[Reblog] Will Getting More Granular Help Doctors Make Better Decisions?

From the 8 February 2015 post at The Health Care Blog

Will Getting More Granular Help Doctors Make Better Decisions?

Excerpt (longish post)

But, there are many things that data will never do well.  For certain things, physician heuristics may lead to better decisions than any predictive model.

Heuristics are shortcuts, based on experience and training that allow doctors to solve problems quickly.  They are pattern maps that physicians are trained to recognize. But, heuristics have a reputation for leading to imperfect answers: Wikipedia notes that heuristics lead to solutions that “(are) not guaranteed to be optimal, but good enough for a given set of goals…. (they) ease the cognitive load of making a decision.”  Humans use them because we simply can’t process information in sequential binary fashion the way computers do.

It would be a mistake to call heuristics a sad substitute for big data.  Some cognitive scientists have made the argument, and I think they’re right, that heuristics aren’t simply a shortcut for coming to good-enough answers. For the right kinds of problems, heuristically generated answers are often better than the those generated by computers.

How can this be?

I often think of the following cartoon in Randall Munroe’s superb recent book, What If? Serious Scientific Answers to Absurd Hypothetical Questions.  In trying to compare human and computer thinking, he rightly notes that each excels at different things.  In this cartoon, for example, humans can quickly determine what they thought happened.  Most people can tell you that the kid knocked over the vase and the cat is checking it out, without going through millions of alternate scenarios.  Monroe notes that most computers would struggle to quickly come to the same conclusion.

So, from the perspective of an emergency doctor, here are the three leading problems with the applied use of complex analytics in the clinical setting:

• 1. The garbage in, garbage out problem.  In short, humans regularly obfuscate their medical stories and misattribute causality. You need humans to guide the patient narrative and ignore red herrings.

• 2. If we want to be able to diagnose, screen and manage an ER full of runny-nosed kids with fevers, we simply can’t afford the time it takes for computers to sequentially process millions of data points. The challenge is at one simple and nuanced: allowing 99% of uncomplicated colds to go home while catching the one case of meningitis. It’s not something that a computer does well: it’s a question of balancing sensitivity (finding all true cases of meningitis among a sea of colds) and specificity (excluding meningitis correctly) and doctors seem to do better than computers when hundreds of cases need to be seen a day.

• 3. There is a problem with excess information, where too much data actually opacifies the answer you’re looking for. Statisticians call this “overfitting” the data. What they mean is that as you add more and more data points to an equation or regression model, the variability of random error around each point gets factored in as well, creating “noise”. The more variables, the more noise.

The paradox is that ignoring information often leads to simpler and ultimately better decisions.

…

Related articles

• It takes more than great algorithms to make personalization work
• Sanjay Bakshi: Daniel Kahneman vs Gary Klein

More information does not equal better care

From the 1 November 2012 article at Medical News Today

…I have found that this concept is hard for non-healthcare people to really grasp – that a less aggressive testing approach knowingly misses disease, but makes no difference in the overall prospects of the patient. It is crucial that the U.S. culture fights the prevailing scare tactics of the diagnostics industry, or we’ll never lower the rate of overtesting. Any administrative tricks to lower testing rates will be subverted by both physicians and patients who assume more tests equal better care unless the underlying culture and conventional beliefs are changed.

The change required is deeper than administrative rules. It has to come from a more humble attitude on the part of doctors, patients, employers, and insurers that just because a patient could be labeled as having a disease, there is nothing to be gained by doing anything about it. More information does not equal better care.

Our American culture proclaims, “Just Do It.” To reclaim resources from the healthcare industry and return them to the general economy, we must proclaim, “Don’t just do something for the sake of doing something, stand there.”..

 

Related articles

•  9-part series on over-diagnosis (short reads from a health care journalist) (jflahiff.wordpress.com)
• Most patients don’t need extra tests for diagnosis (jflahiff.wordpress.com)
• Supplies and Devices Are Biggest Cause of Hospital Cost Increase (jflahiff.wordpress.com)

 

 

Do You Really Need a Yearly Checkup? | Yahoo! Health

Do You Really Need a Yearly Checkup? | Yahoo! Health By Lisa Collier Cool

Excerpt

Typically, a routine visit with your primary care doctor involves a slew of tests and screenings. While patients are often told that all this poking and prodding is crucial to protect their health, is there any scientific evidence to support that? A decade ago, the US Preventative Services Task Force (USPSTF), an independent group of medical experts appointed by Congress, concluded that yearly physicals are unnecessary for healthy, symptom-free adults.

What’s more, a new study published in Archives of Internal Medicine*** reports that primary care doctors often order unnecessary and inappropriate tests, screenings and treatments, costing the healthcare system—and patients—$6.8 billion in 2009. The annual checkup is a prime culprit in needlessly driving up medical bills, the researchers found, with dubious or worthless tests ordered in up to 56 percent of these exams.

