Leveraging machine learning and big data for optimizing medication prescriptions in complex diseases: a case study in diabetes management

• Published in: Journal of big data Vol. 7; no. 1; pp. 1 - 24
• Main Authors: Hosseini, Mahsa Madani, Zargoush, Manaf, Alemi, Farrokh, Kheirbek, Raya Elfadel
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 10-04-2020; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Bayesian analysis; Bayesian network; Big Data; Case studies; Clinical decision-making; Communications Engineering; Computational Science and Engineering; Computer Science; D-separation; Data Mining and Knowledge Discovery; Database Management; Diabetes; Information Storage and Retrieval; Machine learning; Markov blanket; Mathematical Applications in Computer Science; Medication prescription optimization; Metformin; Networks; Optimization; Task complexity; Complex diseases; Medication prescription optimization; Machine learning; Markov blanket; D-separation; Diabetes; Bayesian network; Clinical decision-making
• ISSN: 2196-1115; 2196-1115
• DOI: 10.1186/s40537-020-00302-z

This paper proposes a novel algorithm for optimizing decision variables with respect to an outcome variable of interest in complex problems, such as those arising from big data. The proposed algorithm builds on the notion of Markov blankets in Bayesian networks to alleviate the computational challenges associated with optimization tasks in complex datasets. Through a case study, we apply the algorithm to optimize medication prescriptions for diabetic patients, who have different characteristics, suffer from multiple comorbidities, and take multiple medications concurrently. In particular, we demonstrate how the optimal combination of diabetic medications can be found by examining the comparative effectiveness of the medications among similar patients. The case study is based on 5 years of data for 19,223 diabetic patients. Our results indicate that certain patient characteristics (e.g., clinical and demographic features) influence optimal treatment decisions. Among patients examined, monotherapy with metformin was the most common optimal medication decision. The results are consistent with the relevant clinical guidelines and reports in the medical literature. The proposed algorithm obviates the need for knowledge of the whole Bayesian network model, which can be very complex in big data problems. The procedure can be applied to any complex Bayesian network with numerous features, multiple decision variables, and a target variable.