Page 62 - GTM-2-4

Global Translational Medicine Epigenetics on cardiovascular diseases

at the whole-body status. They propose the Manifold
Epigenetic Model (MEMo) as a conceptual structure to
interpret epigenetic memory emergence and consider
strategies to exploit body-wide memory. The emerging
field of regenerative medicine is based on the epigenetic
memory extending in tissue engineering, the development
of biomaterials, medical devices, and artificial organs,
while cellular therapies are promising for the treatment of
CVDs, diabetes, corneal blindness, and cystic fibrosis [150] .
HF is also a complex clinical complication, the outcome
of many different CVDs affecting the myocardium and
eventually ending up with a common clinical picture.
Pattini et al. [151] analyze the different periods of HF
deterioration through the multistage approach of systems
medicine. Furthermore, pursuing deterioration from one
stage to another, they explore how the SB perspective
and functional genomics transform the clinical approach Figure 6. Schematic diagram based on the SB concept illustrating
toward diagnosis and treatment. communication (links and data transmission) between subclinical and
clinical stages of chronic complex CVDs. This communication concept is
Green [152] argues that the diversification of models intricately connected to data transmission (SB holistic principle) and AI,
and their respectively dissimilar epistemic objectives are with a specific focus on human medical data (Adopted from Lourida and
significant for emerging intelligible scientific theories. Louridas with modifications).
[12]
However, more expertise is required to understand how Abbreviations: AI: Artificial intelligence; CVDs: Cardiovascular diseases;
SB: Systems biology.
the synergy of various epistemic areas, such as SB, can
give rise to and sustain new entities in science. Green and
Andersen [153] debate that scientific co-operation between clinical outcomes and reshaping healthcare practices by
the two fields of research, epigenetics (experiments) and integrating clinical cardiology with information derived
SB (theoretical modeling), is needed for the productive from epigenetic sources.
implementation of SB holistic thinking in epigenetics It is imperative to use AI for integrative network analysis
research. It should overcome the impediment that exists to extract electronic health records by incorporating
between SB and epigenetics scientists due to information diverse data references, uncovering individual patient-
boundaries and segregated research. Presenting and related modes of disease progression. This incorporation of
elucidating the disciplinary experience for the different clinical data necessitates appropriate computer algorithms
views can benefit interdisciplinary cooperation in for risk classification and the prediction of therapeutic
science [153] . clinical effects and after-effects. Developing a new culture

5.1. Artificial intelligence and epigenetics of openly sharing data making datasets and clinical
study reports accessible to others is essential. Perhaps,
Artificial intelligence, developed at the intersection of the interrelationship and interconnection between
technology and medicine, has swiftly integrated into disease networks of epigenetics with networks of clinical
medicine through digital health applications. Its goal is to progression, prediction, and prevention hold the key to
make medicine more precise and error-free (Figure 6). understanding the complex atherosclerotic CVDs . The
[12]
Thus, the rapid integration of AI into medicine analysis and clarification of complex diseases’ biological
increases the prospect of enhancing clinical outcomes and and clinical networks and the expansion of data standards
transforming healthcare practices. AI not only improves could be achieved through AI. Encouraging data standards
the quality of life and home medical care but also elevates and sharing will enhance the integration of clinical and
daily clinical cardiology practices, enhancing medical or non-clinical data, leading to the development of effective
clinical information from cardiac imaging to informed AI tools [154] . AI has the potential to lead the way in
clinical decisions. The capacity of AI to collect, analyze, subsequent medical innovation and upgrade precision
and integrate electronic data from “omics,” epigenetics, medicine to differentiate patients with different phenotypic
and clinical sources is significant for understanding characteristics. However, its usefulness is impeded by
the complexities of chronic CVDs at the individual obstacles such as an absence of adequate algorithms, a
level. Clinical AI holds the promise of improving shortage of physician training, fear of over-mechanization,

Volume 2 Issue 4 (2023) 13 https://doi.org/10.36922/gtm.1868