An Overview of the Archimedes Healthcare Model The Archimedes Project Kaiser Permanente
A KAISER PERMANENTE INNOVATION
This presentation will address three main topics: • What the Archimedes model is • How it can be used • How we know it works
A KAISER PERMANENTE INNOVATION
Until now, there have been four main kinds of mathematical models in health care • Biological modeling – e.g. glucose metabolism, Starling heart equation • Clinical Medicine – e.g. Regression equations, Markov models • Operations research / management science – e.g. Schedule operating rooms, plan hospitals • Economic / system resources – e.g. Forecasting A KAISER PERMANENTE INNOVATION
Archimedes is a new type of mathematical model of health care: it includes all four components Biological modeling Clinical medicine Care processes System resources A KAISER PERMANENTE INNOVATION
Archimedes is also new because it is anchored to reality through clinical trials Biological modeling Clinical medicine Care processes System resources A KAISER PERMANENTE INNOVATION
This presentation will address four main topics. Let’s begin with: • • • • • •
What the Archimedes model is How it can be used How we know it works What we plan to do with it How you will be able to get access to it What’s on this website A KAISER PERMANENTE INNOVATION
Archimedes is • Object oriented • Continuous • Physiology based • Very deep and very broad • and it operates at the level of detail that clinicians and administrators consider essential for making decisions A KAISER PERMANENTE INNOVATION
Now let’s define those terms. This is what we mean by “object oriented” • All the important objects in reality have corresponding objects in the model, one-to-one, at a high level of detail Patients, organs, parts of organs Facilities Health care personnel
Equipment, supplies Policies and procedures Budgets, regulations, more A KAISER PERMANENTE INNOVATION
More specifically, this means that • There are thousands of simulated people in the model, each one of them different • They can get sick, and go see simulated doctors • In simulated offices • And get simulated tests, that use simulated pieces of equipment • And get simulated treatments • And so forth A KAISER PERMANENTE INNOVATION
This is what we mean by “continuous” • Biological variables that are continuous in reality are continuous in the model (e.g. BP, LDL cholesterol) – No “clinical states”, “strata” • Time is continuous; any event can occur at any time – No “ticks”, “steps” or “annual jumps”
A KAISER PERMANENTE INNOVATION
The concept of “physiology based” needs more explanation. And we’re going to need a volunteer I’ll volunteer Thanks. What’s your name? Joe. Joe Miner OK Joe. I hope you’re not ticklish…
A KAISER PERMANENTE INNOVATION
… because we’re going to need to look inside your belly. Can you come a bit closer? Sure
A little bit closer, if you can A KAISER PERMANENTE INNOVATION
How’s this?
That’s good. Nice belly, Joe. Now we’re going to need to do a sort of x-ray
OK. The reason we’re doing this is that we want to show you that every simulated person in the model, like Joe, has organs, such as…
Heart And every organ has all of its types of cells, like these beta cells of the pancreas
Liver
Circulatory system
Pancreas
Fat cells Gut
Muscle
The organs and their cells carry out metabolic functions, such as…
GLYCOGEN GLYCOGEN GLUCOSE GLUCOSE
HEPATIC GLUCOSE PRODUCTION
CIRCULATING GLUCOSE
GLUCOSE UPTAKE BY MUSCLE GLUCOSE UPTAKE BY FAT
SUGARS
In the model, these functions are regulated just as they are in a real person. For example, in response to the circulating levels of glucose, the pancreatic beta cells will secrete insulin
GLYCOGEN GLUCOSE
HEPATIC GLUCOSE PRODUCTION
GLUCOSE UPTAKE BY FAT
CIRCULATING GLUCOSE INSULIN
SUGARS
GLUCOSE UPTAKE BY MUSCLE
And diseases can occur. For example, in a person with diabetes the effect of insulin on uptake of glucose by the muscle and fat is decreased.
