Flashcards in Research methods/ stats/ethics/Canmeds Deck (81):

81

## What is Sensitivity

###
The ability to confirm the presence of disease

true positive rate, or the recall rate

1

## What is specificity

###
The ability to confirm absence of the disease

true negative rate

2

## Positive predictive valve

### the probability of disease if the test is positive

3

## Negative predictive value

### Is the probability of absence of disease if the test is negative

4

## What is null hypothesis

### defined as lack of difference between the two treatments

5

## What is a type 1 error

###
rejecting the null hypothesis when it is true

False positive rate

Occurs when a statistically significant difference is found, when really there is no difference

It is based on the choice of the level of statistical significant p < 0.05

6

## What is a type 2 error

###
not rejecting the null hypothesis when it is false

Chance that the study finds no difference when in fact there is a difference

Chance of a type II error is inversely related to the sample size and to the statistical power

7

##
List Bias associated with meta anlalysis studies

What techniques can be done to reduce bias?

What technique to test for Heteogenity

List 2 strengths of Metanlysis

###
1. Publication bias/Search Bias/Selection bias

2. "Funnell plot"

3. Forest Plot--and a subsequent cochran Q- test

4. Strengths:

a. Increased Effective sample size which greatly increases more outcomes and variable that can be examined

b. Allows examining of rare events

8

##
What is major strength of RCT compared to Observational study?

List 2 ways that Observational studies attempt to account for weakness

List 3 potential limitations of RCT

###
RCT eliminates selection bias

Propensity analysis and Risk adjustment techniques (such as regression or analysis of variance)

weakness of RCT

a. decreased generalizability--specific inclusion/exclusions

b. Inadequate statistical power --expensive to enroll pts

c. Follow-up and approach to treatment may not be representative of real life

9

## What is c statistics

###
probability that predicting the outcome is better than chance.

Used to compare the "goodness of fit" of logistic regression models, values for this measure range from 0.5 to 1.0.

value of 0.5 indicates that the model is no better than chance at making a prediction of membership in a group and a value of 1.0 indicates that the model perfectly identifies those within a group and those not.

Models considered reasonable when the C-statistic is higher than 0.7 and strong when C exceeds 0.8

10

## What is p value

###
p-value is the probability of obtaining a test statistic at least as extreme as the one that was actually observed, assuming that the null hypothesis is true. One often "rejects the null hypothesis" when the p-value is less than the predetermined significance level which is often 0.05 or 0.01, indicating that the observed result would be highly unlikely under the null hypothesis. Many common statistical tests, such as chi-squared tests or Student's t-test, produce test statistics which can be interpreted using p-values.

11

## What is null hypothesis

###
the null hypothesis refers to a general or default position: that there is no relationship between two measured phenomena,or that a potential medical treatment has no effect.Rejecting or disproving the null hypothesis – and thus concluding that there are grounds for believing that there is a relationship between two phenomena or that a potential treatment has a measurable effect – is a central task in the modern practice of science, and gives a precise sense in which a claim is capable of being proven false.

12

## What is C statistic

###
A measure that indicates how well a prediction model or risk score discriminates between pts who do and who do not have an event.

e.g., "how well a value (predicted lactate clearance) is able to discriminate between patients who had an event (death, MI, etc)

A C-statistic is good if it's greater then 0.8 as a good utility, valves from 0.7 to 0.8

A value of 1.0 is assigned to a prediction model or risk score with a perfect ability to discriminate between pts who do and do NOT have an event

13

## What's type I error an type II error

###
Itype I error (or error of the first kind) is the incorrect rejection of a true null hypothesis. A type II error (or error of the second kind) is the failure to reject a false null hypothesis. A type I error is a false positive. Usually a type I error leads one to conclude that a thing or relationship exists when really it doesn't.

A type II error is a false negative.

When comparing two means, concluding the means were different when in reality they were not different would be a Type I error; concluding the means were not different when in reality they were different would be a Type II error.

14

## What is odds ratio

### The odds ratio is a measure of effect size, describing the strength of association or non-independence between two binary data values. It is used as a descriptive statistic, and plays an important role in logistic regression. Unlike other measures of association for paired binary data such as the relative risk, the odds ratio treats the two variables being compared symmetrically, and can be estimated using some types of non-random samples.

