lance said:
Question on probability of later problems due to coumadin
- Thread starter ks1490
- Start date
Help Support Valve Replacement Forums:
MikeHeim
Well-known member
Andyrdj said:
I just re-read my post, and I have to say that I'm completely embarrassed. I'm not sure what the hell I was thinking, but I'm pretty sure that my old stats professor is totally ashamed of me...
Apologies to anyone who read either of my posts on this thread...
A
Andyrdj
No Apology needed!
No Apology needed!
Not to worry, Mike, it's through mistakes that we learn the most.
I almost let some corkers through when typing the drafts of these but was lucky enough to spot them.
To those who have seen my wilder speculations - I hope this explains more of my nature. Mathematics and science often contain propostions to be supported by logic or knocked down.
One of the ways, for example, to prove a statement true is to assume its opposite is true, and show that this leads to absurdity - it's called "proof by contradiction".
That's why I was surprised at people's reaction to some of my propositions - they were basically there as raw ideas to be verfied or disproved, and I was vastly surprised by some of the anger these caused!
No Apology needed!
Not to worry, Mike, it's through mistakes that we learn the most.
I almost let some corkers through when typing the drafts of these but was lucky enough to spot them.
To those who have seen my wilder speculations - I hope this explains more of my nature. Mathematics and science often contain propostions to be supported by logic or knocked down.
One of the ways, for example, to prove a statement true is to assume its opposite is true, and show that this leads to absurdity - it's called "proof by contradiction".
That's why I was surprised at people's reaction to some of my propositions - they were basically there as raw ideas to be verfied or disproved, and I was vastly surprised by some of the anger these caused!
G
Georgia
This discussion, while fascinating, makes me feel just like I did in stat class nearly 40 years ago - utterly clueless. It's deja vu all over again.
I also can't figure out sudoku. Hopeless.
And I'll add my brain blood to Gina's on the floor. What a mess.
I also can't figure out sudoku. Hopeless.
And I'll add my brain blood to Gina's on the floor. What a mess.
sue943
Well-known member
Having had one stroke I really do not want another, as I said, I fear that far more than death. I was just asked if I wanted tissue or mechanical. I had no idea that strokes could be a risk factor if the INR goes too low, had I known then I would have most definitely have gone for tissue.
Even with a relatively minor stroke I know how incapacitated I was, I could not bear to be like that again, or worse. I live alone and have no relatives living anywhere near me, they are all a plane trip away, I am not in the same country.
Stats
Stats
Andyrdj my thinking is exactly the same as yours regarding stats, I want to know exactly the probability of an out come, if you don't have the figures your working on emotion not probability this is a bad way to make major decisions. Insurance company actuaries use this type of analysis if they didn't they would go broke.
sue943 your statement "I don't fear death at all, but what I really fear is having a severe stroke and being unable to care for myself" sums up my outlook on both surgery and post surgery life. I was far more concerned about a stoke with surgery than death.
Stats
Andyrdj my thinking is exactly the same as yours regarding stats, I want to know exactly the probability of an out come, if you don't have the figures your working on emotion not probability this is a bad way to make major decisions. Insurance company actuaries use this type of analysis if they didn't they would go broke.
sue943 your statement "I don't fear death at all, but what I really fear is having a severe stroke and being unable to care for myself" sums up my outlook on both surgery and post surgery life. I was far more concerned about a stoke with surgery than death.
K
Karlynn
sue943 said:
I'm assuming the stroke was a result of your endocarditis (reading your info in your signature). Having had the experience, the outcomes are much more real for you and I can see why you do not like being in the position to worry about another. I wish you an increased peace of mind as you log more time on your mechanical valve.
G
geebee
Maybe I am just looking for the silver lining but, having had many, many TIAs, I can't help but wonder if they would have been full blown strokes had it not been for coumadin. The surgeon was never really sure what caused my TIAs (and I still have them occasionally) so, in my case, being on coumadin could possibly have saved my life many times over. Since there is no proof the TIAs are a result of having the mechanical valve, if I had a tissue valve and was not on coumadin, I might not be around.
My mother had a lot of problems with TIAs and she was not a valve patient so it could be something I inherited.
Yeah - I know it's speculation but there has been a bit of that lately so I will throw this out there.
Also, I am NOT advocating a mechanical valve and coumadin based on my experiences but I am submitting the possibility there could be unknown benefits to coumadin besides just avoiding additional surgeries.
