THE BRAVE NEW WORLD OF TELETRIAGE
The work of teletriage is nothing if not uncertain, and humans intensely dislike uncertainty. However, it is reasonable and prudent to acknowledge the limitations of this work, and to question our assumptions about it. Safer practice and evidence-based tools can reduce uncertainty and improve outcomes.
“Triage (on site) is not an endpoint but a beginning.” American College of Emergency Physicians, 1999. Uniform Triage Scale in Emergency Medicine, Information Paper
"Physician expertise and professionalism alone could not prevent common error.” Killip. (2007),
“All learned occupations have a definition of professionalism, a code of conduct. It is where they spell out their ideals and duties. They all have at least three common elements: expectation of selflessness; of skill; and of trustworthiness. Aviators have a fourth expectation -- discipline”. (Gawande, 2010)
‘We don’t look for patterns of our recurrent mistakes or devise and refine potential solutions for them. But we could, and that is the ultimate point”(Gawande, 2010).
“Any mistake or failure in the diagnostic process can lead to a diagnosis that is wrong, missed or delayed. More diagnostic errors occur in ambulatory settings, but inpatient diagnostic errors tend to be more lethal”. Groszkruger, 2014.
Artificial Intelligence — the Wave of the Future in Teletriage
CDSS that employs AI without a governing framework and guard rails - might produce unsafe outcomes.
Errors of Assessment, Communication, Continuity, Informed Consent and Human Error. (Joint Commission) are Root Causes of unsafe outcomes in teletriage. Malpractice cases in teletriage are typically related to these predictable and preventable errors. Human and system error can be addressed by a system —structure and process — a group of related parts that work together for a common goal.
CERNO…..I Perceive - -
Discern – Distinguish – Sift – Separate - Bear in Mind – Reckon – Determine – Resolve – Contend - Decide
“Improved Systems improve safety” Giesen et al., (2011), Annals of Medicine
“If you fail to plan; plan to fail” (IOM)
Does your institution or facility have a formal system? Or is it just “bits and pieces”? The Institute of Medicine defines system error as “failure to use a plan; using the wrong plan; or failure of planned action to be completed as intended”. Institute of Medicine, 2000. [PubMed]
The Future of Teletriage Guidelines & AI
Currently, computerized decision support systems (CDSS) for nurse teletriage lack meaningful evidence that they are reliable or valid. Some CDSS may actually interfere with the decision making process (Wachter, 2017). Other CDSS are confusing, complicated or bloated with high quality patient education material too lengthy for nurses read to patients in the time frame allowed. Many CDSS designs are too unwieldy for research purposes. These features make it difficult to demonstrate that a given CDSS qualifies as evidence-based medicine (EBM).
It is a given that generative AI, predictive analytics, advanced EMRs and biotechnology will be standard components of teletriage soon. In addition, teletriage designs must be elegant, transparent, user-friendly, seamless and demonstrably reasonably safe (EBM).
The ultimate CDSS will utilize data from generative AI, Predictive Analytics, and relevant EHR data. Later, data from Biotelemetry and Patient Wearables will augment the process of assessment and decisionmaking. Machine learning and planned error recovery will enhance safety and continuous quality improvement. Reduced uncertainty and feedback will enhance clinician job satisfaction.
However, meaningful research on the safety of incorporating advanced technologies into current CDSS is urgently needed. Guard rails are essential for this emerging subspecialty.
A Universal Guideline with embedded standardized components — structure and process — will serve as a virtual History and Physical (H & P). Relevant patient “back story” or history (the EMR) - provide context. Essential assessment questions provide data about the chief complaint. AI and predictive analytics supplant the expert physician advisor at the clinician’s side — supporting, reminding and prompting with additional questions. AI/PA can suggest an estimated symptom urgency level - a triage disposition. This remote High-tech H & P — structure, process, outcome — will be transparent, standardized, valid and reliable.