Fragility Index

57

Transcript of Fragility Index

Page 1: Fragility Index
Page 2: Fragility Index

Yes, a talkabout astatistic…

Page 3: Fragility Index

14 June

Page 4: Fragility Index

FRAGILITY INDEX(the rise of the P value)

@kathyrowan101

Page 5: Fragility Index
Page 6: Fragility Index

de Winter and Dodou (2015) PeerJ

Page 7: Fragility Index

RCTs – best evidence

• RCTs are fundamentally hypothesis testing instruments (a hypothesis being an educated guess about how things work)

• RCTs are a type of scientific experiment which aims to reduce bias when testing new/existing treatments

Page 8: Fragility Index
Page 9: Fragility Index

RCTs – best evidence

• RCTs are fundamentally hypothesis testing instruments (a hypothesis being an educated guess about how things work)

• RCTs are a type of scientific experiment which aims to reduce bias when testing new/existing treatments

• RCTs permit the use of probability theory to express the likelihood of a difference in outcome between treatments/groups

Page 10: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

Page 11: Fragility Index
Page 12: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Null hypothesis H0 – default position – assumed to be true until evidence indicates otherwise

Page 13: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Null hypothesis H0 – default position – assumed to be true until evidence indicates otherwise

• If observed data are unlikely,then null hypothesis is rejected

• If observed data are consistent,then null hypothesis is not rejected

Page 14: Fragility Index

An analogy might help…?

• Analogous to a criminal trial• Defendant assumed to be innocent (null)• Until proven guilty (null is rejected)• Beyond reasonable doubt (agreed threshold)

Page 15: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Agreed threshold traditionally set at 5% (P<0.05)

Page 16: Fragility Index
Page 17: Fragility Index

Fisher’s exact test

• Used in the analysis of contingency tables• Used when sample sizes are small

(valid for all sample sizes)• Calculates significance of deviation from the

null hypothesis exactly• It can’t be calculated in your head…!

Page 18: Fragility Index

RCTs – size and events are important

Page 19: Fragility Index

Bad outcome

Good outcome

Treatment A

1 99

Treatment B

9 91

Bad outcome

Good outcome

Treatment A

200 1800

Treatment B

250 1750

P=0.02

P=0.02

Page 20: Fragility Index

Bad outcome

Good outcome

Treatment A

1 2 99 98

Treatment B

9 91

Bad outcome

Good outcome

Treatment A

200 201 1800 799

Treatment B

250 1750

P=0.06

P=0.02

Page 21: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Agreed threshold traditionally set at 5% (P<0.05)• A shift of only a few events can change

interpretation…

Page 22: Fragility Index
Page 23: Fragility Index

Bad outcome

Good outcome

Treatment A

2 98

Treatment B

9 91

Bad outcome

Good outcome

Treatment A

2 98

Treatment B

9 91

P=0.02chi-square

P=0.06Fisher’s exact

Page 24: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Traditionally set at 5% (P<0.05)• A shift of only a few events can change

interpretation…• Simple recalculation with the correct statistical

test can change interpretation…

Page 25: Fragility Index

Primary and secondary hypotheses

Page 26: Fragility Index
Page 27: Fragility Index
Page 28: Fragility Index

P value

• P value - probability of obtaining a result equal to or more extreme than observed when the null hypothesis is true

• Traditionally set at 5% (P<0.05)• A shift of only a few events can change

interpretation…• Simple recalculation with the correct test can

change interpretation…• Significant subgroups(?!) – hypothesis generating

Page 29: Fragility Index
Page 30: Fragility Index

FRAGILITY INDEX

Page 31: Fragility Index

de Winter and Dodou (2015) PeerJ

Page 32: Fragility Index
Page 33: Fragility Index

• Calculates how many events (f) required to change a significant to a non-significant result

• Designed for dichotomous outcomes

Page 34: Fragility Index

Table

Bad outcome

Good outcome

Treatment A

4 96

Treatment B

17 83

Page 35: Fragility Index
Page 36: Fragility Index
Page 37: Fragility Index
Page 38: Fragility Index

Table

Bad outcome

Good outcome

Treatment A

5 95

Treatment B

17 83

Page 39: Fragility Index
Page 40: Fragility Index
Page 41: Fragility Index
Page 42: Fragility Index
Page 43: Fragility Index
Page 44: Fragility Index

FRAGILITY INDEX EQUALS FOUR

Page 45: Fragility Index
Page 46: Fragility Index

Walsh et al. 2014 Evaniew et al. 2015 Ridgeon et al. 2016RCTs in NEJM, Lancet, JAMA, Annals, BMJ(RCT in MeSH)

RCTs on spine surgery

Multicentre (>1) RCTs in critically ill

2004-2010 2009-2014 No date restrictionP<0.05 resultin abstract

P<0.05 resultin abstract

P<0.05 resultfor mortality

RCTs=399 RCTs= 40 RCTs=56Patients=median 682(IQR 15-112604)

Patients=median 132(IQR 79-208)

Patients=median 127(IQR 79-326)

Page 47: Fragility Index

Walsh et al. 2014 Evaniew et al. 2015 Ridgeon et al. 2016RCTs in NEJM, Lancet, JAMA, Annals, BMJ(RCT in MeSH)

RCTs on spine surgery

Multicentre (>1) RCTs in critically ill

2004-2010 2009-2014 No date restrictionP<0.05 resultin abstract

P<0.05 resultin abstract

P<0.05 resultfor mortality

RCTs=399 RCTs= 40 RCTs=56Patients=median 682(IQR 15-112604)

Patients=median 132(IQR 79-208)

Patients=median 127(IQR 79-326)

66% primary result 58% primary result 52% primary result

Page 48: Fragility Index

Walsh et al. 2014 Evaniew et al. 2015 Ridgeon et al. 2016Fragility Index =median 8(IQR 3-18)

Fragility Index =median 2(IQR 1-3)

Fragility Index =median 2(IQR 1-3.5)

Range = 0-808 Range = 0-39 Range = 0-48FI zero = 10% FI zero = 20% FI zero = 20%FI ≤3 = 25% FI ≤3 = 75% FI ≤3 = 75%FI ≤loss tofollow-up = 53%

FI ≤loss tofollow-up = 65%

FI ≤loss tofollow-up = 87.5%

Page 49: Fragility Index

Walsh et al. 2014 Evaniew et al. 2015 Ridgeon et al. 2016Fragility Index =median 8(IQR 3-18)

Fragility Index =median 2(IQR 1-3)

Fragility Index =median 2(IQR 1-3.5)

Range = 0-808 Range = 0-39 Range = 0-48FI zero = 10% FI zero = 20% FI zero = 20%FI ≤3 = 25% FI ≤3 = 75% FI ≤3 = 75%FI ≤loss tofollow-up = 53%

FI ≤loss tofollow-up = 65%

FI ≤loss tofollow-up = 87.5%

Page 50: Fragility Index

Fragility Index

• Significant results of many RCTs hinge on very few events

• Results could potentially be overturned if missing/loss to follow-up data were known

Page 51: Fragility Index

http://fragilityindex.com/

Page 52: Fragility Index
Page 53: Fragility Index
Page 54: Fragility Index
Page 55: Fragility Index
Page 56: Fragility Index

Fragility Index

• Significant results of many RCTs hinge on very few events

• Results could potentially be overturned if missing/loss to follow-up data were known

• Reporting of the Fragility Index may help interpretation/over-interpretation

• You can calculate it yourself…!

http://fragilityindex.com/

Page 57: Fragility Index