Can Critical Care Analytics Overcome Ethics Concerns?


In the 1990s, I worked for a company named APACHE Medical Systems. (It is now named APACHE Outcomes.) APACHE was an acronym for Acute Physiology and Chronic Health Evaluation. This tool was designed to measure the severity of disease for adult patients admitted to intensive care units. In effect, we developed systems designed to predict the clinical outcomes for ICU patients. The software was a decision support package that gave health care providers and financers risk-adjusted predictive analytics on mortality, length of stay, the amount of resources needed to sustain life, etc. The premise was that by using patient data based on ICU health status, then families, physicians and insurers would have an idea of whether continuing treatment of the ICU patient would result in a viable-life outcome.

(Image: ESB Professional/Shutterstock)

(Image: ESB Professional/Shutterstock)

The unique thing about this system was that it was like a prism; what you thought of it depended on the angle from which you examined it. From the perspective of a developer, this was a great piece of software. You input patient demographic information, severity of injury and physiological measurements and you get a pretty reliable statistical result of what the clinical outcome would be. From the perspective of a shock trauma nurse or surgeon, the software helped you to design the best treatment of care with a minimum amount of information needed, in the shortest period of time. From the perspective of the insurers, it allowed one to know the whether the costs of sustaining the patient would result in the benefit of recovery. Without a question, this was a great piece of critical care software; this was applied analytics at its best.

But let's think about this from another perspective -- it is your loved one that is the object of critical care analysis. There is an algorithm in the background informing opinions on whether efforts should be exerted to save your loved one's life. Let's consider the following scenario:

Your 84-year-old diabetic mother was driving when her glucose level dropped. She passed out and drove into a tree. You arrive at the hospital, contact her primary physician and give the attending physician her background information. Your family history detail states late-onset diabetes in prior generations with an average life expectancy of 86 years. Her blood test shows a low white blood cell count, which might be a viral infection or acute leukemia. The nurse has entered all of the information into the critical care analytics system so that the attending physician can recommend recovery, palliative or hospice care. The question in your mind is "Will they do enough?"

The question in the mind of the health care providers is "Are we doing what is right?"

The questions in the mind of the insurer are "Are they doing more than what is necessary? Will the patient have an unreasonable length of stay? Do we have to reimburse every line item used in this episode of care?"

With this being your personal scenario, the 'cool factor' of the software is overshadowed by the fact that a human life depends on the precision of the calculations and the accurate interpretation of the results. The public popularity of the software is dwarfed by the fact that the work for which someone received a 'Good Job Award' may lead to a decision to end the life of your mom. Your impartial and dispassionate use of analytics will be forgotten when you are told that choices about your mom's care will be based on a regression model that you neither designed nor tested. In that moment, your profession just got real.

So in that light:

  • Are you willing to trust software developed by an analytics peer unknown to you?
  • Does having a personal stake in a patient's outcome make it easier or harder for you to be an advocate for critical care analytics?
  • Should software be used as a decision support tool in matters of life and death?

Please share your thoughts.

Bryan Beverly, Statistician, Bureau of Labor Statistics

Bryan K. Beverly is from Baltimore. He has a BA in sociology from Morgan State University and an MAS degree in IT management from Johns Hopkins University. His continuing education consists of project management training through the ESI International/George Washington University programs. He began his career in 1984, the same year he was introduced to SAS software. Over the course of nearly 30 years, he has used SAS for data processing, analytics, report generation, and application development on mainframes, mini-computers, and PCs. Bryan has worked in the private sector, public sector, and academia in the Baltimore/Washington region. His work initially focused on programming, but over the years has expanded into project management and business development. Bryan has participated in in-house SAS user groups and SAS user group conferences, and has published in SAS newsletters, as well as company-based newsletters. Over time, his publications have expanded from providing SAS technical tips to examining the sociological, philosophical, financial, and political contexts in which IT is deployed. He believes that the key to a successful IT career is to maintain your skills and think like the person who signs your paycheck.

Regulatory Oversight vs. Crowdsourcing: The Best Approach for Quality

If you are looking for data quality, should you rely on professionals or passionate amateurs? Here are the pros and cons.

Work/Life Balance: Do Analytic Professionals Have It?

You use analytics in your career, but do you also apply the same principles and tools to your personal life?


Re: Sickening future
  • 1/23/2017 10:34:00 AM
NO RATINGS

@Seth that's one of the questions that comes up in the book Less Medicine More Health. The author, a doctor, says that we have to accept that death is inevitable for all. He also declares that we should question the assumption that the goal should always be to prolong life. Howevr, he doesn't give set guidelines and indicates that the individual should make his/her preferences known. That was the case for his father who contracted colon cancer at 60, did ony one round of treatment, and then made the conscious decision to die peacefully at home with his pain minimized as much as possible. His mother made it to 90, though she was clear about her own preferences and even joined the Hemlock Scoiety. She ultimtely died of pneumonia.

Re: Sickening future
  • 1/23/2017 10:30:17 AM
NO RATINGS

@Seth exactly, and if you were willing to do that for pets, think about how much more people would od so for family.  And I do know people who have spent thousands on their dogs' surgeries only to have to have them put down a short time later because the dogs are suffering.

