Machine Learning (ML) is a set of contemporary approaches to predicting, recognising, and making decisions without the use of humans. From disease detection to simulation, machine learning is rapidly emerging in the medical industry. The purpose of the proposed study is to examine how supervised machine learning algorithms, such as support vector machines (SVMs), can be used to predict medicine dose. The main advantage of employing SVM-based algorithms is that they can handle an unlimited number of input parameters (patient characteristics, like symptoms), and each parameter is treated identically no matter how differently it looks on the surface. SVM learning, or machine learning with maximisation (support) of separating margin (vector), is a strong classification algorithm that’s used for classification or subtyping. Building a machine learning model to determine the appropriate medication dose for and patient is critical to clinical practise and time-consuming for modelling software. Rather than using conventional explicit approaches, we suggest a machine learning approach in this article for predicting disease and determining medicine dosage based on the patient’s symptoms.
Keywords: Machine learning; SVM; disease prediction; medicine dosage.
Citation : Rekha Gangula, Murali Mohan and Dayakar Thalla, “Optimizing Medicine Dosage Recognition through Symptom Intensity Assessment with Support Vector Machines”, Journal of Computer Allied Intelligence (JCAI), vol.02, no.01, pp.16-25,2024.