Tag Archives: statistics

Statistics: Beware of Exaggerated Certainty

Beware of Exaggerated Certainty – Know Your Chances – NCBI Bookshelf

This is one chapter from an online “Book” from the NIH: Know Your Chances: Understanding Health Statistics.

Of course, the numbers you see in health messages are not the whole story. We’d now like to add another bit of advice: once you have the numbers, ask yourself whether or not you should believe them.

Unfortunately, many statistics should not be accepted at face value, because they convey a sense of exaggerated certainty.

There are at least two reasons why reported research findings might not be right:

  1. much research is based on weak science, and
  2. many results are disseminated too early  Continue reading

Guide to Avoiding Logical Fallacies

A Politician’s Guide to Clear Thinking | Psychology Today

Introduction to critical thinking

Arguments are attempts to persuade by providing reasons (or premises or propositions) in support of a particular claim (or conclusion).

  • In a deductive or ‘truth-preserving’ argument, the conclusion follows from the premises as their logical consequence;
  • in an inductive argument, the conclusion is merely supported or suggested by the premises.

In many cases, arguments are implicit, meaning that their rational structures and their relationships are not immediately apparent, and need to be made explicit through analysis.   Continue reading

Know Your Chances: Risk and Statistics

Know Your Chances – NCBI Bookshelf – from NIH

The goal of this book is to help you better understand health information by teaching you about the numbers behind the messages—the medical statistics on which the claims are based.

The book will also familiarize you with risk charts, which are designed to help you put your health concerns in perspective.

By learning to understand the numbers and knowing what questions to ask, you’ll be able to see through the hype and find the credible information—if any—that remains.

This is a book that will teach you what numbers to look for in health messages and how to tell when the medical statistics don’t support the message.

Men and women doctors vs correlation and causation

Men and women doctors versus correlation and causation – KevinMD – by Ashish Jha – Jan 27, 2017

Our recent paper on differences in outcomes for Medicare patients cared for by male and female physicians created a stir.

Comparison of Hospital Mortality and Readmission Rates for Medicare Patients Treated by Male vs Female Physicians – JAMA Dec 19, 2016
Concusion: Elderly hospitalized patients treated by female internists have lower mortality and readmissions compared with those cared for by male internists.

It’s worth highlighting a few of the more common critiques that have been lobbed at the study to see whether they make sense and how we might move forward.
Continue reading

Medicare May Adopt Flawed CDC Guidelines

Medicare Takes Big Brother Approach to Opioid Abuse — Pain News Network

Just the thought of this makes my stomach lurch.

Politicians, bureaucrats, and financial interests are determined to control how much pain we must suffer by restricting access to the most effective relief.

Various industries which stand to gain from opioid restrictions (addiction-rehab, pharmaceutical, medical device, drug-testing) are colluding with political powers to pass legislation restricting opioid dosages to arbitrary limits.

Investigations of abuse or inappropriate prescribing would be shared with insurers enrolled in the giant Medicare/Medicaid system, even if the allegations are never proven.  Continue reading

New CDC Overdose Study more Truthful

New CDC Overdose Study Reduces Role of Pain Meds – Dec 26, 2016 By Pat Anson, Editor

The Centers for Disease Control and Prevention has quietly released a new report showing that illegal drugs like heroin, cocaine and fentanyl are responsible for more drug overdose deaths in the United States than opioid pain medication.

The report not only underscores the changing nature of the nation’s overdose epidemic, but undermines some of the rationale behind federal efforts to limit the prescribing of pain medication and public statements used to justify them.

In 2010, for example, the study found that oxycodone was the top drug involved in overdose deaths. But by 2014, the painkiller was ranked third, behind heroin and cocaine   Continue reading

More Evidence for Opioids than for Alternatives

Durations of Opioid, Nonopioid Drug, and Behavioral Clinical Trials for Chronic Pain: Adequate or Inadequate?  Pain Med. 2016 Nov – Abstract

This is another study that points out the unscientific reasoning behind the CDC opioid guidelines.

A recent US federal review and clinical guideline on opioids for chronic pain asserted that the literature contributes no evidence on efficacy because all trials had “inadequate duration.”

To explore the evidence, we examined durations of studies on opioid, nonopioid drug, and behavioral therapies for chronic pain.

METHODS:  

We retrieved Cochrane reviews of anticonvulsants, antidepressants, NSAIDs, opioids, or behavioral interventions for chronic pain.   Continue reading

What Is the Truth About Overdose Deaths?

What Is the Truth About Overdose Deaths?  December 3, 2016 by Lynn Webster, M.D.