My mother had a lot of problems with TIAs and she was not a valve patient so it could be something I inherited.
Yeah - I know it's speculation but there has been a bit of that lately so I will throw this out there.
Also, I am NOT advocating a mechanical valve and coumadin based on my experiences but I am submitting the possibility there could be unknown benefits to coumadin besides just avoiding additional surgeries.
Kate
Well-known member
Sue,
Like you, I find the idea of a stroke very scary and can only imagine how much worse it would be having had one previously. I don't know if this will be comforting for you or not, but my understanding is that the risk of stroke is actually about the same for a person with a biological valve and a person with a mechanical valve taking Coumadin. Take care, Kate
Like you, I find the idea of a stroke very scary and can only imagine how much worse it would be having had one previously. I don't know if this will be comforting for you or not, but my understanding is that the risk of stroke is actually about the same for a person with a biological valve and a person with a mechanical valve taking Coumadin. Take care, Kate
Ross
Well-known member
Statistics...........Some of you have got to have them. Why this is, is beyond me since there is no way to predict a certain persons outcome, but if that's what makes you happy, ok.
twinmaker
Well-known member
Statistics are kind of like word problems in math. Don't like them, can't do them, therefore, just don't go there! LINDA
LINDA
Actually, 34% is about what these actual stats seem to say, so it would be a fairly good guess - and good math - at the level of risk discussed:
St. Jude Aortic Valve Events at 10 years… at 20 years…
Thromboembolic Event.............18%...................32%
Bleeding Event.......................23%...................34%
Source: J Thorac Cardiovasc Surg. 2001 Aug;122(2):257-69; Twenty-year experience with the St Jude Medical mechanical valve prosthesis. Ikonomidis JS, Kratz JM, Crumbley AJ 3rd, Stroud MR, Bradley SM, Sade RM, Crawford FA Jr. http://www.ncbi.nlm.nih.gov/entrez/...ve&db=pubmed&dopt=Abstract&list_uids=14688722
However, those statistics (like the percentage being used by all the posters above), are from people who were in Coumadin management 20 to 25 years ago. That's not accurate to the care that a person is capable of applying to him or herself now, if he or she is moderately knowledgeable about warfarin and is willing to self-test for INR.
People in this forum are a part of a bold, new front to Coumadin management. They are not thralls to lackluster technicians and nurses who have limited understanding of the drugs they ply. They are people who take responsibility for their own INR, and who understand how to manage it, and who know where to ask to find out more when they need to. They insist on bridging when it's needed, they fight the self-serving dentists who would be willing to trade a little less blood on the gauze for the risk of a stroke in their patients. They aren't easy victims.
Coumadin patients don't have to live these statistics anymore. They have a choice. In ten years, these statistics can be old hat. In twenty, they can be a sad memorial to the days when this drug was misunderstood and mishandled.
So to these particular statistics, I say, "They're correct - but they ain't right!"
Best wishes,
St. Jude Aortic Valve Events at 10 years… at 20 years…
Thromboembolic Event.............18%...................32%
Bleeding Event.......................23%...................34%
Source: J Thorac Cardiovasc Surg. 2001 Aug;122(2):257-69; Twenty-year experience with the St Jude Medical mechanical valve prosthesis. Ikonomidis JS, Kratz JM, Crumbley AJ 3rd, Stroud MR, Bradley SM, Sade RM, Crawford FA Jr. http://www.ncbi.nlm.nih.gov/entrez/...ve&db=pubmed&dopt=Abstract&list_uids=14688722
However, those statistics (like the percentage being used by all the posters above), are from people who were in Coumadin management 20 to 25 years ago. That's not accurate to the care that a person is capable of applying to him or herself now, if he or she is moderately knowledgeable about warfarin and is willing to self-test for INR.
People in this forum are a part of a bold, new front to Coumadin management. They are not thralls to lackluster technicians and nurses who have limited understanding of the drugs they ply. They are people who take responsibility for their own INR, and who understand how to manage it, and who know where to ask to find out more when they need to. They insist on bridging when it's needed, they fight the self-serving dentists who would be willing to trade a little less blood on the gauze for the risk of a stroke in their patients. They aren't easy victims.
Coumadin patients don't have to live these statistics anymore. They have a choice. In ten years, these statistics can be old hat. In twenty, they can be a sad memorial to the days when this drug was misunderstood and mishandled.
So to these particular statistics, I say, "They're correct - but they ain't right!"
