About this Research Topic
The prevalence of chronic conditions increases with age, as does the risk of having two or more chronic conditions which is referred to as multimorbidity. The provision of personalized care to patients with multimorbidity is constrained by the fact that current health care systems and clinical guidelines are single disease-oriented. There is no knowledge base to support decision-making in the context of multimorbidity, by means of providing an integrated view on the problem that is investigated. To do so we need to create a new knowledge base to change the current research paradigm and way of thinking, by moving from dominating reductionist to complex systems based thinking.
Characteristics of multimorbidity, such as disease clustering (non-random associations), overlapping (between individuals), mutual interactions within the common network, and accumulation over time, mean that data used to describe individuals of particularly older populations are complex, by means of high variability, multi-collinearity, and non-linear correlations. Algorithms and tools for machine learning/big data (ML/BD) and AI application are promising methods that can be used to overcome these complexities in multimorbidity. Particularly in the ability of these methods to potentially reveal latent spaces and time trends in the data.
There is not much research into multimorbidity by using multivariate data sets and ML/BD methods. A data-driven decision making support has not become a part of the everyday routine of medical doctors, although an immense amount and different types of medical data are routinely collected and stored in electronic health records and patient registers, and are available for research. The use of ML/BD methods to analyze this data could provide a platform and knowledge base that could be used to support decisions associated with multimorbidity.
The aim of this Research Topic is to promote a new wave of research on multimorbidity that is based on a data-driven research approach, and has potential to be implemented as a part of the workflows of medical doctors.
We also welcome discussions on the need for the paradigm change in the way of scientific reasoning from reductionist to complex thinking, and papers that address the theoretical conceptualization and models of multimorbidity. Authors are encouraged to provide original research and review papers, as well as viewpoints and commentaries.
Characteristics of multimorbidity, such as disease clustering (non-random associations), overlapping (between individuals), mutual interactions within the common network, and accumulation over time, mean that data used to describe individuals of particularly older populations are complex, by means of high variability, multi-collinearity, and non-linear correlations. Algorithms and tools for machine learning/big data (ML/BD) and AI application are promising methods that can be used to overcome these complexities in multimorbidity. Particularly in the ability of these methods to potentially reveal latent spaces and time trends in the data.
There is not much research into multimorbidity by using multivariate data sets and ML/BD methods. A data-driven decision making support has not become a part of the everyday routine of medical doctors, although an immense amount and different types of medical data are routinely collected and stored in electronic health records and patient registers, and are available for research. The use of ML/BD methods to analyze this data could provide a platform and knowledge base that could be used to support decisions associated with multimorbidity.
The aim of this Research Topic is to promote a new wave of research on multimorbidity that is based on a data-driven research approach, and has potential to be implemented as a part of the workflows of medical doctors.
We also welcome discussions on the need for the paradigm change in the way of scientific reasoning from reductionist to complex thinking, and papers that address the theoretical conceptualization and models of multimorbidity. Authors are encouraged to provide original research and review papers, as well as viewpoints and commentaries.
Keywords: Multimorbidity, Comorbidity, Systems Biology, Machine Learning, AI, Big Data, Methods, Disease
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
