Intelligent Systems and Machine Learning Integration for Solving Computer Based Models in Predictive Analytics of Nano-Biosensor Responses

Abstract

This study investigates the integration of machine learning techniques into the predictive analytics of nano biosensor responses, focusing on mathematical models that describe sensitivity, specificity, detection limits, and response times. The research applied various machine learning models, including logistic regression, random forests, neural networks, and support vector machines, to enhance predictive accuracy of biosensor responses. Notably, the neural network model achieved the highest accuracy of 93% and an F1 score of 0.93, outperforming other models. The random forest model also demonstrated strong performance with an accuracy of 91% and an F1 score of 0.91, particularly in predicting biosensor sensitivity and specificity. Sensitivity and specificity analysis across different thresholds revealed optimal performance at a threshold of 0.5, where specificity reached 95%, with corresponding sensitivity of 85%. These findings highlight effectiveness of machine learning integration in improving the reliability and precision of nano biosensors, enhancing their applicability real-time detection and diagnostic scenarios.