This paper presents the development of a medicine recommender system called RecoMed which aims to assist physicians in the prescription process for hypertension. The system provides information about medications prescribed by other doctors and recommends additional medicines based on association rules and graph mining. The methodology consists of two steps: mining medicine association rules and performing graph mining to generate an enriched recommendation using the ATC code. The initial graph is constructed from historical prescription data followed by data pruning to remove frequently prescribed medicines. The medicines are then matched to the ATC code for classification and clustered using DBSCAN and Louvain algorithms. The system outputs a list of recommended medicines which physicians can choose based on the patient's clinical symptoms. The performance of the system is evaluated using class 2 high blood pressure medications and has been reviewed and confirmed by an expert in the field. Additionally, this paper outlines the proposed method, presents results, compares and evaluates the approach, and concludes with future work suggestions. Overall, RecoMed provides a valuable tool for physicians particularly those in underserved areas or with limited experience to improve their decision-making process in prescribing hypertension medications.
RecoMed is a computer system that helps doctors choose the right medicine for people with high blood pressure. It gives information about medicines that are already prescribed and suggests other medicines based on patterns and connections. The system uses a special way of looking at data called mining to find these patterns. It looks at past prescriptions to make a starting point, then removes common medicines. It also groups similar medicines together using special algorithms. The system gives a list of recommended medicines based on what symptoms the patient has. Experts have checked how well the system works by looking at specific high blood pressure medicines. The paper explains how the system works, shows its results, compares it to other methods, and suggests ways to make it even better. RecoMed helps doctors in areas where there aren't many resources or experience."
Introducing RecoMed: A Medicine Recommender System for Hypertension
Hypertension is a serious medical condition that affects millions of people around the world. It can lead to stroke, heart attack, and other life-threatening complications if not managed properly. To ensure proper management, physicians must be able to prescribe the right medications for their patients. However, this task can be difficult due to the large number of available medicines and limited experience in prescribing them. This is where RecoMed comes in – a medicine recommender system designed to assist physicians in prescribing hypertension medications.
How Does RecoMed Work?
RecoMed uses association rules and graph mining techniques to generate recommendations based on historical prescription data. The process consists of two steps: (1) mining medicine association rules; and (2) performing graph mining using the Anatomical Therapeutic Chemical (ATC) code classification system.
The first step involves constructing an initial graph from historical prescription data followed by data pruning which removes frequently prescribed medicines from consideration. The second step matches each remaining medicine with its corresponding ATC code for classification purposes before clustering them using DBSCAN or Louvain algorithms depending on user preference. Finally, the system outputs a list of recommended medicines which physicians can choose based on their patient’s clinical symptoms.
Evaluating Performance
To evaluate performance, class 2 high blood pressure medications were used as test cases for RecoMed's recommendation engine with results reviewed and confirmed by experts in the field of hypertension management. The results showed that RecoMed was able to accurately recommend appropriate medication options with minimal effort required from physicians – particularly those working in underserved areas or with limited experience in prescribing hypertension medications.
Conclusion
In conclusion, this paper presents an effective method for recommending hypertension medications through association rule mining and graph analysis using ATC codes as well as evaluates its performance against class 2 high blood pressure medications with positive results verified by experts in the field of hypertension management . Additionally, it outlines future work suggestions such as incorporating additional features into the model or expanding it beyond just hypertensive drugs so that it may become even more useful for healthcare professionals worldwide who are tasked with managing this condition effectively while providing quality care to their patients at all times
Background and Objective High medicine diversity has always been a significant challenge for prescription, causing confusion or doubt in physicians' decision-making process. This paper aims to develop a medicine recommender system called RecoMed to aid the physician in the prescription process of hypertension by providing information about what medications have been prescribed by other doctors and figuring out what other medicines can be recommended in addition to the one in question. Methods There are two steps to the developed method: First, association rule mining algorithms are employed to find medicine association rules. The second step entails graph mining and clustering to present an enriched recommendation via ATC code, which itself comprises several steps. First, the initial graph is constructed from historical prescription data. Then, data pruning is performed in the second step, after which the medicines with a high repetition rate are removed at the discretion of a general medical practitioner. Next, the medicines are matched to a well-known medicine classification system called the ATC code to provide an enriched recommendation. And finally, the DBSCAN and Louvain algorithms cluster medicines in the final step. Results A list of recommended medicines is provided as the system's output, and physicians can choose one or more of the medicines based on the patient's clinical symptoms. Only the medicines of class 2, related to high blood pressure medications, are used to assess the system's performance. The results obtained from this system have been reviewed and confirmed by an expert in this field.
