Computational tools in the assistance of personalized healthcare
Chapter
Overview
Identity
Additional Document Info
Other
View All
Overview
abstract
2018 Elsevier B.V. Process Systems Engineering has been many years in the forefront, advancing the standards in healthcare and beyond. Gradually, integrated methods that utilize both experimental and/or clinical data, as well as in silico tools are becoming popular among the medical community. In silico tools have already demonstrated their great potential in various sectors, assisting the industry to produce experiments of significantly reduced cost that allow thorough investigation of the system at hand. Similarly, in biomedical systems, the advancement of the current state of the art through the development of intelligent computational tools can lead to personalized healthcare protocols. The first part of this chapter serves as a brief review of the computational tools commonly used in healthcare, such as big data analytics and dynamic mathematical models. The challenges characterizing biomedical systems, such as data availability and patient variability, are also discussed here. We present the advantages and limitations of the various methods and we suggest a generic framework for the design and testing of advanced in silico platforms. The PARametric Optimization and Control (PAROC) framework presented here is based on the design of high-fidelity, dynamic, mathematical models that are then validated using experimental and/or clinical data. Such models provide the basis for the execution of optimization and control studies for the design of patient-specific treatment protocols. The final part of the chapter is dedicated to the application of PAROC to three different biomedical examples, namely: (i) acute myeloid leukemia, (ii) the anesthesia process, and (iii) diabetes mellitus. The challenges of each case are discussed and the application of the relevant PAROC steps is demonstrated.
