|
Medicine Recommendation System Based On Patient Reviews
[Full Text]
AUTHOR(S)
T. Venkat Narayana Rao, Anjum Unnisa, Kotha Sreni
KEYWORDS
Recommendation system, Sentiment Analysis, N-gram , Lightgbm.
ABSTRACT
Most of the people tend to live a long and healthy life, where they are more conscious about their health. But many studies show that almost many people die due to the medical errors caused in terms of taking wrong medicines and these errors are caused by doctors, who prescribe medicines based on their experiences which are quite limited. As machine learning, deep learning and data mining like technologies that are emerging day by day, these technologies can help us to explore the medical history and can reduce medical errors by being doctor friendly. In this paper proposes a medicine recommendation system , which takes the patient review data and performs sentiment analysis on it to find the best medicine for a disease by using N-Gram model. In order to increase the accuracy, a Lightgbm model is used to perform medication analysis. The paper also discusses the advantages, disadvantages and enhancements that can be incorporated to improve the accuracy.
REFERENCES
S. Fox and M. Duggan. Health online 2013. Pew Internet and American Life Project. http://pewinternet.org/Reports/2013/Health-online.aspx, 2013.
[2] X. Guo, J. Lu, Intelligent e-government services with personalized recommendation techniques, International Journal of Intelligence Systems,2007,401–417
[3] T. Lee, J. Chun, J. Shim, S.-g. Lee, An ontology-based product recommender system for B2B marketplaces, International Journal of Electronic Commerce, 2006,125–155.
[4] J.B. Schafer, J. Konstan, J. Riedl, E-commerce recommendation applications, Applications of Data Mining to Electronic Commerce,Springer, US 2001, 115–153.
[5] O.R. Zaiane, Building a recommender agent for e-learning systems, Proceedings of 2002 International Conference on Computers in Education, 2002, 55–59
[6] T.Hung-Wen,S.VonWun,A personalized restaurant recommender agent for mobile e-service, 2004 IEEE International Conference on e-Technology, e-Commerce and e-Service. EEE, 2004, 259–262.
[7] Popescu AM, Etzioni O (2005)Extracting product features and opinions from reviews. Proceedings of the conference on human language technology and empirical methods in natural language processing. Association for Computational Linguistics, pp: 339-346
[8] Mei Q, Ling X, Wondra M, Su H, Zhai C (2007) Topic sentiment mixture: modeling facets and opinions in weblogs. Predictive Modeling of Web Users, pp: 171-180.
[9] https://www.livewell.pk/ [Accessed on: August 2017].
[10] Aronson AR (2001) Effective mapping of biomedical text to the UMLS Metathesaurus: the MetaMap program. In: AMIA annual symposium proceedings. Washington DC: American Medical Informatics Association, pp: 17-21.
[11] Subhash C. Pandey, “Data Mining techniques for medical data: A Review”, “IEEE”, 2016.
[12] F. O. Isinkaye, Y.O. Fola Jimi, B.A. Ojokoh,“Recmmendation systems : Principles, Methods and Evaluation”, “Elsevier”, 261-273,2015.
[13] Zhang S, Zhang C, Yang Q. Data preparation for data mining[J]. Applied Artificial Intelligence, 2003, 17(5-6): 375-381.
[14] Forman, G. 2003. An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res.3:1289–1305
[15] Chamlertwat, W.; Bhattarakosol, P.; Rungkasiri, T.; and Haruechaiyasak, C. 2012. Discovering consumer insight from twitter viasentiment analysis. J. UCS 18(8):973–992
[16] Lorenzo-Romero C, Constantinides E, Brunink LA (2014) Co-creation: customer integration in social media-based product and service development. Procedia Soc Behav Sci 148: 383-396.
|
