Research On Recommendation System For Healthcare Using Feature Extraction & Pattern Recognition

In the era of health informatics,the growth of health information generated by health information systems and healthcare organizations demand expert and intelligent recommendation systems.It has become one of the most valuable tools as it reduces problems such as information overload while selecting and suggesting doctors,hospitals,medicine,diagnosis,etc.according to the patient’s interests.Recommender systems are intelligent decision support software tools whose aim is to provide the most relevant information to a user by discovering patterns in a dataset They assist users to make decisions on a variety of items from different sources.Various techniques and approaches have been applied to design and implement such systems to generate credible recommendations to users.Traditionally,the most common techniques used by many existing recommendation systems are a collaborative approach,content-based approach,knowledge-based approach,and hybrid-based approach that combines two or more techniques in different ways.A multi-criteria recommendation is an extended technique used to predict unknown ratings and recommend exciting items to users based on ratings given to multiple attributes of items.This method has been used and proven by researchers in industries and academic institutions to provide more accurate predictions than the traditional techniques.There are several problems that need to remain in consider while working on a recommendation system.Accuracy improvement has been one of the issues yet to be solved by the recommender systems research community.Recently,multi-criteria recommender classifications that practice multiple criteria ratings to estimate overall rating have been receiving considerable attention within the recommender systems research domain.There is still a need to work on improving the recommendation system by using machine learning techniques.Weighted ranking model using collaborative and content-based approaches is helpful in improving the utilization of the recommendation model.The current study is focused on the implementation of the weighted ranking model using feature extraction based on several features of items.In this study,we propose a hybrid recommendation system framework that uses heterogeneous health data from different sources based on extracting the features an in-depth analysis of these features with their patterns.Our Health recommendation model is service oriented which gives output in a graphical timeline scrutinize and combine the drugs information with the medical test as well as with historical data of the patient.Besides that,for improving more quality of accuracy,we have used foreign health database for recommendation purpose.The novelty of our proposed algorithm is that it provides a recommendation for the hospital as well as doctors and patients both.We have implemented advanced data mining approaches with feature extraction which gives tremendous results towards health improvement,a decrease in chronic diseases,a decrease in mortality rate,etc.For the patient,it suggests a doctor,for the doctor it recommends treatment,and for management of the hospital,it suggests different ways to increase the efficiency of the hospital regarding turnover of the patients.Later we extended our model to different datasets based on feature extraction.To demonstrate the effectiveness of our proposed frameworks,several experiments were carried out.In the experiments,our proposed model was demonstrated on different datasets besides the health dataset.Different datasets of different types and categories are being used for the evaluation and validation of the proposed strategy based on features extraction.Features of all datasets were listed out in order to get the right recommendation of the results.The experimental results for each of the two proposed frameworks together with their corresponding single rating techniques are presented in this study.To analyze the performance of the approaches,we carried out a comparative analysis of their performance with the collaborative filtering technique and other multi-criteria recommendation methods.Through a comparison study with another single-and multi-criteria collaborative filtering methodologies,we demonstrated that using the proposed feature based multi-criteria learning method is an integral part of the multi-criteria recommendation process.In addition,the experimental results also show that using feature extraction to incorporate the multi-criteria rating information for predicting the overall rating has considerably improved the accuracy of the multi-criteria recommender system than using genetic algorithms.Furthermore,we explored other machine learning algorithms for the purpose of prediction of results and recommendation.We also compared the performance of different algorithms with our proposed algorithm and provide the results on different datasets.