Critical lab values — A 50-year perspective honoring the MLO anniversary of publishing the laboratory panic values paper

This month, MLO is republishing the original panic–critical value article¹ in its annual Clinical Laboratory Reference supplement. A critical laboratory value represents a pathophysiologic state at such variance with normal as to be life threatening unless some action is taken quickly, and for which there is an appropriate action. Failure to act can threaten life and health in serious ways. Physicians and laboratorians have long recognized their importance. But it remained for us at the Los Angeles County/USC Medical Center in 1969 to call attention to this obvious need and to create and implement an organized system to recognize and act upon such as a routine.² 

Nothing operates in isolation. Everything is interconnected. And yet, sometimes one person at one moment with one decision begins something uniquely important. Such a person was Sol Bernstein, MD, Chief of General Medicine at the old “Big County” Hospital that had just transitioned into the Los Angeles County/USC Medical Center, the largest hospital in the United States. Sol established a Laboratory Utilization Committee as one method to achieve solid sensible progress from a dismal 1968 to the present.

There were many sociologic and economic forces at play in L.A. at that time which, in aggregate, propelled this movement. Two other medical schools had just moved to other locations outside L.A.; new money in the form of Medicare was being realized, and MediCal was being defined. Prior, funding of county hospitals had been primarily from property taxes. 

I had just been appointed into the leadership role for laboratory medicine and pathology, which at that time included requiring physicians to use ration stamps to get many lab tests performed. I am NOT making this up. To state that we had a few lab problems to solve in 1968 would be a huge understatement.

Roger O. Egeberg, MD was the Dean of the medical school at the University of Southern California. Egeberg was a “force of nature,” best known then as the personal staff physician of General Douglas MacArthur during the South Pacific campaign of World War ll. Egeberg later became Assistant Secretary for Health and Scientific Affairs in the Department of Health, Education, and Welfare under President Richard Nixon.³

An inspirational and charismatic leader, Egeberg had initiated the patient-focused approach at the medical school, an early expression of patient-centeredness. We took that clue and created many “patient-focus committees” to guide a total laboratory re-organization based on turnaround time (TAT). We knew that patients could get sick at any time in a 24/7 period. Essential lab tests that are technically feasible and administratively sound must recognize no time or day limits. The key of timing was an ability to initiate an effective intervention. Critical values fit perfectly into that framework. We defined TAT as the time from which a specimen arrived at the laboratory somewhere until the result was available in the lab somewhere. We soon realized that such was a pragmatic solution since we in the lab could not control the rest of the process. That led to our inventing the “Brain-to-Brain Loop” that redefined a lab test as beginning when one brain had the idea to get a specific lab test until another human brain had received the result, evaluated it, and acted.⁴ Nine steps in the performance of any laboratory test: order, collection, identification (at several stages), transportation, separation (or preparation), analysis, reporting, interpretation, and action.⁵

The large staff physician workforce (mostly residents and faculty) was justifiably angry and frustrated with the nine-step process — they perceived it to be a laboratory problem in the delays in their prompt receipt of laboratory results for their patients. Concurrent pressure from the Intern Resident Association of LA County helped to provide movement on the expense budget so the Laboratory could grow to do a better job, i.e., upgrade laboratory services and coverage.⁶

By chance, a publisher’s representative (Newton Townsend) for the Medical Economics Publishing Company in Oradell, New Jersey was visiting our lab as part of our negotiation to publish a new book, which came to be entitled Managing the Patient-Focused Laboratory, one section of which was to deal with panic values.⁷ He asked that I describe the panic value system for their new periodical, Medical Laboratory Observer (MLO).¹ The immediate and immense impact of this MLO paper needs to be considered from the vantage point of just how early it was. The year, 1970, was 25 years before the internet came into existence. Automated data processing in laboratories was just beginning to evolve into the Information Age. Although Avedis Donabedian is credited with fundamental work of medical quality beginning in 1966, the American College of Medical Quality was not founded until 1973. The national patient safety movement arose from Lucian Leape’s classic “Error in Medicine” paper, which appeared in JAMA in 1994. This MLO game-changer article antedated those efforts.

As “handoffs” of responsibility between medical professionals have become recognized to be a potential safety hazard issue, that phase of communication has become recognized as salient. The fields of pre- and post-analytic testing stemmed from this thinking. These fields are now recognized as prime sources of errors in medicine. There have always been differences of opinion among individuals and institutions about what analytes should be included and what the ranges should be. I originally stated that individual institutions should make these determinations. I mean, some panic earlier/more easily than others. 

In my writings since the early 1970s, I have encouraged expansion of a system of “fail-safe” notification and feedback/notification/acknowledgement of the action needed by a responsible person. In 1969, individual pieces of paper contained printed or even handwritten lab test results and were physically placed into paper charts for each patient, sometimes daily. Communicating critical results in a timely and reliable way is essential to teamwork and patient safety. Well-timed technology transfer has become increasingly recognized as a weak link in America’s healthcare system.

