Monday, September 12, 2011

Watson and Deductive Reasoning

IBM's Watson computer could be a major improvement in healthcare. But it won't be replacing your doctor anytime soon.

I watched Watson appear on Jeopardy and I was pretty impressed. It appeared to me to be a deductive reasoning engine, taking bits of information and using them one by one to come to an answer. If there was enough information for the machine's algorithm to show a certain confidence level, Watson answered the question. The syntax didn't need to be computer ready either - it was just plain English.

One thing I thought is that Watson could be a major help with medical diagnoses, which use a similar kind of reasoning. A patient would appear with a set of symptoms, say fever, night sweats, and muscle aches. The doctor would use his or her knowledge and come up with an answer cold or flu (or something else - I'm not a doctor). With more information, the doctor may come up with a different answer. That seems to be exactly how Watson works.

I can absolutely see a doctor feeding a set of symptoms into a Watson system to help find likely diagnoses. In fact, it might help improve the diagnosis of rarer conditions with which the average primary care doctor might have less experience.

But it seems that what Watson can't do is figure out the correct follow-up questions, or know how to interpret the patient's answers. Not everyone can put every symptom they may be feeling into words, particularly if they lack vocabulary due to education level or a primary language that doesn't match the doctor's. Some people may be hesitant to give all necessary information for many reasons. A doctor will use all of the patient's answers and non-answers to determine the best course of action, and not just the patient's words.

For example, those symptoms I listed are also those that can occur in the weeks following HIV infection. There are many reasons why a patient might be hesitant to mention possible exposures to HIV, particularly when the two most common modes of transmission are through unprotected sexual contact and the use of IV drugs. A doctor would be able to determine if an HIV test was warranted by paying attention to the patient, even if the patient said that they did not have any possible exposure. I don't know if Watson would.

Friday, September 9, 2011

Is Payment Parity a Good Idea?

Some hospitals and medical groups are paid much more than others. But isn't that what the market's about?

There's a legislative proposal to equalize fees to doctors and hospitals. Those paid the lowest would get a raise, while those paid the highest would get a cut. It sounds like a simple, good idea.

Unfortunately, it may have a detrimental effect on providers for underserved areas. If you're the only doctor or hospital in town, you can demand a higher rate. That creates an incentive to be the only game in town, sending medical care to areas that lack it.

So, say you're the only medical group in an area of the Berkshires. There aren't that many people around, and because of your size your overhead is actually higher than larger groups that can pool resources. Thankfully, the higher reimbursement rate you can charge allows you to keep the practice open. Your doctors may not make more than their urban counterparts, but at least they make a comparable amount after expenses.

What happens when you're reimbursements are cut?

A few providers may stay in that office in the Berkshires and just take the pay cut. Others will head for a larger medical group in a city. Suddenly, that town in the Berkshires just lost most of their medical care. Oops.

The fee-equalization legislation is likely aimed at a certain large hospital group widely known to charge higher fees than comparable hospitals in their area, which shall remain nameless. Maybe they're not justified in charging those higher fees. But this legislation could have some unintended consequences.

Tuesday, August 16, 2011

The Cost of Success

If a program is successful, you should end it. Correct?

That's why the CDC may be gutting Massachusetts' HIV prevention programs. Infection rates are lower in the Northeast than they are in many other parts of the country, and the CDC wants to improve prevention services in places with higher infection rates. Sounds reasonable, but it could have an effect exactly the reverse of the intention.

So what does the CDC do when they find that they've caused the rate of infection in the Northeast to go up to match the rest of the country? That's what could happen, since each program has a measurable impact on the HIV infection rate.

Many prevention programs begin as a research program or a local pilot. Success means that the people who were part of the program had a lower HIV infection rate than a comparable population. Let's use a HIV prevention hotline as a possible pilot. Start by opening it to one region, then look at the infection rate both before and after the hotline opened in that region, and also compared to other regions. If the infection rate went down relative to other regions, that hotline is a success. It then gets rolled out to everyone.

Each program is based on being able to reduce the rate of HIV infection by some percentage. Commonly, the goal is 5%. It doesn't sound like a huge amount, but absolutely worth it when you consider how many people that 5% represents.

The important thing is that the rate of HIV infection is lower while the program is active. What happens when it's no longer active? What happens when five programs, each of which has shown to be able to reduce infections by 5%, are cancelled?

Addressing the higher rate of HIV infection in some areas of the country is an absolute priority. That's another topic to go into later. But here's a hint: once a successful program is gone, so are the people who can help new programs be modeled on it.

Thursday, July 21, 2011

A Good Psychiatrist is Hard to Find

Today, the Globe is reporting on the lack of access to psychiatrists in the Boston area, based on a study conducted by two local hospital groups. Researchers called a number of psychiatric facilities and asked when the first available appointment is with a psychiatrist. In most cases, it was not for a while.

The hospital-based researchers used that as evidence that psychiatrists should be paid more. That prompted Blue Cross Blue Shield to say that the study was done just to be able to say that psychiatrists should be paid more. Well, of course. Who doesn't want to be paid more?

