850 likes | 1.01k Views
Avoiding Bias Due to Unmeasured Covariates. Presentations in this series Overview and Randomization Self-matching Proxies Intermediates Instruments Equipoise. Alec Walker. X. Randomization. Self-matching. Proxies. Proxies. Intermediates. Intermediates. Instruments. D. T. X.
E N D
Avoiding Bias Due toUnmeasured Covariates Presentations in this series Overview and Randomization Self-matching Proxies Intermediates Instruments Equipoise Alec Walker
X Randomization Self-matching Proxies Proxies Intermediates Intermediates Instruments D T
X Randomization Self-matching Proxies Proxies Intermediates Intermediates Instruments D T
X When strong proxies for the possible confounding determinants of exposure indicate no effect on exposure, there is correspondingly strong evidence for an absence of confounding. Randomization Self-matching Proxies Proxies Intermediates Intermediates Instruments D T
X Other, possibly unmeasured, non-confounding determinants of exposure are the sole determinants of treatment variation. Proxies UT D T
Where we’re going When different doctors give different treatments to similar patients, there must be a variety of opinions about therapy in the clinical community. The presence of differing therapeutic opinion has been termed “clinical equipoise” and is a permissive condition for conducting an ethical clinical trial. Clinical equipoise, identified in observational data as “empirical equipoise,” is also a permissive state for comparative effectiveness research.
Σ Provider
Σ Provider
Rx Σ Provider
Σ ? Provider
Σ ? Provider Patient
? complaint
? Σ complaint
? Σ complaint training norms colleagues experience
? Σ symptoms complaint training norms colleagues experience
? Σ signs symptoms complaint training norms colleagues experience
? Σ history signs symptoms complaint training norms colleagues experience
? Σ illnesses history signs symptoms complaint training norms colleagues experience
medications ? Σ illnesses history signs symptoms complaint training norms colleagues experience
test results medications ? Σ illnesses history signs symptoms complaint training norms colleagues experience
test results medications ? Σ illnesses history signs symptoms complaint training norms colleagues experience
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ training norms colleagues experience
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Rx B training norms colleagues experience
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Rx B Σ training norms colleagues experience training norms colleagues experience Rx C
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Σ Rx B Σ training norms colleagues experience training norms colleagues experience training norms colleagues experience Rx C Rx D
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Σ Rx B Σ training norms colleagues experience training norms colleagues experience training norms colleagues experience Rx B Rx A
test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Σ Rx B Σ training norms colleagues experience When the same patient has an equal chance of getting Rx A or Rx B, depending only on which doctor he happens to visit, the treating community is in EQUIPOISE. training norms colleagues experience training norms colleagues experience Rx B Rx A
Personal ambivalence “If a physician knows that these treatments are not equivalent, ethics requires that the superior treatment be recommended. “Following Fried, I call this state of uncertainty about the relative merits of A and B ‘equipoise.’ ” Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145. Reference is to Charles Fried. Medical Experimentation: Personal Integrity and Social Policy. Amsterdam: North-Holland Publishing, 1974
Shortcomings of ambivalence in RCTs Threats to personal equipoise • Studies that motivated the trial • Early results of the trial itself • Findings on secondary endpoints: QoL • Change in experimenter’s understanding of • Relevant data external to the RCT • Views of other competent observers Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
Failed rescue attempts for personal equipoise Conceal results from investigators through a Data and Safety Monitoring Committee Give the patient responsibility for valuing the relative merits of the treatments Informed Consent Frankly admit the social need for reliable health research. Medical Conscription Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
Retained for other reasons Conceal results from investigators through a Data and Safety Monitoring Committee Give the patient responsibility for valuing the relative merits of the treatments Informed Consent Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
Autonomy Conceal results from investigators through a Data and Safety Monitoring Committee Give the patient responsibility for valuing the relative merits of the treatments Informed Consent Frankly admit the social need for reliable health research. Medical Conscription Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
When we do RCTs “The standard treatment is A, but some evidence suggests that B will be superior.” “Or there is a split in the clinical community, with some clinicians favoring A and others favoring B …” “… an honest, professional disagreement among expert clinicians …” Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
When we do RCTs “The standard treatment is A, but some evidence suggests that B will be superior.” “Or there is a split in the clinical community, with some clinicians favoring A and others favoring B …” “… an honest, professional disagreement among expert clinicians …” “At this point a state of ‘clinical equipoise’ exists … A state of clinical equipoise is consistent with a decided treatment preference on the part of the investigators.” Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145.
Clinical equipoise and community “… there is a split in the clinical community ” “There is no consensus within the expert clinical community about the comparative merits…” “… clinical equipoise persists as long as [available] results are too weak to influence the judgement of the community of clinicians.” “As Fried has emphasized, competent (hence, ethical) medicine is social rather than individual in nature.” Benjamin Friedman. Equipoise and the ethics of clinical research. N Engl J Med 1987;317:141-145. Reference is to Charles Fried. Medical Experimentation: Personal Integrity and Social Policy. Amsterdam: North-Holland Publishing, 1974
What prescribers think, what they do test results medications ? Σ illnesses Rx A history In the absence of knowledge of prescribers’ beliefs about alternative treatments, we might assume that each prescriber’s behavior reflects belief about best treatment for the individual patient, given the constraints of their shared environment. signs symptoms complaint training norms colleagues experience
A community of prescribers test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Σ Rx B Σ training norms colleagues experience training norms colleagues experience When the same patient has an equal chance of getting Rx A or Rx B, depending only on which doctor he happens to visit, the treating community is in EMPIRICAL EQUIPOISE. training norms colleagues experience Rx B Rx A
A community of prescribers test results medications ? Σ illnesses Rx A history signs symptoms complaint training norms colleagues experience Σ Σ Rx B Σ training norms colleagues experience training norms colleagues experience We will take empirical equipoise in the population of prescribers as evidence of clinical equipoise in the prescriber community, in just the sense meant by Friedman. training norms colleagues experience Rx B Rx A
Modeling the counterfactual We can’t observe what different doctors would do with the same patient.
Modeling the counterfactual In general, the patients who go to different doctors are not identical. Σ Σ Σ Σ training norms colleagues experience training norms colleagues experience training norms colleagues experience training norms colleagues experience Rx B Rx A Rx B Rx A
Modeling the counterfactual But what if switching patients between doctors made no difference to the treatment assignment? Σ Σ Σ Σ training norms colleagues experience training norms colleagues experience training norms colleagues experience training norms colleagues experience Rx B Rx A Rx B Rx A
Modeling the counterfactual We’d say that the treatment choices are probably most reflective of prescriber beliefs. Σ Σ Σ Σ training norms colleagues experience training norms colleagues experience training norms colleagues experience training norms colleagues experience Rx B Rx A Rx B Rx A
Modeling the counterfactual The patients can’t be switched between doctors in an observational study.
Modeling the counterfactual The patients can’t be switched between doctors in an observational study. Instead of asking whether the patient per se is determinative of doctor’s treatment choice, we can ask whether any observed patient characteristics tend to predict treatment.