The Central Myth of American Medicine

In recent years, there has been significant progress in trying to predict future disease both by statistical and biological methods.  The combination of genomics and artificial intelligence has proved to be quite powerful in moving us along a path that can drive better disease prediction.  I spend most of my working hours with this effort driven by my assumption that early warning will lead to better interventions to fight disease and ultimately to better health.  But I can’t be 100% sure. What if all those predictions only cause anxiety and confusion? I thought about this as I read an article in the WSJ about too much messaging, coming too early dulling our reactions.  This was in the context of storm prediction but similar principles apply in health and disease.  Ultimately, with both storms and impending illnesses, the questions are all about what can be done to either prevent or at least mitigate the potential catastrophe.   Do you want to be able to plan, to take medication to lower the risk, to change your lifestyle? Or will all that information just create anxiety, depression and contribute to a nihilistic type of fatalism?

In the case of storm prediction, the article pointed out that “More accurate data gives more time for emergency planners and residents in a storm’s potential track to prepare. But the long lead-up also can result in saturation storm coverage and social media hype that leads some people to tune out.”

It goes on to note that “continual storm coverage was a source of annoyance for many and led to fatigue for some, adding to concerns that information overload would lead them to miss key communications.”  The earlier the information is obtained and given, the more likely it is for the information to inform, but also the more likely the information will ultimately be wrong. Time is an important variable, and it has a habit of changing things in the weather as in life.  

Health plans, health systems, private companies, and government are all using huge data bases of claims, medical records, genetic data, and anything else they can find to create algorithms or formulas which can predict our future health.  These efforts are having some success, and as someone who works in this area, I expect our abilities to increase. But will we actually be helping by predicting? Will we be contributing to an unhealthy focus on disease prevention instead of healthy living or to a numbing of a message that change is needed?

The questions we are attempting to answer almost appear to have a biblical quality….Who shall live, and who shall die?  Who shall be infirm and who shall be healthy? I am Jewish and will be stating words very similar to these in the Rosh Hashana and Yom Kippur services which are around the corner.  We say this as we pray for forgiveness and hope that in the coming year we will be blessed with health and happiness. It does seem almost God-like to be able to predict in this way.  But it’s important to remember that our predictions are never 100% accurate, and that even if they are, we don’t really know if the predictions will help or not.

The optimists among us believe that these predictions will allow us to intervene and help prevent the diseases before they appear.  The pharmaceutical companies believe that they can develop medications to forestall and prevent diseases before the illnesses express themselves to the detriment of the patient.  Those in the wellness fields believe that changing lifestyles will forestall the “ultimate decree,” as is said in the prayer book for the High Holiday services.  

But we don’t really know, and we also don’t know if we will just be creating undue anxiety and depression.  We don’t know if we will contribute to information overload that does not really help those we hope to impact most.  We don’t know if our new medications and our new approaches to intervention will ultimately lead to unintended consequences that may be harmful.  

We don’t even know how much people want to know.  We do have experience of a sort from the testing for genetic diseases that offer people some predictability.  Huntington’s Disease is a genetic illness and was one of the first genetic diseases for which there was a definitive test to see if someone was a carrier, or likely to have the disease.  It is a disease in which brain cells are killed and which leads to death. Since we can identify people who will likely develop the disease, it is informative to see how often people want to know.  A review from the BMJ showed that only 10 to 20% of those people at risk for Huntington’s Disease end up being tested after being approached and offered genetic testing.  The other 80-90% prefer not to know.  

Perhaps they are right.  After all, life is not about avoiding illness.  Rather it is about enjoying your time on earth and making a difference to those around you.  While health is a central element, it is not the only element. Living your life with a focus on avoiding disease may be the right decision for some, but for others that focus on disease may prevent them from focusing on family and friends. 

All that is not to say our prediction efforts and our attempts to decrease health risk should stop.  It certainly is a big part of what I do every day and I am proud of my own work and believe it can improve people’s lives.  All this brings me back to the title of this blog post. The central myth of American medicine is that Death is Optional. It is not.  Life is a fatal disease. I for one believe that the efforts to predict disease must be tempered by the knowledge that we must use predictions to help people live the lives that they want to live until the moment they die and allow the focus to be on living rather than disease prevention at any price.  I question whether the desire to tell everyone everything about the future may end up making us sicker than we started.  

Tracking Hurricanes and Predicting Illness

As I watched the slow moving disaster known as Hurricane Dorian this past Labor Day weekend, it struck me that the prediction models for both the direction and strength of the hurricane kept changing.  The striking fact that was clear as I sat in the safety of my Chicago condo, was how hard it is to predict exactly where a hurricane will go and how strong it will be.  Different models had it originally heading across Florida into the gulf and later models were constantly being adjusted and changed.  Eventually, it hit the Bahamas, made a hard right turn, and it did not hit the American mainland until it meandered up the eastern seaboard to North Carolina.   An article in the Wall Street Journal about difficult in creating the predictions quoted Matt Lanza, managing editor of Space City Weather, as stating, “I’m constantly amazed at what just one tiny change can do to the whole picture.”