15

## What is relative risk

###
In statistics and mathematical epidemiology, relative risk (RR) is the risk of an event (or of developing a disease) relative to exposure. Relative risk is a ratio of the probability of the event occurring in the exposed group versus a non-exposed group

In a simple comparison between an experimental group and a control group:

A relative risk of 1 means there is no difference in risk between the two groups.

An RR of < 1 means the event is less likely to occur in the experimental group than in the control group.

An RR of > 1 means the event is more likely to occur in the experimental group than in the control group.

16

##
If a patient is incapable of a decision the order of who is selected is?

What ethical principle justifies not obtaining informed consent

###
A person specified by the patient when capable

A court appointed person

A spouse

A child

A brother

relative or friend

Beneficence is the ethical principle

17

## The standards of disclosure in western legal systems

###
Professional standard: what other physicians tell the patient

Reasonable person standard: what a reasonable person would want to know.

Particular person standard: What a reasonable person in the particular circumstance as the patient would want to know

18

## What is Survival Analysis

###
involves the modeling of time to event data; in this context, death or failure is considered an "event" in the survival analysis literature – traditionally only a single event occurs for each subject, after which the organism or mechanism is dead or broken.

19

## What is Hazard ratio

###
In survival analysis, the hazard ratio (HR) is the ratio of the hazard rates corresponding to the conditions described by two levels of an explanatory variable.

Example, in a drug study, the treated population may die at twice the rate per unit time as the control population. The hazard ratio would be 2, indicating higher hazard of death from the treatment. Or in another study, men receiving the same treatment may suffer a certain complication ten times more frequently per unit time than women, giving a hazard ratio of 10

20

##
What is major strength of RCT compared to Observational study?

List 2 ways that Observational studies attempt to account for weakness

List 3 potential limitations of RCT

###
RCT eliminates selection bias

Propensity analysis and Risk adjustment techniques (such as regression or analysis of variance)

weakness of RCT

a. decreased generalizability--specific inclusion/exclusions

b. Inadequate statistical power --expensive to enroll pts

c. Follow-up and approach to treatment may not be representative of real life

21

## What are key aspects of PROFESSIONAl

###
Committed to the health and well-being of individuals and society through ethical practice, profession-led regulation, and high personal standards of behaviours

Comitment to clinical competence, the embracing of appropriate attitudes and behaviors, integrity, altriusm, personal well being and to the promotion of the public good within their domain

22

##
What is major strength of RCT compared to Observational study?

List 2 ways that Observational studies attempt to account for weakness

List 3 potential limitations of RCT

###
1. Publication bias/Search Bias/Selection bias

2. "Funnell plot"

3. Forest Plot--and a subsequent cochran Q- test

4. Strengths:

a. Increased Effective sample size which greatly increases more outcomes and variable that can be examined

b. Allows examining of rare events

23

## Describe levels of Evidence

###
level A evidence = data derived from multiple randomized trials or metal-analyses

Level b: data from single randomized trial or non randomized trial

Level c: only consensus opinion from experts

24

## Five Conditions that must be met for ethical research

###
A: The existence of clinical equipoise

A: Good design

A: Sound foundation of previous work must give good reason to believe that the proposed interventions will achieve the intended result

A: Research interventions are not likely to cause tserious harm to the research subjects

A: Prior approval by a Research Ethics Board

25

## Define clinical equipipose

### This exists when the expert medical opinion remains divided over the best choice among treatment options; the medical community is unable to achieve consensus on the preferred treatment

26

## Distinguish euthanasia and assisted suicide from decisions to forego treatment

###
A: Euthanasia and assisted suicide involve the injection of a lethal substance or the provision of a lethal overdose

A: Decisions to forego treatment involve the non-initiation or discontinuation of a life-sustaining treatment such as CPR, ventilator, tube feeding, etc. The law permits discontinuation, even though it leads to death, under defined conditions

27

## Define competence

###
A: Possession of the required knowledge, skill, and experience to perform a particular task reliably and produce an appropriate outcome

