Drug Recommendation System for Diabetes Using a Collaborative Filtering and Clustering Approach: Development and Performance Evaluation

Abstract

Background Diabetes is a public health problem worldwide. Although diabetes is a chronic and incurable disease, measures and treatments can be taken to control it and keep the patient stable. Diabetes has been the subject of extensive research, ranging from disease prevention to the use of technologies for its diagnosis and control. Health institutions obtain information required for the diagnosis of diabetes through various tests, and appropriate treatment is provided according to the diagnosis. These institutions have databases with large volumes of information that can be analyzed and used in different applications such as pattern discovery and outcome prediction, which can help health personnel in making decisions about treatments or determining the appropriate prescriptions for diabetes management. Objective The aim of this study was to develop a drug recommendation system for patients with diabetes based on collaborative filtering and clustering techniques as a complement to the treatments given by the treating doctor. Methods The data set used contains information from patients with diabetes available in the University of California Irvine Machine Learning Repository. Data mining techniques were applied for processing and analysis of the data set. Unsupervised learning techniques were used for dimensionality reduction and patient clustering. Drug predictions were obtained with a user-based collaborative filtering approach, which enabled creating a patient profile that can be compared with the profiles of other patients with similar characteristics. Finally, recommendations were made considering the identified patient groups. The performance of the system was evaluated using metrics to assess the quality of the groups and the quality of the predictions and recommendations. Results Principal component analysis to reduce the dimensionality of the data showed that eight components best explained the variability of the data. We identified six groups of patients using the clustering algorithm, which were evenly distributed. These groups were identified based on the available information of patients with diabetes, and then the variation between groups was examined to predict a suitable medication for a target patient. The recommender system achieved good results in the quality of predictions with a mean squared error metric of 0.51 and accuracy in the quality of recommendations of 0.61, which is acceptable. Conclusions This work presents a recommendation system that suggests medications according to drug information and the characteristics of patients with diabetes. Some aspects related to this disease were analyzed based on the data set used from patients with diabetes. The experimental results with clustering and prediction techniques were found to be acceptable for the recommendation process. This system can provide a novel perspective for health institutions that require technologies to support health care personnel in the management of diabetes treatment and control.

A practical statin recommendation system based on real-world data to improve LDL-C management in secondary prevention

“…Their study found that individual treatment effects resulted in recommendations that were significantly better than the usual treatment in reducing stroke and the composite end point of stroke and major bleeding. In addition, a diabetes drug recommendation model by Morales et al, 9 which uses a collaborative filtering and clustering approach, was reported to help health personnel determine appropriate prescriptions for diabetes management. The prediction results of this recommender system have good results, providing a new perspective for diabetes treatment and clinical management.…”

“…Recently, machine learning has been studied in precision medication to help decision making in an individual patient. [9][10][11] Although results from large population-based studies provide average treatment effects, physicians are unsure to make the best strategy for a single patient due to potential individual heterogeneity. Machine learning can be used to approach complex clinical situations and train predictive models based on single individuals.…”

Web-Based Patient Recommender Systems for Preventive Care: Protocol for Empirical Research Propositions

“…Furthermore, collaborative filtering and clustering can be used to develop a drug recommendation system that suggests medications for patients with diabetes by comparing a specific patient profile with those of patients with similar characteristics [ 18 ]. Similarly, collaborative filtering and clustering can be used to develop a recommender system for patients with cardiovascular diseases [ 19 ].…”

Personalized surgical treatment recommendation with joint consideration of multiple decision-making dimensions

“…Another major component of these efforts, however, tries to achieve intelligent treatment recommendations in a data-driven manner based on statistical rules learned from big clinical data via diversi ed machine learning methods, for example, clustering analysis, logistic regression, decision tree, tabular Q-learning, and so on. It has been successful in treatment recommendation and optimization for mobilization in ICU 10 , diabetes 11 , atrial brillation 12 , postmenopausal osteoporosis 13 , basal cell carcinoma 14 , breast cancer 15 , cardiovascular disease 16 , and ovarian cancer 17 . Moreover, as a typical representative of machinelearning-driven AI systems for automated disease diagnosis and treatment recommendation, the famous commercialized product Watson for Oncology designed by International Business Machine (IBM) has been proven to be reliable in treatment recommendations for various types of cancer, e.g., breast cancer 18 and lung cancer 19 .…”