Best wishes,
K
Karlynn
And this is why we love you Bob. Always so well thought in your responses.
Now I have to go trap that rabbit that's been eating my plants and put a pancake on it's head.
Now I have to go trap that rabbit that's been eating my plants and put a pancake on it's head.
Fun with Statistics!
Fun with Statistics!
You guys are a lot of fun to watch! After all this let me add a little institutional memory here:
1. Forgive while I attempt to remember my Stat. 101 and 102. First law of statistics; probability assumes that for a given circumstance, formerly call a trial, there is one or more clearly definable outcomes. For example a coin flip is considered to have to two possible outcomes: a head or a tail! This is refereed to as Objective Probability and is calculated by Number of outcomes/number of trials. The math for this is pretty straight forward if you have time. The problem with what you are trying to calculate here with the rules of Objection Probability is they are designed for use when everyone agrees of the definition of the outcome, in this case a bleeding event. I have come out on the losing end of a previous debate because I assumed there was agreed upon definition of what a bleed event was-WRONG! As Al Lodwick and Tobagotwo pointed out, he who does the study may set their own protocols for defining what is or is not a bleed event. Under this situation, the rules of Subjective Probability come in to play. In this world, you talk in terms of random variables and distributions- where binomial, Poisson and Gaussian are not French restaurant, but are represented by receipts or formulas even a statistician can?t remember. Of course, these are no use to us unless we understand the most important theorem in statistics- The Central Limit Theorem; Which is employed to tell you if your conclusions are justified or merely the result of chance. The general proof of this theorem, I?m sure Andy will be delighted to walk us through. What does all this mean? A bleeding event probability is not the same as the flip of a coin probability, because the latter is an objective event and the former is subjective because it is up the researchers protocol to define it meaning. While no one would argue the probability of flipping a coin, it is very easy to fine fault with bleeding event probability based on protocol, sample size and distribution. That is how biostatisticians make a living.
2. Speaking of biostatisticians, Lance you might consider this article as you reflect on your question, as one of its contributors is one of the leading biostatistician of our time- Dr. Gary Grunkemeier:
http://www.onevalveforlife.com/documents/2of3.pdf
Draw your own conclusion. Any biostatisticians want to challenge this?
3. Lynlw, this poll
http://www.valvereplacement.com/foru...t=14312&page=2.
is a good illustration of how one could draw a false conclusion based on problems of sample distribution. Note how one respondent remarks that he would have expected a higher rate of AF among the data set. Not really, because the most of the data was taken from people who had their surgeries within the last several years and are relatively young. AF increases with age and the number of surgeries. What has been the history of heart patients is as the age of the population distribution mature, AF sets in. Also, the younger one is when you have valve surgery, the more likely you will have more years AF free. I didn?t get it till my early thirties, 20 years after my surgery. Some people in their 40?s get it 5 to 10 years after surgery and 50?s 3 to 7 years. Also, Mitral valvers are more prone to it then any other valvers. Statistically, it would be a good bet that ten years from now, if the same people responded, the incident of AF would be much higher. Any takers on that bet?
4. Sue: I too had a stroke and I can tell you it is much worse than any heart surgery. It is the second leading cause of death in the USA after heart disease. It is so strange to be walking around fine one moment and the next you crumble to the ground in disbelief as part of your bodies just doesn?t respond to your brain to move. Your brain suffering trauma is a total emotion wreck. Before my stroke I hadn?t shed a tear since my early teens, even when my mom died, which still bothers me to this day. Three months after her death, on the day I got engaged, I had my stroke. From that point on, I cried like a baby at the slightest bad news. My stroke was because I was off warfarin for four years and my valve was defective.
http://www.warfarinfo.com/warfarinfor43years.htm
When I went for rehabilitation, I saw people of all ages, some younger than me who suffered strokes. Everybody had a different cause of their stroke. I remember one older woman who had a stroke during heart bypass surgery and she remarked rather angrily how if she knew she could have a stroke during surgery, she never would have had it. I wondered then and I still do, what if???? I rarely discuss my stroke, because it makes me so sad. I understand how you feel- it would be nice if we were dealt a better hand of cards, but since we weren?t, all we can do it play it out the best we can. Good luck my dear.
Fun with Statistics!
