|Chapter title||Machine learning in precision medicine|
|Editors||Kumar, P., Kumar, Y. and Tawhid, M.A.|
In recent years, the healthcare industry has made great advancements with the inclusion of poly-omics data, besides the data from traditional heuristic methods. Analyzing this growing multidimensional data is helping to gain knowledge and a better understanding of the disease, i.e., changes or variations in the macro (cellular) to micro (genes/proteins/metabolites) level, which can be correlated to the patient’s phenotype. In particular, this is encouraging for domains like cancer biology, where the underlying causes are complex and heterogeneous. Deciding an appropriate treatment is also challenging for such diseases, as a one-standard-treatment strategy does not fit all patients. Targeted therapies have been trying to address this, but still, there are patient strata who either do not respond or have disease recurrence in a few years.
Precision medicine is trying to address the aforesaid challenges by using data-driven approaches, amalgamating the expertise of bioinformatics, clinical science, and machine learning for making an informed decision(s) including appropriate knowledge and its clinical translation. An overview of how machine learning is used in precision medicine and its potential use in the detection, diagnosis, prognosis, risk assessment, therapy response, the discovery of new biomarkers and drug candidates is discussed in this chapter.
|Book title||Machine Learning, Big Data, and IoT for Medical Informatics|
|Digital Object Identifier (DOI)||https://doi.org/10.1016/b978-0-12-821777-1.00013-6|
|Web address (URL)||http://dx.doi.org/10.1016/b978-0-12-821777-1.00013-6|