I understand.  I have spent a good deal of time and effort leading a group of very smart data scientists, clinical informaticists, health economists and statisticians in developing algorithms to predict the “path” of illness in order to better intercept and intervene before disaster hits.  We have the advantage of using the largest commercial claims data base in the US and possibly in the world, with over 40 million people per year.  It is also possibly the most up to date health care claims database, as it is refreshed monthly, and the database with the greatest claims history, as it reflects 10 years of claims.

Yet even then, it is very difficult because “one tiny change” can have a dramatic impact.  Medicine and health care are filled with low probability and high consequence events.  Life is as well.  Recently, we have been working on a model to predict people who are likely to be sick enough to generate $250,000 in claims in the coming 12 months.  It means predicting any illness, all of which have different profiles, and different patterns that lead up to catastrophe.  Thus, there are many numerous variables to predict numerous disease and combinations of diseases.  This creates a data science problem that belies an easy solution.  It means identifying someone who will be one of the 1 in 7,000 people to be sick enough to generate $250,000 in costs.  The nature of the prediction  challenge is also to identify those who are likely to have an illness that we can impact with proper treatment and/or proper support to improve the outcome.  A missed prediction could mean a person has a much worse outcome, even death or disability.  A personal “hurricane” that one may not be able to withstand.

The data that one uses must also include all factors that are present when a person becomes ill.  That means including data on emotions, social factors, finance and culture, among others.  If someone you love is in an accident and you are speeding while distracted while going to the hospital, you are more likely to have an accident.  That is a data point that medical records or health care claims will not reflect.  If you have just been fired from your job, that is another datapoint.  If you are poor and/or lonely, these are extremely important factors in trying to predict illness.  It is not just biology.

But biology is the central pathway, and claims databases, while reflecting medical care and medical interventions and encounters, are basically financial databases.  Electronic medical records, genomic information, and social information must be integrated into co-mingled databases to make analysis and, more specifically, prediction more powerful.

With healthcare, as opposed to hurricanes, there are issues of privacy and confidentiality that bring legal and ethical issues into play when combining data.  Dorian does not care if we know the details of its hurricane force winds but Jane Smith might care a lot that we are using her genetic information, combining it with her financial profile, any police record, her family dynamics, her friends and her spirituality to try and predict any illnesses and healthcare needs.

All these data feeds help us to become more accurate, but even if the privacy concerns are overcome, there will always be uncertainty. Progress will increase with each new insight, but someone can always trip in their own home and break an arm.

With each new insight we gain more predictability. Recently, in trying to predict patients who are likely to have very high costs due to critical illness, we found that the “velocity” of their medical activities was a useful variable in building our models.  To calculate this requires a different algorithm to feed the algorithm.

In other work I am doing, we have found that knowledge of the genetic makeup of the bacteria that are in a normal human intestinal tract, part of the microbiome, can help predict things like sensitivity to medications, propensity to diabetes depending on diet, and disease activity in someone with Inflammatory Bowel Disease.  Thus, the microbiome data has become an important variable in predicting disease.

And yet, our society demands perfection and immediacy.  In another article about forecasting the path of a hurricane, it was pointed out that forecasts tend to define a forecast cone.  The forecast cones have gotten significantly more narrow in the last ten years due to better measures and techniques, but there is still a 1 in 3 chance that the hurricane will be outside the cone completely.  That is far from perfection.

I believe that in healthcare, it will be no different.  We will make progress and get better with our predictions, but we must always remember that there will always be uncertainty in medicine.  We will need to better differentiate between the need for huge databases, such as the one used by my team, and the deep data that will come from more knowledge of the individual, and how the the two will interact.  In a future post, I will talk more about big data and deep data and how they both must be used.  Ultimately, there will always be some uncertainty, but we can decrease it incrementally in our quest to improve care.

Restarting - It Appears I Have More to Say

I have taken a hiatus of a few years from writing these thoughts, opinions, and occasional facts about health care, health economics and health benefits.  The hiatus came from a lack of time, a shift in my focus, and a need to rethink my reasons for writing.

During this writing lull, I have continued to fight for approaches to health care that are data driven and humanistic.  I have continued to fight entrenched ways of doing things, the use of health care for political means,  and the decisions made based on poor judgement, faulty data, and over reliance on blunt instruments.  I have continued to fight organizations that make decisions based on protecting their own positions and organizations rather than understanding and addressing the needs of people who are suffering.

I have seen health care attorneys look at all health care through the lens of the contract, health care data scientists look at all health care as new data algorithms to be developed, and internet entrepreneurs look at health care as their latest app.  With all this, I have also seen physicians move from being independent patient advocates to being shift workers paid by large systems whose goals sometimes seem to be more focused on margins and growth than on caring for those in need.  I have seen ego and wealth generation driving decisions instead of healing those in pain.  I have also seen brave, caring professionals who get up every day to fight for the patient.  I see those people getting tired and beaten down by the system in ways that are sad to watch.

So I will start again to put down my thoughts and observations in writing for anyone who cares to read them.  My first blog post will be posted shortly, and I thank those who do take the time to read it.