You guys are a lot of fun to watch! After all this let me add a little institutional memory here:
1. Forgive while I attempt to remember my Stat. 101 and 102. First law of statistics; probability assumes that for a given circumstance, formerly call a trial, there is one or more clearly definable outcomes. For example a coin flip is considered to have to two possible outcomes: a head or a tail! This is refereed to as Objective Probability and is calculated by Number of outcomes/number of trials. The math for this is pretty straight forward if you have time. The problem with what you are trying to calculate here with the rules of Objection Probability is they are designed for use when everyone agrees of the definition of the outcome, in this case a bleeding event. I have come out on the losing end of a previous debate because I assumed there was agreed upon definition of what a bleed event was-WRONG! As Al Lodwick and Tobagotwo pointed out, he who does the study may set their own protocols for defining what is or is not a bleed event. Under this situation, the rules of Subjective Probability come in to play. In this world, you talk in terms of random variables and distributions- where binomial, Poisson and Gaussian are not French restaurant, but are represented by receipts or formulas even a statistician can?t remember. Of course, these are no use to us unless we understand the most important theorem in statistics- The Central Limit Theorem; Which is employed to tell you if your conclusions are justified or merely the result of chance. The general proof of this theorem, I?m sure Andy will be delighted to walk us through. What does all this mean? A bleeding event probability is not the same as the flip of a coin probability, because the latter is an objective event and the former is subjective because it is up the researchers protocol to define it meaning. While no one would argue the probability of flipping a coin, it is very easy to fine fault with bleeding event probability based on protocol, sample size and distribution. That is how biostatisticians make a living.
2. Speaking of biostatisticians, Lance you might consider this article as you reflect on your question, as one of its contributors is one of the leading biostatistician of our time- Dr. Gary Grunkemeier:
http://www.onevalveforlife.com/documents/2of3.pdf
Draw your own conclusion. Any biostatisticians want to challenge this?
3. Lynlw, this poll
http://www.valvereplacement.com/foru...t=14312&page=2.
is a good illustration of how one could draw a false conclusion based on problems of sample distribution. Note how one respondent remarks that he would have expected a higher rate of AF among the data set. Not really, because the most of the data was taken from people who had their surgeries within the last several years and are relatively young. AF increases with age and the number of surgeries. What has been the history of heart patients is as the age of the population distribution mature, AF sets in. Also, the younger one is when you have valve surgery, the more likely you will have more years AF free. I didn?t get it till my early thirties, 20 years after my surgery. Some people in their 40?s get it 5 to 10 years after surgery and 50?s 3 to 7 years. Also, Mitral valvers are more prone to it then any other valvers. Statistically, it would be a good bet that ten years from now, if the same people responded, the incident of AF would be much higher. Any takers on that bet?
4. Sue: I too had a stroke and I can tell you it is much worse than any heart surgery. It is the second leading cause of death in the USA after heart disease. It is so strange to be walking around fine one moment and the next you crumble to the ground in disbelief as part of your bodies just doesn?t respond to your brain to move. Your brain suffering trauma is a total emotion wreck. Before my stroke I hadn?t shed a tear since my early teens, even when my mom died, which still bothers me to this day. Three months after her death, on the day I got engaged, I had my stroke. From that point on, I cried like a baby at the slightest bad news. My stroke was because I was off warfarin for four years and my valve was defective.
http://www.warfarinfo.com/warfarinfor43years.htm
When I went for rehabilitation, I saw people of all ages, some younger than me who suffered strokes. Everybody had a different cause of their stroke. I remember one older woman who had a stroke during heart bypass surgery and she remarked rather angrily how if she knew she could have a stroke during surgery, she never would have had it. I wondered then and I still do, what if???? I rarely discuss my stroke, because it makes me so sad. I understand how you feel- it would be nice if we were dealt a better hand of cards, but since we weren?t, all we can do it play it out the best we can. Good luck my dear.
Joe Cool
Well-known member
Simple answer
Simple answer
I had a friend that explained it simply like this. EVERYTHING is 50/50. Either you do or you don't. Therefore, you have a 50% chance you will live, you have a 50% chance that you will die. As long as you keep this in mind, you will appreciate each day a little more. Your chances of getting in a fatal car crash are pretty high, but we keep driving, right?! As Mark Twain once said, " "there are lies, damn lies, and statistics"! Here is and article on stats for you stats lovers to think about.
Harvard Public Health Review
Fall 2004
Keeping Risk in Perspective
Which risk of death seems scarier: Shark attack or heart attack? Murder or accident? Plane crash or car crash?
