AUTHOR=Bai Yongyi , Yao Haishen , Jiang Xuehan , Bian Suyan , Zhou Jinghui , Sun Xingzhi , Hu Gang , Sun Lan , Xie Guotong , He Kunlun TITLE=Construction of a Non-Mutually Exclusive Decision Tree for Medication Recommendation of Chronic Heart Failure JOURNAL=Frontiers in Pharmacology VOLUME=Volume 12 - 2021 YEAR=2022 URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2021.758573 DOI=10.3389/fphar.2021.758573 ISSN=1663-9812 ABSTRACT=Objective: Although guidelines have recommended standardized drug treatment for Heart failure (HF), there are still many challenges in making the correct clinical decisions due to the complicated clinical situations of HF patients. Each patient would satisfy several recommendations, meaning the decision tree of HF treatment should be non-mutually exclusive and the same patient would be allocated to several leaf node in the decision tree. In the current study, we aim to propose a way to ensemble a non-mutually exclusive decision tree for recommendation system for complicated diseases, such as HF. Methods: The non-mutually exclusive decision tree was constructed via knowledge rules summarized from the HF clinical guidelines. Then the similar patients were defined as those who followed the same pattern of leaf node allocation according to the decision tree. The frequent medication patterns for each similar patient were mined using the Apriori algorithms. And we also carried out the outcomes prognosis analyses to show the capability for the evidence-based medication recommendations of our non-mutually exclusive decision tree. Results: Based on a large database which included 29,689 patients with 84,705 admissions, we tested the framework for HF treatment recommendation. In the constructed decision tree, the HF treatment recommendations were grouped into two independent parts. The first part were recommendations for new cases, and the second part were recommendations when patients had different historical medication. There are 14 leaf nodes in our decision tree and most of the leaf nodes had a guideline adherence of around 90%. We reported the top 10 popular similar patients, which accounted for 32.84% of the whole population. In addition, the multiple outcomes prognosis analyses were carried out to assess the medications for one of the similar patient’s subgroups. Our results showed even for the same similar patient’s subgroup, there was no one medication pattern would benefit all outcomes. Conclusions: In the present study, the methodology to construct a non-mutually exclusive decision tree for medication recommendations for HF and its application in CDSS was proposed. Our framework is universal for most diseases and could be generally applied for developing the CDSS for treatment.