The elemental complexity of emergency medical care leads to barriers that must be overcome for meaningful Emergency Medicine Artificial Intelligence (EMAI) to exist. Accurate data extraction is at the core of a successful AI tool.
As EMRs mature, the information contained becomes more trusted. The structured data is relatively easy to extract and subsequently used for standard machine learning or statistical applications. This is illustrated by current claims of EMAI use, which in reality is little more than analysis of the structured EMR data.
The bulk of the acute care information is unstructured data buried in the text of the history, exam, and medical decision-making portions of the patient chart. The successful application of natural language processing (NLP) extraction is where an EMAI goes from a limited use tool to a truly invaluable augmented decision-making instrument.
Further, Integration of the individual patient data with patient records from the vast pool of patients within the health system, along with millions of patient records worldwide, further adds to the power of an EMAI tool. Both rare and common conditions coupled with the unique characteristics of the patient suddenly finds commonalities in an artificial brain containing other similar patients.
The impact of Emergency Medicine Artificial Intelligence (EMAI) in the emergency department
EMAI begins assisting the emergency medicine provider and improve emergency department (ED) workflow from the moment initial patient contact occurs and data is gathered.
As the ED evaluation proceeds, the synthesis of thousands of data sources results in appropriate triage, reduction in initial exam times, the development of comprehensive focused differentials, directed evaluations, diagnoses and treatment plans.
All of this results in reduced morbidity and mortality. Unnecessary testing and treatments are reduced, while data that can be overlooked the clinician is incorporated into the care plan.
The results are accurate primary and secondary diagnoses, treatments, and disposition.
Although the ED is an environment that is ripe for human error and limitations, it is most amenable to AI.
Current EMAI is being developed that takes advantage of the vast quantities of EMR data, practice guidelines, and current research.
The incorporation of unstructured data through the use of NLP from EMR data with clinical treatment information is the basis of a meaningful EMAI that allows for augmented clinical decision making resulting in improved efficiency and improved care.
Whether the emergency department is rural, urban, academic or community, the care becomes standardized and more comprehensive through the application of the EMAI tool.
Rourke M. Yeakley, MD, MHA
Board certified and practicing emergency medicine physician for over 15 years. Founder of Precision EM. Medical Director, Air St. Luke’s since 2007. Boise Regional Dean for Pacific Northwest University of Health Science. Clinical faculty at the University of Washington School of Medicine. Inventor of the Avepax medical device for single dose delivery of liquid medications, vaccines and nutritionals that are mixed at the point of care. Seven patents have been issued worldwide for this device.
Mayur Saxena, Ph.D
Healthcare strategy enthusiast || Passionate for artificial Intelligence implementations on noisy datasets ||Always curious about B2B technology strategy || Healthcare market and policy dynamics