GLYCOGEN GLUCOSE
HEPATIC GLUCOSE PRODUCTION
INSULIN
Diabetes
GLUCOSE UPTAKE BY FAT
Diabetes
SUGARS
GLUCOSE UPTAKE BY MUSCLE
Diabetes also affects the effect of insulin on production of glucose by the liver cells
GLYCOGEN GLUCOSE
Diabetes HEPATIC GLUCOSE PRODUCTION
GLUCOSE UPTAKE BY FAT
INSULIN
SUGARS
GLUCOSE UPTAKE BY MUSCLE
If we were to illustrate the biological variables and relationships in the model that affect the metabolism of glucose, it would look something like this
Family history
Gliburide
Insulin treatment
Insulin level
Unexplained variance in OGT
Sex Type 1 Diabetes feature Race/ ethnicity
Type 2 Diabetes feature
Joint Diabetes feature
Insulin production (Pancreas) Insulin efficiency (Muscle)
Age
BMI
Height
Insulin efficiency (Liver)
Age, sex, race/ ethnicity
Weight
Diabetes blood pressure factor Peripheral resistance
Glucose uptake by muscle
OGT
OGTT test
Random plasma glucose
Random plasma glucose test
Random error and variation
FPG test
FPG HbA1c test
Glucose production by liver Untreated insulin level
Care processes
Normal liver glucose production
Urine ketone test
Metformin
Fractional change in Insulin
Ketoacidosis
Diet and exercise
FPG
Hypoglycemia
HDL cholesterol
Diabetes diagnosis
LDL cholesterol
Triglyceride s
Systolic blood pressure
Coronary artery stenosis
Smoking
Diabetes cardiac risk factor
Propensity to blurred vision
To treatment models
Patient takes action Blurred vision Memory
Mean arterial pressure
Propensity to polyuria
Polyuria
FPG Perception
Cardiac output
Arterial compliance
Pulse \ pressure To the Retinopathy model
To the Nephropath y model
To the Neuropathy model
To the Coronary artery disease model
Propensity to fatigue
Fatigue
Propensity to thirst
Thirst
A KAISER PERMANENTE INNOVATION
All of that, and many, many more variables that are important to the complications of diabetes and to other diseases, are being calculated continuously in every simulated person in the model
Family history
Gliburide
Insulin treatment
Insulin level
Unexplained variance in OGT
Sex Type 1 Diabetes feature Race/ ethnicity
Type 2 Diabetes feature
Joint Diabetes feature
Insulin production (Pancreas) Insulin efficiency (Muscle)
Age
BMI
Insulin efficiency (Liver)
Age, sex, race/ ethnicity
Glucose uptake by muscle
Random plasma glucose test
Random error and variation
Diabetes diagnosis
FPG test
HbA1c test
Glucose production by liver Untreated insulin level Normal liver glucose production
UKPDS data Weight
OGTT test
FPG
Metformin
Height
OGT
Random plasma glucose
Diet and exercise
Diabetes blood pressure factor
HDL cholesterol
LDL cholesterol
Triglyceride s
Peripheral resistance
Mean arterial pressure
Systolic blood pressure
Coronary artery stenosis
Cardiac output
Arterial compliance
Pulse \ pressure
Smoking
Diabetes cardiac risk factor
Care processes
Urine ketone test
Fractional change in Insulin
Ketoacidosis
FPG
Hypoglycemia
Propensity to blurred vision
Blurred vision
Propensity to polyuria
Polyuria
Propensity to fatigue
Fatigue
Propensity to thirst
Thirst
To treatment models
Patient takes action
Memory
FPG Perception
To the Retinopathy model
To the Nephropath y model
To the Neuropathy model
To the Coronary artery disease model
A KAISER PERMANENTE INNOVATION
And there are lots of simulated people, thousands in fact, all of them with different risk factors, physiologies, behaviors, et cetera. (The differences are shown as different colors of their aprons)
A KAISER PERMANENTE INNOVATION
Thanks Joe, you can go back to the model now.
