Naive Bayesian Prediction of Bleeding After Heart ByPass Surgery

1
Naive Bayesian Prediction of Bleeding After
Heart By-Pass Surgery

• Raymond Lister
• University of Technology, Sydney
• (presenting author)
• other authors ...
• Smith, Ray Hawson
• The Prince Charles Hospital, Brisbane

2
Problem

• Predict Who Will Bleed Excessively After Heart
  Bypass Surgery.

3
Physiological Bleeding

• Not haemophilia
• its the technology
• Affects 1 in 8 patients
• Can cause death, or lifelong disability
• e.g. Alan Bond
• Treatable with drugs and blood products
• problem is distinguishing it from surgical error.
  

4
Earlier Attempts at Prediction

• Correlation to single clinical parameter
• several inadequately weak indicators found.
• Multivariate Linear models
• Gravlee et al. (1994)
• ... Poor results

5
Naive Bayes

• Combines multiple weak evidence ei to calculate
  probability of hypothesis P(H).
• Its simple. Details? See references
• Duda, Gashnig, and Hart (1979) Prospector
• Shinghal R. (1992)
• Single pass through data! No magic numbers!
• Occams razor
• c.f. Neural Networks

6
Our Data

• N 83 patients
• 8 physiological bleeders
• prior probability 8/83 0.1
• 6 pre-operative parameters
• including whole blood aggregation (WBAG)
• 63 possible combinations
• 8 post-operative parameters
• 255 possible combinations

7
Blood Loss v. WBAG
8
Cross Validation
Repeat Construct random 90 subset of
training data Develop Naive Bayes Model
with that data Test that model on remaining
test data Many times (100?) Report average
prediction for each patient, with standard
deviation (67 confidence interval)
9
Pre-op versus Post-op testing
A solid pre-operative test strategy ideal, but
not possible. Hence a two-stage procedure
1. Screen all patients pre-op, to cull those at
low risk. 2. Take special precautions with
remainder and test them post-op.
10
Parameter Selection
For the 63 combinations of pre-op
parameters do Perform 100 cross validation runs
(N83). Select best set of pre-op parameters.
Also identify the subset of patients judged as
being at risk by pre-op system (N29
patients). For the 255 combinations of post-op
parameters do Perform 100 cross validation runs,
using the subset of at risk patients
(N29). (Total computer run time is just a few
seconds!)
11
Best Pre-Operative Predictor
Each dot is a patient. 54/83 65 patients
culled.
12
Best Post-Operative Predictor
Each dot is a patient. All real bleeders
identified, plus 7 false positives.
13
Conclusion

• Results encouraging
• N83 not definitive, but cross validation gives
  confidence.
• Larger study justified.
• (Dont build complex models until simple models
  are shown to be inadequate.)