In its 2015 Report Overview, the Clinton Foundation calls prescription drug abuse (leading to overdose) an imminent public health threat that kills “more people than motor vehicle accidents.”

The CDC reports that, during 2014, a total of 47,055 drug overdose deaths occurred in the United States. Indeed, that is a large number of tragic deaths.

Is There More to This Problem Than Prescription Drugs?

But a closer look at that statistic reveals that these deaths were caused by all drugs, not just prescription drugs, which is what those who relay statistics to the public often imply.

Furthermore, the number also includes overdoses of illicit drugs along with over-the-counter medications.

In 2014, 61% of 47,055 (28,647)drug overdose deaths involved some type of opioid, including heroin.

Note that even this figure is about one third fewer than the number of motor vehicle deaths reported for the same year.

In fact, National Safety Council reports that, in 2015, “38,300 people were killed on U.S. roads, and 4.4 million were seriously injured.” That number makes the Clinton Foundation’s statement … alarming.

The blind adherence to the media-hyped anti-opioid sentiment seems to be causing an epidemic of blatant statistical manipulation and repeated lying by government agencies entrusted with our health.

3 Reasons Why the Clinton Foundation Is Wrong

But the statement by the Clinton Foundation is inaccurate for three reasons.

First, the Clinton Foundation apparently puts all drug overdoses into the category of prescription drug overdoses. Many drugs contributing to the overdose statistic are not prescription drugs. For example, acetaminophen, ecstasy, and ibuprofen are not prescription drugs but contribute to the mortality stats.

Second, of the drug overdoses that are related to prescription drugs, many resulted from drugs other than opioids. Antidepressants, antipsychotics, and amphetamines are common examples.

Third, opioid-related drug overdoses comprise prescription opioids (including Oxycontin and Methadone) and illicit, non-prescription opioids (such as heroin and synthetic fentanyl).

All overdoses are bad, but it is important not to misrepresent the data. In order to curb the opioid epidemic, we have to understand the statistics that could drive policy.

The actual number of prescription opioid overdose deaths was closer to 14,000 in 2014 and has been on the decline since 2011,despite an increase in the number of illicit opioid deaths (mainly due to heroin and synthetic fentanyl opioids).

This isn’t to trivialize the points that the Clinton Foundation is making. Any drug overdose is devastating to a family of a decedent. However, to suggest that all of these deaths are due to prescription opioids just muddies the water and confuses the issue. Even the CDC cannot determine from death statistics whether an opioid is responsible for a death or whether it’s only associated with the death.

When an opioid is involved, it’s rarely possible to determine from the statistics the degree to which these overdoses were caused by a prescription opioid or other factors. Most people die from polysubstance abuse rather than just one drug. Ignoring the other factors that contribute to deaths means we have only part of the information we need to develop appropriate interventions.

An example is the report that 40% of people who use opioids also use prescription benzodiazepines. An FDA review found, “the growing combined use of opioid medicines with benzodiazepines or other drugs that depress the central nervous system (CNS) has resulted in serious side effects, including slowed or difficult breathing and deaths.”

Questionable reporting and mischaracterized, unclear statistics have lead policymakers to blame prescription opioids as the main culprit in the overdose epidemic. Prescription opioids have contributed to a large number of overdoses, but they have not come close to exceeding the number of deaths from motor vehicle accidents.

So neither prescription drugs nor prescription opioids cause more deaths than motor vehicle accidents.

In an attempt to curb the opioid crisis, people in pain are being ignored or told by physicians that nothing can be done for them.

This is happening partly because of the misunderstandings of the data that lead to statements such as the Clinton Foundation’s and public policy.

Solving the opioid crisis is important, but efforts to reverse the problem should not be based on misinformation. Policy should be based on fact and not a catchy headline.

Purchase Dr. Webster’s book, The Painful Truth: What Chronic Pain Is Really Like and Why It Matters to Each of Us (available on Amazon), or read a free excerpt here.

Standard Opioid Dosages for Postoperative Pain?

Study Sets Ideals For Opioid Use in General Surgery – Pain Medicine News – 12/1/2016

At the end of summer 2016, when it had become apparent that the number of opioid overdoses across the country could hit a new record this year, Surgeon General Vice Adm. Vivek Murthy, MD, MBA, Standard Opioid Dosages for Postoperative Pain?

For surgeons, whose opioid prescribing rates are, at 37%, among the highest of all specialists, this is a challenging task: There are few data on how to meet the acute pain needs of patients in the office without adding to the abundance of excess pills that are driving the opioid epidemic.

By now, we know that prescribed pills are NOT driving the “opioid epidemic” (see Manipulating Truth About Overdose Deaths), but this publication aimed at doctors continues spreading this false narrative.
Continue reading