A: It is a categorical variable; one is competent, or not, to provide a particular service or perform a particular operation

28

## What are the elements of informed consent

###
Capacity: the patient is able to understand the risks and benefits of treatment vs non-treatment

Voluntariness: The patient is not subjected to coercion

Disclosure: the patient is informed enough to give consent

the right to accept or refuse treatment is preserved by the charter of rights in canada

29

## Q: What are the 3 standards for how the decision should be made, in decreasing order of priority?

###

A: Wishes – Prior expressions by the patient, while competent that seem to apply to the actual decision that needs to be made

A: Values and beliefs

A: Best interests – This is more important for children, where the decision maker is usually the parent; decisions should be respected unless they would cause direct and serious harm to the child

30

## Q: What are the 3 important aspects to informed consent as per the Royal College?

###

A: Disclosure – Information about the risks and benefits of the proposed test or treatment as well as any alternatives, presented in language that the patient can understand

A: Capacity – The ability to understand and appreciate the consequences of a particular decision or lack of decision; If in doubt, consultation from a psychiatrist, hospital attorney, or ethicist may be helpful, the ultimate judge of a patient's capacity is court; If the patient is incapable, seek consent from the appropriate substitute decision maker

A: Voluntariness – The ability to make treatment choices without undue external coercion

31

## What are the 7 CanMEDS

###
Scholar

Manager

Health Advocate

Collaborator

Communicator

Professional

Medical expert

32

## Q: What are the 7 CanMEDs roles?

###

A: Medical expert – Diagnostic and Therapeutic skills, effective patient care, access and apply information, consultation

A: Communicator – Therapeutic relationship, relevant history, listen effectively, discuss appropriate information

A: Collaborator – Consult effectively, multidisciplinary team

A: Manager – Utilize and allocate resources, health care organization, use information technology

A: Scholar – CME, facilitate learning, critically appraise the literature, contribute to new knowledge

A: Health advocate – Identify determinants of health, for patients and community, recognize and respond

A: Professional – Integrity, honesty, and compassion, interpersonal behaviours, practice medicine ethically consistent with obligations

33

## List key issues of SCHOLAR

###
life long commitment to reflective learning, as well as creation, dissemination, application and translation of medical knowledge

Pursuit of matering their domain of expertise, crtical appraise sources of medical info

Facilitate the education of their students, pts, colleagues, new knowledge,

34

## List 8 principles of ethics

###
Autonomy--persons right to self rule

Beneficence--promote well being of others

Confidentiality--persons right to decide how and to whom information is communicated

Covenant-binding agreement between two or more parties

Fiduciary relationship- relationship founded on faith and trust

Informed consent--

Justice--

Maleficience--the act of committing hard

35

## List barriers to obtaining consent in non-english pt

###
Disclosre

Accuracy

Autonomy

voluntariness

Impartiality

Capacity/competency

Doctor-patient confidentiality

36

## List exceptions to the doctor-patient confidentiality act

###
A Third party who may be harmed should be informed

Spousal or child abuse must be reported to authorities

Some communicale diseases must be reported to health authorities

37

## What is confidentiality

###
the right to privacy prohibits and MD from revealing information unless pt waives privledge

HIPPA--Health care information Privacy and protection Act

Legal Issues--if neccessary to avert danger to others, or the needs of society

38

## 4 Reasons why you have to tell a pt about an operation

###
Autonomy: pt has freedom to choose own path

Fidelity: trusting theapeutic relationship with pt

Veractiy: truthfulness with pt

Disclosure:

Therapeutic privilege:

39

## What is required for Informed Consent

###
Nature of Procedure

Benefits/Objectives

Alternatives

Clear indications for surgery

Risks/Possible complications

40

## What are important aspects of collaborator

###
Work within a healthcare team to achieve optimal patient care

Collaborate with interprofessional health care team

Work to resolve interprofessional conflict

41

## List key aspects of Communicator

###
Physicians effectively facilitate the doctor patient relationship and the dynamic exchanges that occur before, during, and after the medical encounter

Shared decision-making and effect dynamic interactions with patients, families, caregivers, other professionals, and important other individuals

Rapport and trust, ethical therapeutic relationships with patients

convey relevant information to collegues

42

## List important aspects of MANAGER

###
1. work as individuals, as members of teams or groups, as participants in the health system locally, reigionally and nationally.

