Using Artificial Intelligence to Improve the Accuracy of a Wrist-Worn, Noninvasive Glucose Monitor: A Pilot Study.

BACKGROUND: Self-monitoring of glucose is important to the successful management of diabetes; however, existing monitoring methods require a degree of invasive measurement which can be unpleasant for users. This study investigates the accuracy of a noninvasive glucose monitoring system that analyses spectral variations in microwave signals. METHODS: An open-label, pilot design study was conducted with four cohorts (N = 5/cohort). In each session, a dial-resonating sensor (DRS) attached to the wrist automatically collected data every 60 seconds, with a novel artificial intelligence (AI) model converting signal resonance output to a glucose prediction. Plasma glucose was measured in venous blood samples every 5 minutes for Cohorts 1 to 3 and every 10 minutes for Cohort 4. Accuracy was evaluated by calculating the mean absolute relative difference (MARD) between the DRS and plasma glucose values. RESULTS: Accurate plasma glucose predictions were obtained across all four cohorts using a random sampling procedure applied to the full four-cohort data set, with an average MARD of 10.3%. A statistical analysis demonstrates the quality of these predictions, with a surveillance error grid (SEG) plot indicating no data pairs falling into the high-risk zones. CONCLUSIONS: These findings show that MARD values approaching accuracies comparable to current commercial alternatives can be obtained from a multiparticipant pilot study with the application of AI. Microwave biosensors and AI models show promise for improving the accuracy and convenience of glucose monitoring systems for people with diabetes.

An Uncontrollable, Aggressive Patient at a Free-Standing Emergency Department.

We present the case of an aggressive male patient who was unable to be successfully sedated with conventional medications in the ED and ultimately required intubation to ensure the safety of the patient himself and the staff. After admission to the ICU, he was found to have atrophy of the frontal and bilateral lobes secondary to a traumatic brain injury (TBI) 19 years prior. Managing the patient required collaboration with the intensivist, hospitalist, and psychiatry and neurology teams for 10 months, and he was refused admission to multiple psychiatric facilities due to safety concerns because of his high level of aggression and unpredictability. An out-of-state, high-security facility eventually accepted the patient. The second challenge was finding a highly trained medical team willing to transport the patient. This case illustrates the difficulty and safety concerns with regard to managing an aggressive patient with previous TBI when the commonly used medications do not produce the desired effect. A literature search did not reveal a standard protocol or consensus on managing these types of patients in emergent situations.