Over time, Artificial Intelligence (AI) has shifted from simple algorithms, which rely on programming rules and agent logic, to Machine Learning (ML) solutions. On the one hand, algorithms contain few rules. On the other hand, the same algorithms ingest training data, from hospitals, to learn by trial and error. Characterizing ML behavior.
Machines could be able to integrate a large amount of patient data, but the problem is when and where. As well as, under which clinical circumstances, in a patient, two patients, or three patients or no patient at all. Clinicians are different in their mental state during patient diagnosis. How to program the clinical and workflow changes under different circumstances into AI? And how AI could learn from clinicians? How much power (i.e., patient data) should the computer need? [DOI: 10.13140/RG.2.2.11112.83207]
I interpret AI as deep learning. Neural network are application of Bayesian statistics. It refines the hypothesis from many. AI can identify some diagnostic. However, our body is not like a computer. Often elements are not as straightforward or logical ... So, we need to talk about AI/ML to extend knowledge and human intelligence. .. As long as we can explain its mechanism and validate it against the data.
Preprint Intellectual activity, knowledge, information, data... An at...
Most AI algorithms learn from the past, i.e., according to diagnoses given by the experts themselves. In this sense, AI isn't meant to replace the expert, but to support and help in decision making.
- Badges
- Science topic
- Similar topics
- Psychology
- Mental Processes
- Learning