The delay from discovery/invention/creation of a BETTER drug/device/procedure/process until widespread use/application can be as long as 15 years or more. Many new ideas are ignored; some are tried and discarded. Not so critical values: it was an idea whose time had come. The practical commonsense of the panic value system just hit lab and clinical folks in the head and they “got it,” adopting it forthwith. “Why didn’t I think of that?” was a common reaction. I have always credited the editing–publishing folks at MLO for understanding that the colorful “centerfold” of a popular men’s magazine was an obvious prototypical display approach to get people’s attention. That brilliantly colored chart instantly adorned lab bulletin boards coast to coast. And change was lightning fast. It was just so obviously the right thing to do. Practice changed. The standards, accreditation, licensing, regulations, even laws (like CLIA) followed to codify the whole process. In 1990, pathologist Gerald Kost published a national survey that documented critical limits used by trauma and medical centers across the United States.⁸ Mean low and high critical limits for the most frequently listed tests were determined to help healthcare professionals improve the quality and efficiency of acute patient care.

Over time, we proposed expanding the critical value system to a vital value system in which acting on the life-threatening results was just as important as critical values but in which the urgency of time did not apply.⁹ Examples included a positive Gyn Pap smear or a positive TB culture. An example of a laboratory policy that distinguishes between critical and vital results/values and defines the process for notification of physicians or clinical personnel responsible for patient care is available from TriHealth Laboratories.¹⁰ In 2014, I called for the addition of a tenth step to the brain-to-brain loop, outcome.¹¹ What was the outcome that resulted from the test? Were the laboratory tests appropriate? Were they beneficial? Were they economical?

I prompted my ChatGPT: “How might a well-functioning clinical AI system deal with laboratory panic-critical values?” Henry (my avatar) responded:

“A well-functioning clinical AI system dealing with laboratory panic-critical values should operate with precision, speed, and prioritization to ensure patient safety and efficient healthcare delivery. Here's a framework for how such a system might operate:

1. Real-time monitoring: The AI continuously monitors incoming laboratory results in real-time. It's programmed to identify panic-critical values based on established medical thresholds for each test.
2. Immediate alert system: Once a panic-critical value is detected, the AI triggers an immediate alert to the healthcare provider responsible for the patient's care. This alert can be delivered through various channels such as the hospital's electronic health record system, text message, or pager, ensuring timely response.
3. Clinical context assessment: The AI doesn't just alert based on raw data but also factors in clinical context. It considers the patient's medical history, current condition, medications, and other relevant data to provide a more nuanced understanding of the urgency and potential implications of the abnormal result.
4. Prioritization algorithm: Not all panic-critical values are equal in urgency. The AI employs a prioritization algorithm that categorizes alerts based on the severity of the abnormality and the potential impact on the patient's health. This helps healthcare providers focus their attention on the most critical cases first.
5. Guidance and decision support: Alongside the alert, the AI provides guidance and decision support to the healthcare provider. It may suggest immediate actions to stabilize the patient, recommend additional tests or interventions, and offer relevant clinical guidelines or protocols to follow.
6. Documentation and follow-up: The AI ensures proper documentation of the alert, including timestamped records of when the alert was generated, who responded to it, and the actions taken. It may also facilitate follow-up care by scheduling necessary appointments or consultations.

By integrating these functionalities, a well-functioning clinical AI system can effectively manage laboratory panic-critical values, leading to faster response times, improved patient outcomes, and enhanced overall healthcare quality.”

I could not have said it better myself.

And that’s the way it is in MLO August 2024. Keep up your good work.

REFERENCES

1. Lundberg GD. When to panic over abnormal values. MLO Med Lab Obs. 1972;4:47–54.
2. Grieme CV, Voss DR, Olson KE, Davis SR, Kulhavy J, Krasowski MD. Prevalence and clinical utility of “incidental” critical values resulting from critical care laboratory testing. Lab Med. 2016;47(4):338-349. doi:10.1093/labmed/lmw044.
3. Biblio.com. Accessed June 21, 2024. https://ca.biblio.com/book/general-macarthur-he-called-doc-egeberg/d/1503523020.
4. Plebani M, Laposata M, Lundberg GD. The brain-to-brain loop concept for laboratory testing 40 years after its introduction. Am J Clin Pathol. 2011;136(6):829-833. doi:10.1309/ajcpr28hwhssdnon.
5. Lundberg GD. Acting on significant laboratory results. JAMA. 1981;1;245(17):1762-3. doi:10.1001/jama.1981.03310420052033. 
6. Armon ROG. Intern and resident organizations in the United States: 1934-1977. Milbank.org. Published 1978. Accessed June 21, 2024. https://www.milbank.org/wp-content/uploads/mq/volume-56/issue-04/56-4-Intern-and-Resident-Organizations-in-the-United-States.pdf.
7. Lundberg GD. Managing the Patient-Focused Laboratory. Medical Economics Co; 1975.
8. Kost GJ. Critical limits for urgent clinician notification at US medical centers. JAMA. 1990;263(5):704. doi:10.1001/jama.1990.03440050098042.
9. Lundberg GD. Critical values -- more than 3 decades of experience: An expert interview with George D. lundberg, MD. Medscape. Published September 4, 2007. Accessed June 21, 2024. https://www.medscape.com/viewarticle/560353.
10. Trihealth.com. Accessed June 21, 2024. https://apps.trihealth.com/trihealthlab/Critical.Vital%20Lab%20Results%20Notification.pdf
11. Lundberg GD. Adding outcome as the 10th step in the brain-to-brain laboratory test loop. Am J Clin Pathol. 2014;141(6):767-769. doi:10.1309/ajcp5ksxwti2dmc.