Loading...

Investigation and Comparison of Data Mining Techniques Used for Pharmaceutical Drug Consumption Pattern Prediction

Bastani Allahabadi, Shahrzad | 2022

123 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 55484 (51)
  4. University: Sharif University of Technology, International Campus, Kish Island Science and Engineering
  5. Department: Science and Engineering
  6. Advisor(s): Haji, Alireza; Fatahi Valilai, Omid
  7. Abstract:
  8. Data mining is the process of extracting information from large data sets using algorithms and methods derived from the field of statistics, machine learning and database management systems. Data mining, popularly known as knowledge discovery in big data, enables companies and organizations to make informed decisions by collecting, aggregating, analyzing and accessing company data. The pharmaceutical industry is one of the most important levels of the drug supply chain, which has a significant impact on the healthcare sector of any society. In this context data mining can be used in various procedure such as discovery of a new medicine, sequential registration of clinical trials, combining the properties of the new molecule with other molecules, prediction of drugs behavior, demand forecasting, and supply and demand management. Most of Healthcare institutes are lacking valid data bases to make authentic reports except for purely financial and volume-related statements. This research used China total antibiotic consumption data from January 2011 to December 2015 that a total of 173 unique chemical substance names were identified in single or combination antibiotics. These antibiotics were aggregated into 31 classes then into 9 groups. The aim of this research is to forecast antibiotic consumption with the help of this data by using Multi-Layer Perceptron (MLP) we have achieved a function that can be predicted by determining each group of antibiotics and the desired number of months. For this purpose, we have pre-processed the data we had in Excel and sorted them and found a series of information that has the greatest impact on the consumption of antibiotics in the coming year. The results show that the used method has well predicted the antibiotic consumption of group J01xx for 2016. Treatment results and patient satisfaction can be achieved
  9. Keywords:
  10. Pharmaceutical Industry ; Data Mining ; Forecast ; Neural Network ; Consumption Demand ; Multi-Layer Perceptron (MLP) ; Machine Learning

 Digital Object List

 Bookmark

No TOC