You’re welcome. Good bye
A KAISER PERMANENTE INNOVATION
That was “physiology-based”. Let’s move on now. Here’s what we mean by “broad and deep” • Object oriented • Continuous • Physiology based • Very deep and very broad • and it operates at the level of detail that clinicians and administrators consider essential for making decisions A KAISER PERMANENTE INNOVATION
“Very broad and very deep ” means that the model includes • Not only – Anatomy, Physiology, Pathology, Signs and symptoms, Tests and treatments
• But also – Patient and provider behaviors – Care processes: e.g. guidelines, disease management, CQI – System resources: e.g. facilities, personnel, equipment, supplies, costs … A KAISER PERMANENTE INNOVATION
To get the idea of “very deep and very broad”, let’s follow a problem from the cellular level to the parking lot • All the simulated people in the model have all the important organs. E.g. hearts, kidneys, immune systems… • All the simulated organs have all the important parts. E.g. hearts have coronary arteries, ventricles, myocardium, sino-atrial node… • All the part have all the important subparts. e.g. arteries have lumens, walls… • All the organs and their parts have functions. e.g. arteries carry blood to the myocardium A KAISER PERMANENTE INNOVATION
There’s more •
Things can go wrong with the organs or their functions. e.g. coronary arteries can occlude.
•
When something goes wrong, it affects other things. e.g. when arteries occlude, blood flow to the myocardium is reduced. When blood flow is reduced, the feels pain (angina).
•
All the simulated patients have behaviors; when the pain reaches a threshold, the patient makes a simulated call to a simulated hospital.
•
Simulated telephone operators at simulated call centers use simulated protocols to triage calls. A KAISER PERMANENTE INNOVATION
And still more • Patients go to simulated emergency departments. (This is where the parking lot comes in) • They are seen by simulated personnel (e.g., nurses). • Simulated tests are performed…tests use equipment and supplies • Diagnoses are made…and mistakes are made • Patients are admitted, rooms are occupied, … • Treatments are given… A KAISER PERMANENTE INNOVATION
You get the idea. “Very broad” and “very deep” means that the effects of any encounter keep ramifying through the simulated health care system, just as happens in the real world • • • •
Logistics happen… Utilization occurs… Outcomes occur… Costs occur… A KAISER PERMANENTE INNOVATION
There’s one more thing to discuss, the level of detail • • • • •
Object oriented Continuous Physiology based Very deep and very broad It operates at the level of detail that clinicians and administrators consider essential for making decisions A KAISER PERMANENTE INNOVATION
The level of detail is determined by the people who will use the model • If a clinician says that a particular variable is critical to their own thinking, and the model won’t be credible without it … • We include the variable – e.g. ejection fraction, insulin level, “beta cell fatigue”, peripheral resistance • Ditto for administrators – E.g. there are 37 different types of office visits A KAISER PERMANENTE INNOVATION
Now let’s talk about: • What the Archimedes model is • How it can be used • How we know it works
A KAISER PERMANENTE INNOVATION
The purpose of Archimedes is to create a virtual world • • • • • • • •
Virtual people who have virtual physiologies get virtual diseases have virtual signs and symptoms go to virtual doctors get virtual tests and treatments and have virtual outcomes just like real people A KAISER PERMANENTE INNOVATION
If it works, then we can use the virtual world to try out, evaluate, explore, optimize, plan, improve, predict…lots of different things. Such as… • • • • • •
Guidelines Disease management programs Nursing algorithms Changes in care processes Continuous quality improvement programs Performance measures and targets A KAISER PERMANENTE INNOVATION
And more… • • • •
Priority setting Strategic goals Research How “ideal” research trials translate to “real” clinical settings • Logistics, use of resources • Costs, cost-effectiveness, and value • Planning A KAISER PERMANENTE INNOVATION
The idea is that we can use the virtual world to learn the effects of lots of different types of interventions that would be infeasible to study through empirical methods (more research), for a variety of reasons: • • • •
Too high a cost Too long time needed for a new study Too many patients needed Unwillingness of patients and/or physicians to participate • Too large a number of options to study • Technologies that are changing too rapidly A KAISER PERMANENTE INNOVATION
This is very important, because • An empirical study – e.g. an evaluation study or clinical trial – of a single intervention will – cost hundreds of thousands, or even hundreds of millions of dollars – require hundreds, or thousands of people – take years • Whereas an Archimedes simulation takes much less time and costs less A KAISER PERMANENTE INNOVATION
Sounds good. And I’m happy to help out. But if you don’t mind, I’ve got a question. All this is premised on an assumption that it works right. How do you know that it works? I mean, I know that my equations are working fine. But I’m not so certain about the other jokers who are in here with me. A KAISER PERMANENTE INNOVATION
Thanks Joe, that is indeed a crucial question: • What the Archimedes model is • How it can be used • How do we know it works?