2 prioritize, execute tasks collaboratively with colleagues, and make systematic choices when allocating health care resources.

3. manage their practice and career effectively

4. Employ information technology, life-long learning

43

## List Key aspects of Health Advocate

###
use their expertise and influence to advance the health and well-being of individual patients, communities, and population

recognize their duty and ability to improve the overall health of their patients and the society t

Health promotion, recognize to determinants of Health

44

## What are major point of Medical Expert

###
Integrate all the CanMEDS in a patient centered care

Body of knowledge, clinical skills, procedural skills, and professional attitudes

apply knowledge to collect interpret information and make appropriate clinical decisions

Function as consultants

45

## What are weakness of Randomized Controlled Trials

###
Expensive

Feasibility

Ehthical Issue

Possible lack of external valdity

- ability to generalize to overall population

- strict/inclusion exclusion

- participants enrolling may be different then those that don't agree "Volunteer Bias"

46

## Strengths RCT

###
Provides greatest strength of causal inference

Optimal methodology to rest efficacy of a treatment program

Protects against selection bias and known and unknown confounding variables

Double blinding

- ascertainment bias

- diagnostics suspicion bias

- Detection bias

Method of choice to evaluation small/modest effects

The 2 groups are equal at baseline

47

## Describe 3 times of analytical observation studies

###
Cohort--retrospective or prospective

Case-Control- by definition its retrospective

Cross-section- "snap shot" in time

48

## Describe a Cohort study design

###
Retro-looks at exposure and then finds the outcome in charts

prospective- takes a group that is exposed and another group that is unexposed and follows them forward.

Can attempt to control for confonding variable by

1) Stratifying

2) Multi-variable analysis

49

## Disadvantages of Cohort

###
More subjective to systemic error then RCT (weaker at establishing causation)

Baseline characteristics are not equal--cannot be blinded

Detection bias--increased chance of detecting an abnormality

Selection bias--pt who choose one thing over another differ at baseline

Strength of association cannot be provided as evidence of causation

50

## What is details of Case-control study design

###
"begins at the end"

patient selection is based on whether or they have the disease or outcome

Design is retrospective by definition

Typically 1 ours

Advantage

- More efficient for addressing an assoication between rare outcomes and exposre of interest

- can be done quickly

- less expensive

51

## What disadvantages of case control study design

###
Easy to do poorly

only one outcome can be measured

Prone to Bias

observer bias

recall bias

selection bias

Difficult to choose appropriate control group

can't calculated incidence or prevalence

Confounding effects

Difficult to establish cause and effect

52

## List 2 descriptive observational studies and advantages

###
Case series

Case report

No comparison group/least sophisticated study design

good for highly unusual cases or series

Valuable information on: frequency, natural history, possible determinats of condition

general hypothesis

53

## List 3 types of Systemic reviews

###
Meta-Analysis

Decision Analysis

Economic Analysis

54

## Define Decision Analysis

###
quantitative approach to evaluate relative values of different management options

--each outcome is assigned a probability based on a review of the literature and medical expertise, then these probabilities are statistically analyzed

55

## Describe Economic Analysis

###
Focus on cost

COST-BENEFIT analysis--the costs of medical care and the benefits of reduced loss of net earnings due to preventing premature death or disability are considered

COST-EFFECTIVENESS analysis--determine the costs and effectiveness of an activity or to compare similar alternative activities to determine the relative degree to which they will obtain the desired objectives or outcomes

56

## Define selection bias

###
subjects in the sample are not representative of the population (non random sampling), pts characteristics have an impact on outcomes other than those being studies

57

## Define recall Bias

### relying on a subjects memory with respect to exposure or outcomes

58

## Ascertainment bias

### systemic failure to present equally all classes or persons supposed to represented in the sample

59

## Detection bias

###
bias due to systemic errors in methods of ascertainment, diagnosis or verification of cases in an epidemiologic study

