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.

Capta: The Data of Conscious Experience

Phenomenological researchers say "capta" is the "data of the conscious experience." Is there room for this kind of data in analytics? How should analytics pros use it?

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.


Sickening future
  • 1/3/2017 11:21:05 PM
NO RATINGS

It's all elegance and efficiency and savings galore til we insert personal details into the equation -- living, breathing humans, not pallets of merchandise or commodities being shipped around. The calculations at work in this equation may be statstically sound; they are also morally suspect.

Re: Sickening future
  • 1/4/2017 2:08:13 AM
NO RATINGS

@TS, Would you mind elaborating a little please? Whose morals would you deem as suspect - the physicians or the insurers?

Re: Sickening future
  • 1/4/2017 3:57:01 AM
NO RATINGS

..

Especially when issues of life or death, life quality, and the well-being or even survival of loved ones are involved, the separate motivations and interests of medical practitioners and those close to the patient are complicated enough. Adding the interests of profit-oriented private insurance companies into this mix would seem to make the situation even more difficult. 

That said, the analytics approach Brian describes would appear to be helpful, at least for rational medical decisionmaking.

..

Re: Sickening future
  • 1/4/2017 5:55:19 AM
NO RATINGS

You bet, Bryan... it's the insurers, who want to quantify and cost out everything from an aspirin to a CAT scan. We were reminded with the healthcare overhaul how many parts of the system are broken and craven, but these folks lead the pack, in my opinion.

Re: Sickening future
  • 1/4/2017 7:22:01 AM
NO RATINGS

@TS - I agree with you. However in the interests of 'stirring the idea pot' a little, please consider this. If you look through my posts, you will see a piece on The Value of a Statistical Life. The VSL methodology is often used to determine how much a community is willing to spend in new taxes to prevent or eliminate a problem. For example, if tax payers are willing to pay $200 more per person in taxes for abestos removal in a building they want the mayor to sell, in the hope that the additional taxes will reduce the number of deaths by one person, then that puts a dollar figure on how much that community believes each person is worth statistically. While I fully agree with you about the morals of the insurers, I wonder in a broader sense, don't we make the same judgments as tax payers when we say that we will give $200 more per year to reduce cancer deaths attributed to abestos, but not $300? If we ask our municipal executives to settle wrongful death suits because it is less of a tax burden to do that than to spend ten times as much to eliminate the problem, then in that sense, don't we share he same value system as the insurers? If an insurance company says that it will lose money to sustain the life of an elderly person in an ICU, who has a 10% chance of survival - and if we say that we don't want to increase our tax burden more than $200 this year to keep one less person from getting cancer from asbestos in an old building that we want to sell to a company that will bring new jobs to our community, then aren't the value systems/moral foundations/ethical frameworks the same?

Re: Sickening future
  • 1/4/2017 10:57:11 AM
NO RATINGS

@bkbeverly theere are even more questions when you have taxpayers footing the bill for everyone's healthcare, as in the case of the NHS in the UK and socialized medicine in Canada. In the former, there tends to be shortage of hospital beds and major waits for just about all surgical procedures. As for Canada, I have no doubt that the economics of the situation is behind the legalization of assisted suicide. Terminally ill patients would be a major drain on the halthcare system.

Re: Sickening future
  • 1/4/2017 2:05:19 PM
NO RATINGS

..

Ariella writes that


... there are even more questions when you have taxpayers footing the bill for everyone's healthcare, as in the case of the NHS in the UK and socialized medicine in Canada. In the former, there tends to be shortage of hospital beds and major waits for just about all surgical procedures.


 

It's important to understand that Britain's National Health Service once represented perhaps the world's best public health system among countries with capitalist economies. In his documentary film Sicko Michael Moore even focused on it as an example of what a good national health service could offer.

But rising conservative political forces, including within the leftist Labour Party, have systematically underfunded the NHS and slashed services and quality. This process has accelerated with the Conservative Cameron (and now May) regime. Some measure of public concern can be gauged from the fact that a de facto protest against the cutbacks, and in celebration of the NHS, was staged as one of the main performances in the 2012 Olympics in London.

..

Re: Sickening future
  • 1/4/2017 11:03:51 AM
NO RATINGS

@bkbeverly I recall that over 25 years ago when a friend of mine was training to become a nurse, she said that the official direction was to push people to consider "quality of life" and not request extended life support. In that case, they really seemed to believe that it was not just a drain of resources but that life like that is not worth sustaining. It's a tough question, really.

A woman in my neighborhood developed something like ALS, though doctors didn't diagnose it as such exactly. She had been an energetic person, attending the gym regularly and entertaining regularly. She first became ill about 4 or 5 years ago. Then she became weaker and weaker. For the past couple of years, she has been unable to walk. It also takes a great effort to transport her, as she needs to be connected to oxygen. The costs must be very high as the she has two nurses for round-the-clock care, and at least one of them is not covered by insurance at all. Yet her family considers her life worthwhile, and her children and grandchildren (most are not that far away) visit her all the time.

Re: Sickening future
  • 1/4/2017 12:15:04 PM
NO RATINGS

@Ariella, so it sounds like for that family, money was not an object. In that case, love is all that matters. That family is very fortunate. However, in most other cases, there are financial caps. Hence you have to use quality of life to justify spending. Hence when you have unlimited love but limited health care financing, that's when the heart breaking decisions have to be made.

