The Real Era of the Art of Medicine Begins with Artificial Intelligence

Abstract

Physicians have been performing the art of medicine for hundreds of years, and since the ancient era, patients have turned to physicians for help, advice, and cures. When the fathers of medicine started writing down their experience, knowledge, and observations, treating medical conditions became a structured process, with textbooks and professors sharing their methods over generations. After evidence-based medicine was established as the new form of medical science, the art and science of medicine had to be connected. As a result, by the end of the 20th century, health care had become highly dependent on technology. From electronic medical records, telemedicine, three-dimensional printing, algorithms, and sensors, technology has started to influence medical decisions and the lives of patients. While digital health technologies might be considered a threat to the art of medicine, I argue that advanced technologies, such as artificial intelligence, will initiate the real era of the art of medicine. Through the use of reinforcement learning, artificial intelligence could become the stethoscope of the 21st century. If we embrace these tools, the real art of medicine will begin now with the era of artificial intelligence.

A short guide for medical professionals in the era of artificial intelligence

“…When an algorithm using reinforcement learning, thus not being restricted by our human cognitive limitations, comes up with a cure which we could never find with our knowledge about biology, medicine and other life science, the real art of medicine will be to find out and to understand how it did that 35 .…”

The Roles and Modes of Human Interactions with Automated Machine Learning Systems

“…A pioneer of modern reinforcement learning, Richard Sutton, argues in a blog post that "the biggest lesson that can be read from 70 years of AI research is that general methods that leverage computation are ultimately the most effective, and by a large margin" [283]. Certainly, machines are not beset by human cognitive flaws and limitations, nor do they struggle with the same learning curves [196]; again, we emphasise this is in the context of narrowly defined ML problems. Modern computational resources are also vast, even if they fall short of the postulated exaFLOP that a human brain operates at, and leveraging them efficiently/intelligently can achieve significant outcomes.…”

Data Collection in Multiple Sclerosis: The MSDS Approach

“…The coordinated exchange of health-related information is associated with numerous promising opportunities for daily care in clinics and practices supporting decision-making and the treatment process as a whole (10,29). Technologies such as an electronic medical record (EMR) enable the rapid exchange of health information between patients, practitioners, and caregivers, regardless of time and location, with the EMR mainly exchanging data between health professionals in single entities of the health system (4,22,(30)(31)(32)(33). Today, every part of the treatment process-from diagnosis, treatment selection, and application to patient education and long-term care, including drug treatment and rehabilitation-can be complemented by a quality-assured implementation of information technologies in healthcare ("eHealth"), which also takes into account data security standards and concerns (4,34,35).…”