60

## What are confounders

### the illusory association between 2 variable when in fact there is no association--it is caused by a third variable which is correlated with the first two

61

## What is Criteria for Causation (Bradford Hill)

###
1. Strength of Association--How larges is the effect

2. Temporal relationship- does the cause precede the effect

3. Consistency--study findings consistent over numerous reports

4. Biologic plausibility--does the relationship make biological sense

5. Biogloic-gradient--is there a dose-response relationship

6. Evidence: Is there experimental evidence to support or refute the association

7. Specificity: does altering only the cause alter the effect

8. Coherence--does the evidence fit with what is known regarding the history and biology of the outcome

9. Reasoning analogy-- is the observed association supported by similar associations

62

## What are types of validity

###
Internal Validity

External Validity

Construct Validity

Statistical conclusion validity

63

## What is Validity

###
Degree to which the inferences drawn from the study are warranted when account is take of the study methods, the representativeness of the study sample and the nature of the population from which it is drawn

64

## What is is External Validity

###
the generalizability is the degree to which the results of an observation hold true in other settings (does it apply to my practice)

65

## What is Internal validity

###
The degree to which the results of an observations are correct for the patients being studied

66

## Define Reliability

### the extent to which repeated measurements of a relatively stable phenomenon fall closely to each other

67

## List 4 things you need for a sample sized calculation

###
Alpha Error

Beta Error

Standard deviation

Minimally clinically important difference

68

## What is a study's power

###
The ability to detect an association when one truly exists

type II error = 1 - POWER

Power increases as sample size increase

Is determined by

a. Frequency of condition under study/prevalance

b. magnitude of the effect

c. the study design

d. the sample size

69

## What is Likelihood ratio

###
likelihood that a given test result would be expected in a patient with the target disorder compared to the likelihood that the same result would be expected in a patient without the target disorder

assess how good a diagnostic test is, and to help in selecting appropriate diagnostic tests

70

## What is Number needed to Treat

###
the reciprocal of the change in the absolute risk brought about by an intervention (if risk reduction is 0.5 then NNT = 1/0.5 = 2.

No set limit to be considered clinically effective, but generally the lower the better

71

## Describe confidence intervals

###
An indication of variability of a point estimated

In general the wider the CI the less precise the point estimate

A 95% CI means that there is a 95% that this elevated or decreased risk not due to chance

72

## List 3 measurements of central tendency of descriptive stats

###
Mean--average--

Median-the value with half the subjects below it and half the subjects above it

Mode--for Nominal data--most frequently reported

73

## List two measurements of variance

###
Standard deviation--determines on average how much the individual values differ from the mean

Standard error--describes the distribution of the mean value== SD divided by the square root of the same size.

74

##
List 4 tests for assessing continuous data, assumed to following a bell curve

###
T-test--2 groups of continuous data

unpaired t-test--independent samples

paired-2 paired observations on the same individual or matched pats

ANOVA--comparison of two or more sample means

ANCOVA--combines regression and anlysis of variance

75

## List Non Parametric tests

###
1. Ordinal data and independent samples

Mann-Whitney-U test

Krusak Wallis test

2. Ordinal data, matched samples

Wilcoxon test

3. Freidmans 2 way ANOVA

76

## List tests for Proportions

###
For nominal data and independent samples

Chi-squared (typically proportions)

Fishers Exact test (use if one of the values as a 0)

Binominal test

77

## What is Linear regression and linear correlation

###
Linear regression analyzes the relationship between 2 variables --X and Y and attempts to find the best straight line through the data (assumes the data is Gaussian/normal)

goal is to find the line that best predicts Y from X

"Goodness of fi" = r2= it calculates how well the least squares regression line fits a given set of paired data--is a number between 0.0 and 1.0, if r2 is 0.0 then there is no linear relationship between X and Y, if it 1.0 then Y can be predicted perfectly from X

78

## What is a Logistic regression analysis

###
Most common example of multi-variable analysis

Statistical tool used to evaluation simultaneously the relationship of many variable (confounders) to the outcome of interst

79

## What is equation for sensitivity

### A/A + C

80