x 10cm x 5cm.
- Statistical Classification Software: The prototype software is designed to run on a computer system and employs machine learning algorithms such as PLS-DA, SVM, Decision Trees, and Naïve Bayes for data analysis. Input data consists of protein expression profiles obtained from the diagnostic device.
Biomarker panel validated in human clinical serum samples using multiple proteomics and immunoassay platforms. Demonstrated discrimination of falciparum, vivax, and healthy controls with high accuracy. A prototype diagnostic kit has been developed. The technology is currently available for licensing and ready for further clinical validation.
6
Improved diagnosis enables accurate and early detection of malaria, which is crucial for effective treatment and reducing disease transmission. This advancement significantly enhances public health by strengthening malaria surveillance and control efforts. Furthermore, the ability to differentiate between Plasmodium falciparum and Plasmodium vivax allows for precise, targeted therapy, ensuring patients receive the most appropriate treatment. Such accuracy also promotes efficient use of medical resources, which is especially vital in low-resource settings where healthcare infrastructure may be limited.
- Malaria Diagnosis: Accurate detection and differentiation of falciparum and vivax malaria.
- Disease Surveillance: Monitoring malaria prevalence in populations.
- Clinical Research: Studying host protein responses to malaria infection.
- Personalized Medicine: Tailoring treatments based on protein expression profiles.
- Diagnostic Device Development: Creating advanced tools for malaria detection.
Geography of IP
Type of IP
201922050215
512772