Affiliation:
1. Central Michigan University, USA
Abstract
In an era where health organizations are constantly striving to increase the quality of care amidst significant challenges, such as the recent pandemic, the development of clinical decision support systems (CDSS) can make contextually relevant predictions that can contribute to more efficient and safe health systems. This chapter outlines the conceptual design principles for data-driven clinical decision support systems. It starts by explaining to the reader the user setting and healthcare data use characteristics to discuss 11 principles and considerations for designing contextually data-driven models for clinical decision-making. The chapter was written to be comprehensive to a wide range of audiences and is meant to be enjoyable for readers without an extensive background in data science.
Reference38 articles.
1. Time Complexity Analysis of Support Vector Machines (SVM) in LibSVM
2. Evidence-based medicine as Bayesian decision-making
3. AsohH.AkahoM. S. S.KamishimaT.HasidaK.AramakiE.KohroT. (2013). An application of inverse reinforcement learning to medical records of diabetes treatment. Semantic Scholars.
4. Bennett, C., Doub, T., Bragg, A., Luellen, J., Van Regenmorter, C., Lockman, J., & Reiserer, R. (2011, July). Data mining session-based patient reported outcomes (PROs) in a mental health setting: toward data-driven clinical decision support and personalized treatment [Paper Presentation]. Healthcare Informatics, Imaging and Systems Biology (HISB), San Jose, CA, United States.
5. Artificial intelligence framework for simulating clinical decision-making: A Markov decision process approach