The first threats may seem worse, but the second threats are far more likely. Why are people often more afraid of relatively low risks, and less afraid of bigger ones? Research into the perception of risk has revealed that, in addition to rationally considering the probabilities about a risk, human beings rely on intuitive faculties and emotions when subconsciously deciding what to fear, and how fearful to be. By understanding the factors that influence people's perception of risk, public health communicators can more effectively encourage them to make healthier choices.
David Ropeik, director of Risk Communication at Harvard Center for Risk Analysis (HCRA) and a former television journalist, lectures on this topic to HSPH students as well as government officials, reporters, and public health practitioners. As described in the book he co-authored in 2002 with HCRA Executive Director George Gray, RISK! A Practical Guide to What's Really Safe and What's Really Dangerous in the World Around You, several factors shape people's perception of risks:
Trust. The more we trust the people informing us about a risk, or the institution or company exposing us to the risk, or the government agencies that are supposed to protect us, the less afraid we'll be. The less we trust them, the greater our fear.
Control. The more control we have over a risk, the less threatening it seems. This explains why it feels safer to drive than fly, though the risk of death from motor vehicle crashes is much higher.
Dread. The more dreadful the nature of the harm from a risk, the more worried we'll be. Cancer is generally considered a more dreadful way to die than heart disease, yet heart disease kills roughly 25 percent more Americans.
Risk vs. benefit. The more we get a benefit from a choice or behavior, like using a cell phone when we drive or that "nice, healthy-looking tan" from the sun, the less concerned we are about any associated risk.
Human-made vs. natural. Natural risks seem less scary. Solar radiation causes an estimated 7,100 melanoma deaths in the U.S. per year. Yet many sunbathers worry more about nuclear radiation. Among more than 90,000 survivors of Hiroshima and Nagasaki, only about 500 cancer deaths have been attributed to radiation exposure over the past 59 years.
"Could it happen to me?" Statistical probabilities like one in a million are often used in risk communication, usually to no avail. One in a million is too high if you think you could be "the one." That is why the public sometimes demands additional regulations to cut already low risks to zero.
New or familiar. New threats--for example, West Nile virus when it first appears in a community--generate concern. After residents have lived with the risk for a while, familiarity lowers their fear.
Children. Any risk to a child seems more threatening in the eyes of adults than the same risk does to them.
Uncertainty. The less we know, or understand, about a risk, the scarier it seems.
Perceiving risk through these emotional and intuitive lenses, which have been identified by researchers Paul Slovic, Baruch Fischhoff, and others, is natural human behavior, but "It can lead us to make dangerous personal choices," Ropeik says. Driving may have felt safer than flying after September 11, 2001, but those who opted to drive rather than fly were actually raising their risk. Risk misperception can threaten health by making us too afraid, or not afraid enough.
Finally, as George Gray points out, failing to keep risk in perspective leads us to "pressure government for protection against relatively small risks, which diverts resources from bigger ones."
"By understanding and respecting the way people relate to risk," Gray says, "risk communicators can play a vital role in improving the public's health."
What?s the risk?
Average annual estimates of the risk of death for the U.S. population. Individual risks vary.
Heart disease: 1 in 430
Cancer (all forms): 1 in 550
Skin cancer from sun: 1 in 4,200
Flu: 1 in 8,300
West Nile virus: 1 in 30,400
Suicide: 1 in 9,000
Murder: 1 in 13,500
Crash, motor vehicle: 1 in 7,100
Crash, commercia aircraft: 1 in 3.1 million
Falls: 1 in 20,000
On the job: 1 in 48,000
Accidental electrocution: 1 in 300,000
Lightning: 1 in 3 million
Shark attack: 1 in 300 million
Sources: Risk! A Practical Guide to What?s Really Safe and What?s Really Dangerous in the World Around You (Houghton Mifflin 2002) and the U.S. Centers for Disease Control and Prevention
Simple answer
I had a friend that explained it simply like this. EVERYTHING is 50/50. Either you do or you don't. Therefore, you have a 50% chance you will live, you have a 50% chance that you will die. As long as you keep this in mind, you will appreciate each day a little more. Your chances of getting in a fatal car crash are pretty high, but we keep driving, right?! As Mark Twain once said, " "there are lies, damn lies, and statistics"! Here is and article on stats for you stats lovers to think about.
Harvard Public Health Review
Fall 2004
Keeping Risk in Perspective
Which risk of death seems scarier: Shark attack or heart attack? Murder or accident? Plane crash or car crash?
