A heterogeneous network embedded medicine recommendation system based on LSTM

In the healthcare sector, patient data plays a crucial role in medical diagnoses and treatment plans. However, existing techniques for finding similar patients based on Electronic Health Record (EHR) data face challenges due to high-dimensional and sparse vectors. To overcome this challenge, the paper proposes developing a novel heterogeneous network-embedded drug recommendation system. The system focuses on classifying the sentiment of drug users based on their reviews and other relevant features such as their medical condition, drug rating, and usage date. The overall framework of the system follows a step-by-step approach, starting with data exploration and preprocessing, followed by the development of a classification model based on Long-Short-Term Memory (LSTM) networks. During the data exploration phase, various visualization and statistical techniques are employed to analyze the different data types. This process helps in understanding the characteristics of the data, identifying patterns, and preparing the data to align with the research objective. Furthermore, additional variables are considered suitable for the LSTM model, a recurrent neural network (RNN) type designed to handle sequence data and long-term prediction problems. Unlike other models that process individual data points, LSTM incorporates feedback connections to process complete data sequences. This approach enhances the effectiveness of recommendation systems and enables the prediction of new drug user ratings based on existing user ratings. The developed system demonstrates promising results, achieving a classification accuracy of 92%. This indicates its ability to accurately predict the sentiment of drug users based on their reviews and other associated features. The novelty of this research lies in the integration of a heterogeneous network-embedded approach with LSTM-based classification, providing a more comprehensive and accurate drug recommendation system compared to existing methods.