Re: Sickening future
  • 1/22/2017 7:45:04 PM
NO RATINGS

I find it odd that people here have talked about the family, doctors and insurance company but no one has talked about what the patient wants.   Without that we are essentially talking about death panels.  

Having worked in a hospital for years I can tell you with certainty that their are family members who want to pull the plug asap for financial reasons.  What is a necessary part in making an ethical decision is to have a patients DNR, partial DNR, or the request to do everything possible to keep them alive. 

Re: Sickening future
  • 1/22/2017 7:37:20 PM
NO RATINGS

@ Ariella -  You're speaking (or should I say writing) to someone who shelled out $500 twice to have tumors removed from my pet rats.  I could easily have just bought a new pet for $6 but it is about the relationships. 

Re: Sickening future
  • 1/9/2017 7:12:30 PM
NO RATINGS

@PC, you raise an interesting point. In term of 'programs', there is the problem with administrative costs. If a program designed to improve quality of life or outcomes has an overhead percentage of 50% or more, then you have a situation where you have to ask some REALLY tough questions. When discussing the cost of care to save a life, you hope that you are paying for direct costs. But providers also have to make money for the hospitals (especially if they specialize in expensive procedures). And if the hospital has been losing money in unreimbursed expenses, it will make it up somewhere else. In short, the true cost of saving a life is not clearly defined and may be a moving target, based on whether the hospital is losing money. A program is a good way of sheltering indirect costs. Very astute observation!

Re: Sickening future
  • 1/9/2017 6:26:02 PM
NO RATINGS

Most people who have significant direct experience with a special ed child will tell you that every single child has a way to bring joy. And the minority who can't see this; who can't see the dignity of children who are 'limited', probably have a longer mental list of 'people who don't deserve to live'.

Life is priceless. But that doesn't mean we spend infinite amounts of money on esoteric programs that might add a minute to someone's life sometime in the future.

A Little Dirty Hospital Secret - It Matters Where A Person Dies in a Hospital
  • 1/8/2017 2:20:32 AM
NO RATINGS

One use of the APACHE Analytics that I did not mention is that, for business reasons, it matters where a person dies in a hospital. Hospitals have different business units and cost centers (emergency, ICU, surgery, X-ray, etc.). Survival rates are important for marketing and insurance purposes, From a business perspective, the APACHE Analytics not only inform decision makers if it is worth spending dollars to treat someone whose death may be imminent, but it also means that the patient can be moved out if the ICU before s/he dies. A patient who dies in a step down unit (non emergency but still needing care) or a patient who is discharged to die at home or in a hospice, would not be counted as an ICU failure. Some of the major hospitals make money from folks from Saudi Arabia and other nations who get care in the USA because they expect to survive. Fatalities count against hospital business units so if decision makers have the analytics to predict outcomes, they can keep the survivors and move the others to other units or move them out of the hospital. In short, there is a business side to health care. Not only the insurance, but each business unit must foster as many success stories as possible because that is how you get more business. No one wants to go to a hospital where you are likely to die. Hence, the APACHE Analytics give hospitals the tools that administrators need to keep insurance costs down and to minimize fatalities in either revenue raising units (like ICUs) or in the hospital as a whole. Hospitals and insurance companies like healthy people or those who can recover from morbid conditions. So please don't find fault with the analytics, these business concerns were there long before the software was developed. This is just the business side of health.

Re: Need a human
  • 1/8/2017 1:56:22 AM
NO RATINGS

@kq4ym, Great idea! One challenge point is that ICU patients are typically there based on an emergency situation. They either go there directly or they were in the hospital and had a sudden change in their clinical conditions. But to your point, any advanced info that could proactively guide the decision making process would be excellent.

Re: Need a human
  • 1/7/2017 5:05:27 PM
NO RATINGS

I would prefer that patients be given the results or as a preventive matter, potential hospital ICU clients should be allowed the benefit of knowing just what are probable outcomes for various treatments and operations. This knowlege would certainly go a ways in making rational choices for those who want to elect no resuscitation orders for themselves and to help families choose treatments when needed on behalf of patients.

Re: Sickening future
  • 1/5/2017 11:05:19 AM
NO RATINGS

@SaneIt As you say, that woud really vary based on the individual. It may also depend on what stage of life they are at. I recall someone saying after his mother died, "The first 80 years were good." The last six were very miserable. In contrast to his father who lived to just over 90 in relatively good health, his mother's end was very difficult, especially for the children who tended to her. So if a person is in a situation like that and had 80 good years and is up for extending life with a lot of pain and suffering, they may opt not to have treatment (though in that case I don't think treatment even came into it). Certain conditions like Alzheimer's still entail an extended period of degeneration, and there's really little one can do to ameleriorate the condition as of now. Still, I think that our society is not ready to just say that these people's lives lose all value.

Page 1 / 3   >   >>
INFORMATION RESOURCES
ANALYTICS IN ACTION
CARTERTOONS
VIEW ALL +
QUICK POLL
VIEW ALL +