首页|Cracow University of Technology Reports Findings in Machine Learning (RECOMED: A comprehensive pharmaceutical recommendation system)
Cracow University of Technology Reports Findings in Machine Learning (RECOMED: A comprehensive pharmaceutical recommendation system)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Krakow, Poland,by NewsRx journalists, research stated, "To build datasets containing useful i nformation from drug databases and recommend a list of drugs to physicians and p atients with high accuracy by considering a wide range of features of people, di seases, and chemicals. A comprehensive pharmaceutical recommendation system was designed based on the features of people, diseases, and medicines extracted from two major drug databases and the created datasets of patients and drug informat ion." The news reporters obtained a quote from the research from the Cracow University of Technology, "Then, the recommendation was given based on recommender system algorithms using patient and caregiver ratings and the knowledge obtained from d rug specifications and interactions. Sentiment analysis was employed by natural language processing approaches in pre-processing, along with neural network-base d methods and recommender system algorithms for modelling the system. Patient co nditions and medicine features were used to make two models based on matrix fact orization. Then, we used drug interaction criteria to filter drugs with severe o r mild interactions with other drugs. We developed a deep learning model for rec ommending drugs using data from 2304 patients as a training set and 660 patients as our validation set. We used knowledge from drug information and combined the model's outcome into a knowledge-based system with the rules obtained from cons traints on taking medicine. Our recommendation system can recommend an acceptabl e combination of medicines similar to the existing prescriptions available in re al life. Compared with conventional matrix factorization, our proposed model imp roves the accuracy, sensitivity, and hit rate by 26 %, 34 %,and 40 %, respectively. In addition, it improves the accuracy, se nsitivity, and hit rate by an average of 31 %, 29 %, a nd 28 % compared to other machine learning methods. We have open-s ourced our implementation in Python. Compared to conventional machine learning a pproaches, we obtained average accuracy, sensitivity, and hit rates of 31 %,29 %, and 28 %, respectively. Compared to convention al matrix factorisation our proposed method improved the accuracy, sensitivity, and hit rate by 26 %, 34 %, and 40 %, res pectively."
KrakowPolandEuropeCyborgsEmergin g TechnologiesMachine Learning
NETL
NSTL
