| dc.description.abstract | The goal of this article is to evaluate how recent developments in fabrication
techniques, genome editing, and machine learning are influencing the future of
cardiac tissue engineering. AI algorithms have been used to diagnose, segment
and reconstruct images, quality control, prognosis, Phen grouping, and scientific
discovery in cardiology. AI is being used to automate electrocardiogram
interpretation and patient categorization and prognosis. ML models can detect
and compute a variety of cardiac parameters, including P and T waves, QRS
complexes, heart rate, cardiac axis, ECG interval lengths, ST-changes, and
common rhythm abnormalities. A 34-layer DNN has recently been developed that
can recognise with more recall a human cardiologist. A variety of machine
learning (ML), including SVMs, gradient boosting machines (GBMs), MLNNs,
it is used to estimate patients' likelihood of experiencing an ischemic stroke.
Transthoracic echocardiography provides instantaneous visualisation of the
heart's structure, allowing for rapid diagnosis of structural abnormalities. An
innovative method for calculating LVEF automatically from 2-D
echocardiographic pictures using AI-learned pattern recognition. CRISPR/Cas9
systems used to design for cell of cardiac, with potential such as enhanced the
avoidance of the body's immunological response. CRISPR/Cas9 technology can
be used to improve cell homing, delete inactive genes, model cardiovascular
disease, reduce immunogenicity, and protect hESC-derived allografts from
immune rejection. | en_US |