My issue with the study is that the researchers asked for appointments with psychiatrists. There are many more behavioral health clinicians qualified to treat depression. A psychologist, for example, would be fully qualified to treat depression and may have much more availability.

The main thing that a psychiatrist can do that other clinicians cannot is prescribe medication. Other clinicians ask for a psychiatrist to consult in a case where they might think medication is a good idea. It isn't always.

If I were to try this study again, I would call up those facilities and ask for someone who can treat depression. First available. I don't know what the results will be, but I would guess that a psychologist or nurse might be available in a shorter time than a psychiatrist.

Note:
In case you don't know the difference, a psychiatrist is a medical doctor (MD or DO), who completed medical school and specializes in psychiatry. A psychologist completed a doctorate (PhD) in psychology, but is not a medical doctor. Nurses may also specialize in psychiatry, and there are a few other certifications such as Licensed Mental Health Clinician (LMHC) that allow certify a person to provide behavioral health treatment.

Tuesday, July 19, 2011

Prevention Is a Hard Sell

The latest report to be issued on the state of health in Massachusetts just came out. If you want the details, the Globe did a writeup that covers some of the key points. There are many areas in which the Commonwealth is doing well, and many areas sorely lacking, but ultimately it all comes down to the money.

According to the report, Massachusetts spends $63 billion on medical services and $600 million on public health (which includes prevention). So in total, the amount that we spend to prevent medical issues is less than 1% the amount that we spend to treat them after they occur. Due to the Commonwealth's tight budget, the relative percentage has actually gone down over the past few years.

What might happen if you doubled the amount spent on prevention, so that it's maybe up to somewhere around 2% of the money we spend on treatment? Over time, the population will be healthier and expenditures on treatment of preventable illnesses will go down.

For example, take Codman Square in Dorchester. There's no supermarket there, but there is a fast food restaurant. There are some parks where people can exercise, but they're not always safe so many people don't. Some money to bring in fresh, healthy food and make the streets and parks safe would be a great way to make the people of Codman Square healthier. In particular, the rate of obesity and diabetes might go down.

Now, prove that there's a return on the investment. How exactly would I show that those people who now don't have diabetes would have developed diabetes if that money hadn't been spent? There are very few feasible ways to do it. How would you prove that something that could have happened didn't due to something that you did?

The thinking about prevention is completely backwards. Why isn't improved health an outcome worth funding? Instead of looking at health as an absence of disease, why not think of it as a presence of proper body and mind function? The return on investment will come, but it will really be from the increased productivity of healthy people and not from an illness that didn't happen.

Thursday, July 14, 2011

What's in a serving?

Kids should eat a variety of healthy foods. I don't think you'll be able to find anyone outside of a large processed food company's lab who will argue. So, of course, legislators are spending quite a bit of time an energy trying to make kids food healthier.

The government wants to limit the amount of sugar in products aimed at kids (using cartoon characters) to no more than 8 grams per serving. The food industry is suggesting that they voluntarily limit that amount to 10 grams per serving. What's missing is any talk about the serving size.

When you look at a food label, such as on the side of a cereal box, at the top you'll find the product's serving size. A cereal that I often enjoy lists the serving size as 1 cup. And therein lies the problem. It's not regulated.

I'll pour cereal into a bowl until it looks like the amount I want to eat, which is somewhere around 2 cups. Then I'll add milk. On the side of the cereal box I should have 1/2 cup milk per serving. That's pretty dry cereal. Of course I add more.

Now watch a cereal commercial. A kid will pour cereal from the box into a bowl and more or less fill it. He or she does not find a measuring cup and make sure only to pour one serving.

No matter what limit on sugar is passed, 8 or 10 grams per serving, a cereal maker only has to reduce their serving size to meet it. Today, the side of the box may say 1 cup of cereal with 10 grams of sugar. Tomorrow, that can be changed to 3/4 cup of cereal with 7.5 grams of sugar. Either way, a full cereal bowl is much more than that.

Another example is a small bag of chips, like you might have with lunch. Look at the number of servings listed in the bag. I was recently surprised to find a major brand said that there were 1.5 servings in a bag. Who doesn't finish that little bag of chips?

The serving size often does not correspond to how much a person might eat at one time. Limiting the amount of sugar in a serving is great, but only if the serving is the actual amount that an average child may eat.

Welcome to the Boston Healthcare Translation Service

When I meet someone at a cocktail party, after some polite banter, the question of what I do usually comes up. When I mention that I work in health care, that often becomes the topic of conversation. 

The health care system, especially in Massachusetts, is extraordinarily complex. I hope to explain a little bit of it over time. First, there are the health care jargon terms that you will hear if you are within earshot of a health care professional. They mean something in English, really. Next, there's the doublespeak you hear coming from advocates for every part of the health care system, which often doesn't mean what it sounds like. Finally, there's the research that's breathlessly repeated by news outlets, often contradicting an article that came out last week.

I think that I'll be able to keep posting for a while.