Artificial Intelligence in Medicine
Artificial Intelligence (AI) refers to the ability of a computer or computer controlled machine to think and reason like a human. AI is already pervasive in our society, and is mostly famously displayed by the Google driverless cars that travel down the road with no human intervention. Although AI has been slow to work its way into medicine, glucose control in ICU patients represents an excellent opportunity to introduce this technology to the bedside clinician, as the ICU is a highly structured environment with minute to minute oversight provided by the bedside nursing staff.
The AI based Artificial Pancreas system being developed by Ideal Medical Technologies uses software that adjusts the doses of IV insulin/glucose infusing into the patients on an every 5-10 minute basis. This frequency of adjustment was chosen as it mimics the frequency of insulin adjustment used by the native pancreas, and the frequency of glucose output from the liver. In fact, the software attempts to mimic the native pancreas/liver in all respects, from timing of insulin/glucose release to how quickly it can raise or lower its doses of insulin/glucose flowing into the patient based on the glucose dynamics of each patient.
This software was developed by Dr. Leon DeJournett, who is a Stanford trained ICU physician with 30 years of clinical experience. Dr. DeJournett used a thorough review of the native glucose control provided by the pancreas/liver, which has been previously published in a peer reviewed journal, to help him develop the AI based software that is the core of Ideal Medical Technologies AI based Artificial Pancreas system. Ideal Medical Technologies has already successfully tested its Artificial Pancreas system in a large scale simulation study that has been recently published. In addition, it has also successfully tested its system in an animal model of stress induced hyperglycemia, which is what ICU patient’s experience, with the latter study being performed at a major academic medical center. Both of these test results were presented at the 2016 American Diabetes Association meeting.