The first threats may seem worse, but the second threats are far more likely. Why are people often more afraid of relatively low risks, and less afraid of bigger ones? Research into the perception of risk has revealed that, in addition to rationally considering the probabilities about a risk, human beings rely on intuitive faculties and emotions when subconsciously deciding what to fear, and how fearful to be. By understanding the factors that influence people's perception of risk, public health communicators can more effectively encourage them to make healthier choices.
David Ropeik, director of Risk Communication at Harvard Center for Risk Analysis (HCRA) and a former television journalist, lectures on this topic to HSPH students as well as government officials, reporters, and public health practitioners. As described in the book he co-authored in 2002 with HCRA Executive Director George Gray, RISK! A Practical Guide to What's Really Safe and What's Really Dangerous in the World Around You, several factors shape people's perception of risks:
Trust. The more we trust the people informing us about a risk, or the institution or company exposing us to the risk, or the government agencies that are supposed to protect us, the less afraid we'll be. The less we trust them, the greater our fear.
Control. The more control we have over a risk, the less threatening it seems. This explains why it feels safer to drive than fly, though the risk of death from motor vehicle crashes is much higher.
Dread. The more dreadful the nature of the harm from a risk, the more worried we'll be. Cancer is generally considered a more dreadful way to die than heart disease, yet heart disease kills roughly 25 percent more Americans.
Risk vs. benefit. The more we get a benefit from a choice or behavior, like using a cell phone when we drive or that "nice, healthy-looking tan" from the sun, the less concerned we are about any associated risk.
Human-made vs. natural. Natural risks seem less scary. Solar radiation causes an estimated 7,100 melanoma deaths in the U.S. per year. Yet many sunbathers worry more about nuclear radiation. Among more than 90,000 survivors of Hiroshima and Nagasaki, only about 500 cancer deaths have been attributed to radiation exposure over the past 59 years.
"Could it happen to me?" Statistical probabilities like one in a million are often used in risk communication, usually to no avail. One in a million is too high if you think you could be "the one." That is why the public sometimes demands additional regulations to cut already low risks to zero.
New or familiar. New threats--for example, West Nile virus when it first appears in a community--generate concern. After residents have lived with the risk for a while, familiarity lowers their fear.
Children. Any risk to a child seems more threatening in the eyes of adults than the same risk does to them.
Uncertainty. The less we know, or understand, about a risk, the scarier it seems.
Perceiving risk through these emotional and intuitive lenses, which have been identified by researchers Paul Slovic, Baruch Fischhoff, and others, is natural human behavior, but "It can lead us to make dangerous personal choices," Ropeik says. Driving may have felt safer than flying after September 11, 2001, but those who opted to drive rather than fly were actually raising their risk. Risk misperception can threaten health by making us too afraid, or not afraid enough.
Finally, as George Gray points out, failing to keep risk in perspective leads us to "pressure government for protection against relatively small risks, which diverts resources from bigger ones."
"By understanding and respecting the way people relate to risk," Gray says, "risk communicators can play a vital role in improving the public's health."
What?s the risk?
Average annual estimates of the risk of death for the U.S. population. Individual risks vary.
Heart disease: 1 in 430
Cancer (all forms): 1 in 550
Skin cancer from sun: 1 in 4,200
Flu: 1 in 8,300
West Nile virus: 1 in 30,400
Suicide: 1 in 9,000
Murder: 1 in 13,500
Crash, motor vehicle: 1 in 7,100
Crash, commercia aircraft: 1 in 3.1 million
Falls: 1 in 20,000
On the job: 1 in 48,000
Accidental electrocution: 1 in 300,000
Lightning: 1 in 3 million
Shark attack: 1 in 300 million
Sources: Risk! A Practical Guide to What?s Really Safe and What?s Really Dangerous in the World Around You (Houghton Mifflin 2002) and the U.S. Centers for Disease Control and Prevention
A
Andyrdj
RCB is asking me to give you headaches!
RCB is asking me to give you headaches!
Aaargh! trying to type all of the equations necessary into this field!
The gist of the "Central Limit Theorem", if RCB is referring to what I think it is, is to do with Hypothesis testing - if you have an unusual result, do you put it down to reasonable chance, or are you justified in regarding yourself as "different to the main population"?