A KAISER PERMANENTE INNOVATION
Here’s how: • We compare what happens in the virtual world with what happens in the real world, • in lot’s of different settings, • that test the parts of the model that will be used for the types of applications we want to do – i.e. similar people, similar treatments, similar outcomes A KAISER PERMANENTE INNOVATION
The best way to do this is to use clinical trials because we know the most about them A trial involves people who meet the entry criteria for the trial
The trial is conducted
And the outcomes are measured
They get the treatments specified in the protocols of the trial A KAISER PERMANENTE INNOVATION
We use the virtual world of the model to simulate the real-world trial People Treatments We use the same criteria to select people We have simulated physicians follow the same treatment protocols
Real clinical trial
Real Outcomes
And we compare the results We let the model do its thing
We count the outcomes, using the same definitions and protocols A KAISER PERMANENTE INNOVATION
There are 10 steps involved in performing a validation 1. We start with a large population of simulated people, just like a simulated city 2. We identify the inclusion criteria for the trial 3. We randomly select from the large population a sample who meet the inclusion criteria for the trial 4. Confirm that major characteristics match (“Table 1”) 5. Randomize the simulated people A KAISER PERMANENTE INNOVATION
There are 10 steps involved in performing a validation (Cont’d) 6. Identify the treatment protocols used in the trial 7. Have simulated providers apply the treatment protocols to the simulated people 8. Have the simulated providers apply the follow-up protocols 9. Record the results seen in the real trial 10. Compare the simulated results to the real results A KAISER PERMANENTE INNOVATION
You can think of these validations as being previews of real applications • We used the populations that were in the trials – But we could have used the population that would be candidates for your guideline (or performance measure, etc)
• Similarly for the tests, treatments, outcomes, etc. A KAISER PERMANENTE INNOVATION
Archimedes has been validated against these trials, so far MRC
HOPE
DCCT primary
SHEP
4-S
DCCT secondary
HHS
CARE
MICRO-HOPE
LLRC
LIPID
IRMA
WOSCOPS DPP
Lewis
HPS
IDNT
UKPDS
VA-HIT A KAISER PERMANENTE INNOVATION
Here’s an example: the Heart protection Study • Population: adults age 40 – 80, at high risk of MI because of high LDL, or other arterial occlusive disease, or diabetes • Treatments: Simvastatin vs. placebo • Size: 20,500 • Duration: 6 years A KAISER PERMANENTE INNOVATION
This was the rate of major coronary artery events in the placebo and treated groups Major Coronary Events in Heart Protection Study 0.14
Solid lines are the real results
Fraction of patients
0.12 0.1
Placebo group
0.08 0.06
Treated group
0.04 0.02 0 0
0.5
1
1.5
2
2.5 Years
3
3.5
4
4.5
5
A KAISER PERMANENTE INNOVATION
The dotted lines showed what the model calculated Major Coronary Events in Heart Protection Study 0.14
Dotted lines are the model’s results Fraction of patients
0.12 0.1
Placebo group 0.08 0.06
Treated group 0.04 0.02 0 0
0.5
1
1.5
2
2.5 Years
3
3.5
4
4.5
5
A KAISER PERMANENTE INNOVATION
Here’s another example, the Diabetes Prevention Program • Population: men and women over age 25. broad range of racial and ethnic groups. Prediabetes (IGT or IFG) • Treatments: intensive lifestyle vs. Metformin vs. standard care • Size: 3000 • Mean duration: 2.8 years A KAISER PERMANENTE INNOVATION
