Design of Medicine Recommendation System (MRS) for Biomedical Application Using Machine Learning Techniques

Machine learning has been more prevalent recently in the medical industry. These systems can both assist individuals in locating the most appropriate drug for their conditions as well as assist physicians in making better treatment choices. To create pharmaceutical recommendation systems, a variety of different machine learning techniques may be applied. Collaborative filtering is a popular technique that suggest medicines to patients based on those that people with comparable diseases have used. A different strategy like Content-based filtering, Random forest approach, and Decision tree makes prescription recommendations by considering different healthcare parameters of patients like symptoms, duration of symptoms and temperature. Medical recommendations systems based on machine learning have the potential to raise the standard of patient care. These technologies can aid in ensuring that patients receive the care they require by making personalized suggestions to them. Additionally, these technologies can contribute to enhancing the security and effectiveness of drug therapy by assisting physicians in making more knowledgeable treatment choices. Basically, this technique analyses the symptoms, duration of symptom, Body temperature and predicts the best suitable medicine. It involve multiple comparisons and multiple decisions to predicted the medicine. The results are represented graphically that gives the relation between the features as symptoms, Duration, Temperature and Target as medicines. It gives the whole account of recommending the medicines based on all the above parameters. The research will aid in the healthcare sector's transition from the conventional scenario to a more personalize model in a tele-health environment.