Artificial Intelligence and Its Integration with Regenerative Medicine Approach

Basics Of Artificial Intelligence

AI is not a single technology, but rather a combination of several interlinked modalities (Figure 1). Although most technologies could be related directly to the healthcare industry, the processes and tasks they support vary considerably (Howard, 2019). Machine learning (ML) currently dominates AI research in medicine. This is mostly because ML can be applied to a wide range of complex tasks, such as assisting physicians with disease diagnosis and personalizing treatment for each patient. A key characteristic of ML is its capacity to “learn and apply” acquired knowledge to similar situations by using various algorithmic methods (Chen & Decary, 2020; Howard, 2019).

Figure 1.

Common technologies involved in the AI field

Source: Author’s creation

Since ML can process vast quantities of digital data, prediction tools are the most extensively used and studied methods in the healthcare sector. In the classical model, ML can be divided into task-driven Supervised Learning (SL) and data-driven Unsupervised Learning (UL). Whilst SL deals with predictions and prediction models (pre-categorized data), UL is involved with pattern and structure recognition (unlabeled data) (Serey et al., 2021).