It's the same stuff used to debunk proofs of "psychic ability" - someone shows that a seemingly remarkable result has e.g. a 10% chance of occuring by luck - which isn't enough reason to go believing in magic, since 1 in 10 chances happen all the time in your day to day life.
Similarly, getting a bleeding event in your first year (2% probability) isn't really enough to say with certainty that this is going to be your situation from now on - because 1 in 50 events are all that unusual. 2 bleeds in 2 years, though, is only 0.04% (1 in 2500) likely to happen by chance, so you might worry more then.
P.S. Bob H - thanks for the info, looks like maths really works. In point of fact, I suspect the 2% per year stat I used was calculated from results similar to yours. So If you come up with newer stats for better managed patients, we can
get a new yearly event free estimate for a trial of N years by calculating the Nth root of the fraction of event free patients. Though I really ought to dig out my old stats theory stuff and calculate the error margin on the estimate too!
RCB is asking me to give you headaches!
Aaargh! trying to type all of the equations necessary into this field!
The gist of the "Central Limit Theorem", if RCB is referring to what I think it is, is to do with Hypothesis testing - if you have an unusual result, do you put it down to reasonable chance, or are you justified in regarding yourself as "different to the main population"?
It's the same stuff used to debunk proofs of "psychic ability" - someone shows that a seemingly remarkable result has e.g. a 10% chance of occuring by luck - which isn't enough reason to go believing in magic, since 1 in 10 chances happen all the time in your day to day life.
Similarly, getting a bleeding event in your first year (2% probability) isn't really enough to say with certainty that this is going to be your situation from now on - because 1 in 50 events are all that unusual. 2 bleeds in 2 years, though, is only 0.04% (1 in 2500) likely to happen by chance, so you might worry more then.
P.S. Bob H - thanks for the info, looks like maths really works. In point of fact, I suspect the 2% per year stat I used was calculated from results similar to yours. So If you come up with newer stats for better managed patients, we can
get a new yearly event free estimate for a trial of N years by calculating the Nth root of the fraction of event free patients. Though I really ought to dig out my old stats theory stuff and calculate the error margin on the estimate too!
M
Mary
Karlynn said:
Now THAT's FUNNY!
interesting site
interesting site
one of my friends sent me this link, it is about congenital heart defects and a 'risk score' http://www.aristotleinstitute.org/aboutScore.asp
as i was looking at it I kept thinking about this thread so thought some of you would find it interesting
here is a little bit about how/why it was started
DEVELOPMENT
The motivation behind the Complexity Score Project was a growing frustration of pediatric cardiac surgeons over the fact that their surgical performance was being evaluated based on hospital mortality without regard for the complexity of the operations performed. A working group of Congenital Heart Surgeons from Europe and the United States decided to develop a risk-stratification method which could be adapted to our specialty.
When starting this project in 1999, two difficulties were encountered: 1) Multi-institutional databases were just starting and there was no reliable data yet available. 2) Due to the absence of risk stratification, the more prominent centers dealing with the sickest patients and potentially having a significant mortality were very reluctant to send their data. It was, therefore, necessary to base this risk-adjustment on an evaluation that was largely subjective. Following many discussions, it was concluded that a subjective probability approach based on the consensus of a panel of experts was valid, provided that the risk-adjustment score is subsequently validated based on collected outcome data.
A group of 50 internationally accepted experts has been working for more than five years on a new method to evaluate the quality of care in Congenital Heart Surgery (CHS) that is called Aristotle. Senior, experienced congenital heart surgeons considered the possible risk factors for each procedure and assigned scores based on potential for mortality, potential for morbidity, and anticipated surgical difficulty.
The Aristotle system, electronically available, has been introduced by both the European Association for Cardio-Thoracic Surgery (EACTS) and Society of Thoracic Surgeons (STS) as an original method to compare the performance of Congenital Heart Surgery (CHS) centers. Pediatric cardiologists have joined the project and are currently developing a complexity score for interventional cardiology procedures.
interesting site
one of my friends sent me this link, it is about congenital heart defects and a 'risk score' http://www.aristotleinstitute.org/aboutScore.asp
as i was looking at it I kept thinking about this thread so thought some of you would find it interesting
here is a little bit about how/why it was started
DEVELOPMENT
The motivation behind the Complexity Score Project was a growing frustration of pediatric cardiac surgeons over the fact that their surgical performance was being evaluated based on hospital mortality without regard for the complexity of the operations performed. A working group of Congenital Heart Surgeons from Europe and the United States decided to develop a risk-stratification method which could be adapted to our specialty.
