Commercial applications of artificial intelligence and machine learning have made remarkable progress recently. Meanwhile, much of the public and, of course, the medical community are aware that the physician shortage is worsening, including anesthesia specialists.
There are currently about 30,000 anesthesiologists practicing in the United States, down from 35,000 in 2011. By the end of 2020, the shortage of anesthesiologists is expected to grow to 12,500. While artificial intelligence and machine learning has been advancing in medical fields, the practice of anesthesiology embodies a requirement for high reliability, and a pressured cycle of interpretation, physical action, and response rather than any single cognitive act. Research has identified six areas of possible applications for artificial intelligence in anesthesiology:
- Depth of anesthesia monitoring
- Control of anesthesia
- Event and risk prediction
- Ultrasound guidance
- Pain management
- Operating room logistics
While the human mind excels at estimating the motion and interaction of objects in the physical world, at inferring cause and effect and at extrapolating those examples to determine plans of action to cover previously unencountered circumstances, fatigability presents a tendency to short-cut mental work. The human mind can become slow and error-prone at performing even straightforward arithmetic or logical reasoning.
In contrast, a computer can rapidly retrieve and process data from 32 gigabytes of internal memory—a quarter of a trillion discrete bits of information—with absolute fidelity and tirelessness, given an appropriately constructed program to execute.
Anesthesia specialists have long relied on personalized streams of quantified data to care for their unconscious patients, and advances in monitoring and the richness of that data have underpinned the dramatic improvements in patient safety in the specialty. The specialty of anesthesiology actually features a broad history of attempts to apply computational algorithms, artificial intelligence, and machine learning to tasks in an attempt to improve patient safety and anesthesia outcomes.
Impact on the Quality of Care
The lack of physician anesthesia providers is likely to have a dramatic impact on the quality of health care in this country. Without qualified anesthesiologists, many critical surgical procedures may be delayed or even performed under the supervision of CRNAs, rather than medical doctors.
Assistance with artificial intelligence has the potential to impact the practice of anesthesiology in aspects ranging from perioperative support to critical care delivery to outpatient pain management. Once implemented properly, this should provide some relief for the many over-worked anesthesia specialists.
The most plausible route to the introduction of artificial intelligence and machine learning into anesthetic practice is that the routine intraoperative management of patients will begin to be handed off to closed-loop control algorithms. Maintaining a stable anesthetic is a good first application because the algorithms do not necessarily have to be able to render diagnoses, but rather to detect if the patient has begun to drift outside the control parameters that have been set by the anesthesiologist.
A closed-loop control system need not necessarily have any learning capability itself, but it provides the means to collect a large amount of physiologic data from many patients with high fidelity, and this is an essential precursor for machine learning. Access to large volumes of high-quality data will enable more machine-learning successes. For now, finding algorithms that provide good clinical predictions in real time should be emphasized. Management of all the parameters of a stable anesthetic is not a simple problem, but embedding the machine in the care of the patient is a good way to begin.
With the demand for anesthesiology specialists only growing in the coming years, it seems that it is just a matter of time for artificial intelligence and machine learning to be an important factor for the practicing anesthesiologist. Perhaps decision-making behaviors can emerge from simple equations where machine learning might help solve them, thus bringing anesthesiology into an era of machine-assisted discovery.
Artificial Intelligence and Machine Learning in Anesthesiology. anesthesiology.pubs.asahq.org
The Shortage of Anesthesiologists is Quickly Approaching a Crisis. onyxmd.com