In this case, the results were calculated by the model before the real results were known. This is what the model predicted. DPP: Diabetes Progression 0.5
Control Metformin Lifestyle
0.45 0.4
Fraction
0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 0
1
2
3
4
5
Time (years) A KAISER PERMANENTE INNOVATION
The dotted lines are what the model predicted. The solid lines are the results that were eventually published. DPP: Diabetes Progression 0.5
Control Metformin Lifestyle
0.45 0.4
Fraction
0.35 0.3 0.25 0.2 0.15 0.1 0.05 0 0
1
2
3
4
5
Time (years) A KAISER PERMANENTE INNOVATION
Here’s an example of a long term trial that measured the effects of treatment on complications of diabetes: UKPDS • Population: middle aged men and women, with newly diagnosed type 2 diabetes • Treatments: intensive treatment vs. conventional treatment • Size: 3900 • Duration: 15 years A KAISER PERMANENTE INNOVATION
This shows the effect of treatment on the most important outcome: heart attacks UKPDS: MI (fatal and non-fatal) 0.3
The solid lines are the real results
Fraction of patients
0.25
Conventional treatment
0.2
0.15
Intensive treatment
0.1
0.05
0 0
2
4
6
8 Time (years)
10
12
14
A KAISER PERMANENTE INNOVATION
This is what was calculated by the model UKPDS: MI (fatal and non-fatal) 0.3
The dotted lines are the model’s results
Fraction of patients
0.25
Conventional treatment
0.2
0.15
Intensive treatment
0.1
0.05
0 0
2
4
6
8 Time (years)
10
12
14
A KAISER PERMANENTE INNOVATION
We have done this for 74 different combinations of populations, treatments and outcomes. This chart compares results calculated by the model (y-axis) against results of the real trial (x-axis). Results calculated by model
0.6
Each dot represents an arm of a trial. The real result of the trial is plotted against the result calculated by the model. Perfect correspondence would be the 45º line
0.5
0.4
0.3
0.2
0.1
0 0
0.1
0.2
0.3
0.4
Results from trials
0.5
0.6 A KAISER PERMANENTE INNOVATION
One would not expect perfect correspondence because of random factors, related to the number of people in the trial • 71 of 74 are well within sampling error • The other 3 have good explanations – either it just missed (e.g. p = .04) (which is to be expected statistically) – or the description of the trial was incomplete • 54 of 74 are within ± 1 standard deviation • For all 74 exercises: r = 0.99 A KAISER PERMANENTE INNOVATION
For some of the trials, some of the data from the trial were used to help build parts of the model. The other trials are 100% independent • For the exercises that were not used at all to build the model (100% independent), the correlation between the model and the trial was still extremely high • The correlation was still r = 0.99 A KAISER PERMANENTE INNOVATION
These validations are important for several reasons • They give us confidence that for applications that are spanned by validations, the model is accurate • They illustrate the types of applications that the model can do • No other model of clinical medicine has been validated in this way • The alternative to the model, expert judgment, has not been validated in this way either (no offense intended)
A KAISER PERMANENTE INNOVATION
The “span” of the validations is important, because it indicates the types of populations, organ systems, and treatments we can be confident about
A KAISER PERMANENTE INNOVATION
Imagine that the disease that we want to understand is represented by an island. We need to completely map out and reach every part of that island
A KAISER PERMANENTE INNOVATION
Imagine that the available research can be represented as radio beacons on the island. The bigger and better the trial, the wider its signal.