Re: Sickening future
  • 1/4/2017 12:23:00 PM
NO RATINGS

@bkbeverly they're not rich. The only breadwinner now works as an administrator in a university. I'm sure that this is eating up all that they may have saved for retirement. But some people think that you just can't put a price tag on certain things -- and keeping a family member alive and as comfortable as possible woudl be one of them. When people make the decision to let someone die, I doubt they admit that money enters into it. That was the point I was making when I referenced my friend's nurse's training. The medical professionals there really believe it's not worth keeping a person alive in that state. This seeps into different atttitudes you also encounter in hospitals when the patient is young versus when the patient is old. When my son had surgery a few years ago, they kept referencing, "for a young person..." While that was meant to be reassuring, I couldn't help thinking of the flip side: for an older person they would see less of a payoff because the person would naturally have fewer years to live. My husband who enjoys reading books by doctors says that is indeed the case: they are far more motivated for a person who has a natural lifespan of another 50 plus years than for someone who is already past 70.

Re: Sickening future
  • 1/4/2017 3:40:07 PM
NO RATINGS

@Ariella

If one owns a car that requires an expensive repair, it's only natural to think of the car's remaining useful life. Is it worth $2500 to fix the air conditioning in a old car that's only worth $2000 after it's fully working? Probably not. But the same repair for a relatively young $40,000 sports car, is well worth doing.

We generally don't think of people in this way. With people that we know and love, it is not difficult to avoid thinking this way.

 

Re: Sickening future
  • 1/4/2017 6:46:15 PM
NO RATINGS

@PC Indeed, I know of people who would even do that for their pets. Consider, you have a mutt for 6 years that you've come to love, and he needs an operation that will cost you $2,500. If it were purely a question of economics, you could say, I an buy a new mutt for less than $500, so it's more economical to let him die or have him euthanized. But most pet owners would shell out for the operation (unless they are told it will cause the dog undue suffering). Now with people, it would be completely callous to say, save your money, and let your kid die because you always have or adopt another one for far less money. 

One of my cousins had a baby born at about 25 weeks. She was in the NICU for many months, and I have no doubt that the bill topped 6 figures. But what kind of society woudl demand that the baby not receive care and just be allowed to die? She has now been released and is doing well, from what I've been told. I know of another family who had a child born that prematurely. He had to be in special ed classes his whole life, though he is pretty high function. So would we say, he should have been allowed to die to save on costs all around? That is the beginning of the path toward fostering a superior race and weeding out those whose lives we value less -- shade of Nazi ideology there.

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.

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
  • 1/22/2017 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
  • 1/23/2017 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
  • 1/22/2017 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
  • 1/23/2017 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
  • 1/4/2017 2:11:51 PM
NO RATINGS

@bkbeverly, this is a very deep issue and I think a lot of us have trouble removing emotional responses from those business decisions.  In a perfect post scarcity world where we would save everyone that we could possibly save from every disease/injury.  The line drawn to determine the ethical duty to save an individual is not only grey it will shift greatly due to more than just the dollars required for treatment.  $200 in NYC versus $200 in rural Kentucky will mean different things as well. 

 

Re: Sickening future
  • 1/4/2017 3:46:12 PM
NO RATINGS

@SaneIT

Some medical treatments are so expensive, and so fruitless; that if I were a candidate for one myself I would pass.

My Aunt was offered some of these treatments. After careful consideration, she declined and went home to spend her last months peacefully with her family. She might have lived a bit longer with more treatment, but it would have basically taken the life she had. She didn't think it was worth it.

Re: Sickening future
  • 1/5/2017 8:21:01 AM
NO RATINGS

I'm not arguing for assisted suicide here but I don't think treatment is always about money.  I know people who could afford the treatment but didn't have the appetite for months of pain and sickness through a treatment that might not extend their lifespan at all.  Quality of life comes into play and what is an acceptable level of quality will vary from person to person.  I would prefer that we let individuals determine what they think they can handle and if they think treatment is going to worth it but I'm sure self preservation really kicks in for some people and they would insist on every treatment available even though chances of survival are statically zero.

 

 

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.

Re: Sickening future
  • 1/4/2017 4:45:09 PM
NO RATINGS

@SaneIT, so noted! What has pleasantly surprised me thus far has been the responses posted. Analytics professionals who typically are dispassionate on most topics are expressing the conflict between the human aspect and the need for making valid and reliable decision support tools.

Need a human
  • 1/4/2017 5:55:03 PM
NO RATINGS

I think that while the software provides valuable input, you still need a human in the equation. Matters like these will vary person by person, so the averages may not be the est guide.

Re: Need a human
  • 1/4/2017 6:22:29 PM
NO RATINGS

@tomsg - Agreed. The question is who has the dominant voice - the family, the physicians or the medical/health insurers (who control claim reimbursements and payments for medicines and surgery)? In most cases, I am guessing the family has the dominant voice, but I am also assuming that the physicians and providers are totally transparent regarding the options available. In total agreement that the software should only point but not decide.

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: 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.

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.

INFORMATION RESOURCES
ANALYTICS IN ACTION
CARTERTOONS
VIEW ALL +
QUICK POLL
VIEW ALL +