When starting this project in 1999, two difficulties were encountered: 1) Multi-institutional databases were just starting and there was no reliable data yet available. 2) Due to the absence of risk stratification, the more prominent centers dealing with the sickest patients and potentially having a significant mortality were very reluctant to send their data. It was, therefore, necessary to base this risk-adjustment on an evaluation that was largely subjective. Following many discussions, it was concluded that a subjective probability approach based on the consensus of a panel of experts was valid, provided that the risk-adjustment score is subsequently validated based on collected outcome data.
A group of 50 internationally accepted experts has been working for more than five years on a new method to evaluate the quality of care in Congenital Heart Surgery (CHS) that is called Aristotle. Senior, experienced congenital heart surgeons considered the possible risk factors for each procedure and assigned scores based on potential for mortality, potential for morbidity, and anticipated surgical difficulty.
The Aristotle system, electronically available, has been introduced by both the European Association for Cardio-Thoracic Surgery (EACTS) and Society of Thoracic Surgeons (STS) as an original method to compare the performance of Congenital Heart Surgery (CHS) centers. Pediatric cardiologists have joined the project and are currently developing a complexity score for interventional cardiology procedures.
G
geebee
OMG - I didn't think my head could explode twice.
Anyway - here's my unscientific theory based on the heads-tails odds thingy. Every time you toss a coin you have a 50/50 chance of getting heads. Doesn't matter how many times you toss the coin, each toss has the same chance. I guess when you throw probability in the mix, it might change things but I am not going there.
In addition, every year I have a 1-2% chance of a bleeding event. Each year becomes a whole new ballpark in my little corner of utopia. I don't care what happened last year and I don't care what might happen 20 years down the road, I am in this year.
Sweet, simple and works for me. Maybe for others, maybe not but I will still share it with you.
Please don't quote stats at me for this particular post. I have no brain matter left to cover the floor.
Anyway - here's my unscientific theory based on the heads-tails odds thingy. Every time you toss a coin you have a 50/50 chance of getting heads. Doesn't matter how many times you toss the coin, each toss has the same chance. I guess when you throw probability in the mix, it might change things but I am not going there.
In addition, every year I have a 1-2% chance of a bleeding event. Each year becomes a whole new ballpark in my little corner of utopia. I don't care what happened last year and I don't care what might happen 20 years down the road, I am in this year.
Sweet, simple and works for me. Maybe for others, maybe not but I will still share it with you.
Please don't quote stats at me for this particular post. I have no brain matter left to cover the floor.
No- not quite right
No- not quite right
are not a coin, whose outcome can only be heads or tails(Objective Probability). You are rather a data point in a distribution, where in the average of probability is 1 to 2 % depending on how a bleeding event is defined (Subjective Probability). Also, is the distribution a Poisson or Gaussian and where do your own risk factors put you on that curve. Statistics only tell you what the mythical average person?s chances are, but your chances might be much lower. I think being on this board, having access to Mr. Lodwick and home testing put you at a much lower probability.
Now that is sweet, simple and surely works for you
No- not quite right
I hate to correct such a smiling face, but the statement "every year I have a 1-2% chance of a bleeding event" may not be true. Remember, yougeebee said:OMG - I didn't think my head could explode twice.
Anyway - here's my unscientific theory based on the heads-tails odds thingy. Every time you toss a coin you have a 50/50 chance of getting heads. Doesn't matter how many times you toss the coin, each toss has the same chance. I guess when you throw probability in the mix, it might change things but I am not going there.
In addition, every year I have a 1-2% chance of a bleeding event. Each year becomes a whole new ballpark in my little corner of utopia. I don't care what happened last year and I don't care what might happen 20 years down the road, I am in this year.
Sweet, simple and works for me. Maybe for others, maybe not but I will still share it with you.
Please don't quote stats at me for this particular post. I have no brain matter left to cover the floor.
are not a coin, whose outcome can only be heads or tails(Objective Probability). You are rather a data point in a distribution, where in the average of probability is 1 to 2 % depending on how a bleeding event is defined (Subjective Probability). Also, is the distribution a Poisson or Gaussian and where do your own risk factors put you on that curve. Statistics only tell you what the mythical average person?s chances are, but your chances might be much lower. I think being on this board, having access to Mr. Lodwick and home testing put you at a much lower probability.
Now that is sweet, simple and surely works for you