A KAISER PERMANENTE INNOVATION
Now suppose that Archimedes has been validated against all of those trials. Using this visual image, we can talk about the usefulness of Archimedes for new applications
A KAISER PERMANENTE INNOVATION
If you ask it a question about this part of the island (A), it should do extremely well
A
A KAISER PERMANENTE INNOVATION
If you ask it a question about this part of the island (B), it should do very well
B
A KAISER PERMANENTE INNOVATION
If you ask it a question about this part of the island (C), it should do fairly well
C
A KAISER PERMANENTE INNOVATION
If you ask it a question about this part of the island (C), it should do fairly well, but we’d like to see a new trial done down here
C
A KAISER PERMANENTE INNOVATION
If you ask it a question about this part of the island (D), we’ll say “OK, but only use the model for “what if” type questions We’d rather help you design a new trial
D
A KAISER PERMANENTE INNOVATION
If you ask it a question about that is out in the ocean (E), We’ll say “Archimedes can’t do that yet. Help us raise some money and we’ll build a new model for that”
E
A KAISER PERMANENTE INNOVATION
With that in mind, it is important that Archimedes has been validated for a wide range of populations
Average risk Hypercholesterolemia Diastolic hypertension Systolic hypertension Many risk factors Angina or MI Diabetes MI average Cholesterol MI high Cholesterol Pre diabetes
Newly diagnosed diabetes Type 1, uncomplicated Type 1, retinopathy Type 1, moderate to severe nephropathy Type 2, uncomplicated Type 2, mild nephropathy Type 2, moderate nephropathy Young, Middle age, Old A KAISER PERMANENTE INNOVATION
…and organ systems • • • • •
Liver Pancreas Heart Vascular Nerves
• • • • • •
Muscle Fat Kidneys Eyes Lungs Gut
A KAISER PERMANENTE INNOVATION
…and treatments • • • • • • •
Nothing (placebo) Cholestyramine Gemfibrozil Anti-hypertensive Pravastatin Simvastatin ACE Inhibitors
• Angiotensin –IIreceptor antagonists • Insulin • Metformin • Sulphonylurea • General diet advice • Intensive lifestyle A KAISER PERMANENTE INNOVATION
That’s what we mean when we say that Archimedes is anchored to reality Biological modeling Clinical medicine Care processes
(74 anchors)
System resources A KAISER PERMANENTE INNOVATION
What does all this mean? • It is possible to write equations that represent human physiology, disease, treatments and outcomes using existing information • In the “virtual world” created by these equations, simulated patients behave like patients in the real world, … • …at least as we know it through the most important epidemiological studies and clinical trials A KAISER PERMANENTE INNOVATION
It means the virtual world can be used for many purposes, such as • • • • • • •
Guidelines Performance measures Disease management programs Continuous quality improvement Strategic goals and priority setting Research planning Estimating patient-specific outcomes A KAISER PERMANENTE INNOVATION
And that’s good, because it’s a whole lot easier to explore problems and programs in the virtual world • Much faster • Much less expensive • Much more flexible • Can explore many more options • Can tell you the critical points to watch A KAISER PERMANENTE INNOVATION
If you want to use the model, there is one more thing you will need to understand • Real people like you will still have to make the final decisions • Archimedes will give you much better information than you’ve ever had before • But there are always elements of a decision that can not be quantified and that require value judgments • This is the role of humans • Thus the model is a just a tool -- a very powerful tool, but just a tool A KAISER PERMANENTE INNOVATION
But watch out. I’m gaining on you.
Family history
Gliburide
Insulin treatment
Insulin level
Unexplained variance in OGT
Sex Type 1 Diabetes feature Race/ ethnicity
Type 2 Diabetes feature
Joint Diabetes feature
Insulin production (Pancreas) Insulin efficiency (Muscle)
Age
BMI
Insulin efficiency (Liver)
Age, sex, race/ ethnicity
Glucose uptake by muscle
Random plasma glucose test
Random error and variation
Diabetes diagnosis
FPG test
FPG HbA1c test
Untreated insulin level Normal liver glucose production
UKPDS data Weight
OGTT test
Glucose production by liver
Metformin
Height
OGT
Random plasma glucose
Diet and exercise
Diabetes blood pressure factor
HDL cholesterol
LDL cholesterol
Triglyceride s
Peripheral resistance
Mean arterial pressure
Systolic blood pressure
Coronary artery stenosis
Smoking
Diabetes cardiac risk factor
Care processes
Urine ketone test
Fractional change in Insulin
Ketoacidosis
FPG
Hypoglycemia
Propensity to blurred vision
Blurred vision
Propensity to polyuria
Polyuria
To treatment models
Patient takes action
Memory
FPG Perception
Cardiac output
Arterial compliance
Pulse \ pressure To the Retinopathy model
To the Nephropath y model
To the Neuropathy model
To the Coronary artery disease model
Propensity to fatigue
Fatigue
Propensity to thirst
Thirst
A KAISER PERMANENTE INNOVATION