Find out how to save big on rising healthcare costs.

Instead of a yearly checkup, the new thinking is that healthy patients should “check in” with their doctors periodically, on a schedule tailored to their individual needs, to discuss any medical concerns and which tests truly are appropriate for their age, gender, and family history. Here’s a look at routine screenings that primary care doctors are most likely to use needlessly, according to analysis by the National Physicians Alliance (NPA)—and when these tests are worthwhile….

Read the article (it includes comments about specific tests)

Related articles

• How much guidance do patients want with their medical decisions? (jflahiff.wordpress.com)
• Top 5” Lists Top $5 Billion in Potential Savings  (National Physicians Alliance)
• How much guidance do patients want with their medical decisions? (kevinmd.com)
• What Makes Patients Complex? Ask Their Primary Care Physicians (medicalnewstoday.com)
• What makes patients complex? Ask their primary care physicians (eurekalert.org)
• Let physician assistants be part of the primary care answer (kevinmd.com)

***The article, “Top 5” Lists Top $5 Billion, is available online only through paid subscription.
Click here for suggestions on how to get this article (and other science/medicine articles) for free or at low cost 

Here are the first 150 words of the Top 5 article from the Archives of Internal Medicine Web page

Minal S. Kale, MD; Tara F. Bishop, MD, MPH; Alex D. Federman, MD, MPH; Salomeh Keyhani, MD, MPH 

Arch Intern Med. 2011;171(20):1856-1858. doi:10.1001/archinternmed.2011.501

	Since this article does not have an abstract, we have provided the first 150 words of the full text and any section headings.

The Good Stewardship Working Group presented the top 5 overused clinical activities across 3 primary care specialties (pediatrics, internal medicine, and family medicine), as chosen by physician panel consensus.¹ All activities were believed to be common in primary care but of little benefit to patients. We examined the frequency and associated costs of these activities using a national sample of ambulatory care visits.

Methods

We performed a cross-sectional analysis using data from the 2009 National Ambulatory Medical Care Survey (NAMCS) and the National Hospital Ambulatory Medical Care Survey (NHAMCS). The NAMCS and NHAMCS survey patient visits to physicians in non–federally funded, non–hospital-based offices and non–federally funded hospital outpatient departments, respectively.²

We limited our sample to visits by patients to their primary care physicians. Visits for each “top 5” primary care activity were identified . . . [Full Text of this Article]

Microneedle sensors may allow real-time monitoring of body chemistry

IMAGE: This is a scanning electron micrograph of a hollow microneedle, which was prepared out of an acrylate-based polymer. In this study, hollow microneedles were integrated with sensors for detection of glucose, lactate, and pH levels in a selective and simultaneous manner.

From the 15 December 2011 Eureka News Alert

Researchers from North Carolina State University, Sandia National Laboratories, and the University of California, San Diego have developed new technology that uses microneedles to allow doctors to detect real-time chemical changes in the body – and to continuously do so for an extended period of time.

“We’ve loaded the hollow channels within microneedles with electrochemical sensors that can be used to detect specific molecules or pH levels,” says Dr. Roger Narayan, co-author of a paper describing the research, and a professor in the joint biomedical engineering department of NC State’s College of Engineering and the University of North Carolina at Chapel Hill.

Existing technology relies on taking samples and testing them, whereas this approach allows continuous monitoring, Narayan explains. “For example, it could monitor glucose levels in a diabetic patient,” Narayan says. Microneedles are very small needles in which at least one dimension – such as length – is less than one millimeter.

“The idea is that customized microneedle sensor arrays could be developed and incorporated into wearable devices, such as something like a wristwatch, to help answer specific medical or research questions,” Narayan says. “It’s also worth pointing out that microneedles are not painful.”

In addition to its clinical applications, the new technology may also create opportunities for new research endeavors. For example, the microneedle sensor arrays could be used to track changes in lactate levels while people are exercising – rather than measuring those levels only before and after exercise.

The researchers developed a proof-of-concept sensor array incorporating three types of sensors, which could measure pH, glucose and lactate. However, Narayan says the array could be modified to monitor a wide variety of chemicals.

The paper, “Multiplexed Microneedle-based Biosensor Array for Characterization of Metabolic Acidosis,” is published online in the journal Talanta. The paper was co-authored by Narayan and NC State Ph.D. students Philip Miller and Shelby Skoog as well as researchers from Sandia National Laboratories and the University of California, San Diego. The research was funded by the National Science Foundation, the National Institutes of Health, and the Department of Energy.

Related articles

• You: Microneedle sensors may allow real-time monitoring of body chemistry (cyberneticsnews.com)
• Microneedle Array Allows Real-Time Monitoring Of Body Chemistry (medgadget.com)