PMID- 21672907
OWN - NLM
STAT- MEDLINE
DCOM- 20111102
LR  - 20211020
IS  - 1527-974X (Electronic)
IS  - 1067-5027 (Print)
IS  - 1067-5027 (Linking)
VI  - 18
IP  - 4
DP  - 2011 Jul-Aug
TI  - The application of naive Bayes model averaging to predict Alzheimer's disease 
      from genome-wide data.
PG  - 370-5
LID - 10.1136/amiajnl-2011-000101 [doi]
AB  - OBJECTIVE: Predicting patient outcomes from genome-wide measurements holds 
      significant promise for improving clinical care. The large number of measurements 
      (eg, single nucleotide polymorphisms (SNPs)), however, makes this task 
      computationally challenging. This paper evaluates the performance of an algorithm 
      that predicts patient outcomes from genome-wide data by efficiently model 
      averaging over an exponential number of naive Bayes (NB) models. DESIGN: This 
      model-averaged naive Bayes (MANB) method was applied to predict late onset 
      Alzheimer's disease in 1411 individuals who each had 312,318 SNP measurements 
      available as genome-wide predictive features. Its performance was compared to 
      that of a naive Bayes algorithm without feature selection (NB) and with feature 
      selection (FSNB). MEASUREMENT: Performance of each algorithm was measured in 
      terms of area under the ROC curve (AUC), calibration, and run time. RESULTS: The 
      training time of MANB (16.1 s) was fast like NB (15.6 s), while FSNB (1684.2 s) 
      was considerably slower. Each of the three algorithms required less than 0.1 s to 
      predict the outcome of a test case. MANB had an AUC of 0.72, which is 
      significantly better than the AUC of 0.59 by NB (p<0.00001), but not 
      significantly different from the AUC of 0.71 by FSNB. MANB was better calibrated 
      than NB, and FSNB was even better in calibration. A limitation was that only one 
      dataset and two comparison algorithms were included in this study. CONCLUSION: 
      MANB performed comparatively well in predicting a clinical outcome from a 
      high-dimensional genome-wide dataset. These results provide support for including 
      MANB in the methods used to predict outcomes from large, genome-wide datasets.
FAU - Wei, Wei
AU  - Wei W
AD  - Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, 
      Pennsylvania 15260, USA.
FAU - Visweswaran, Shyam
AU  - Visweswaran S
FAU - Cooper, Gregory F
AU  - Cooper GF
LA  - eng
GR  - HHSN276201000030C/LM/NLM NIH HHS/United States
GR  - R01 LM010020/LM/NLM NIH HHS/United States
GR  - R01-LM010020/LM/NLM NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, U.S. Gov't, Non-P.H.S.
PL  - England
TA  - J Am Med Inform Assoc
JT  - Journal of the American Medical Informatics Association : JAMIA
JID - 9430800
RN  - 0 (Apolipoproteins E)
SB  - IM
MH  - Aged
MH  - Aged, 80 and over
MH  - Algorithms
MH  - Alzheimer Disease/*diagnosis/*genetics
MH  - Apolipoproteins E/genetics
MH  - *Artificial Intelligence
MH  - Bayes Theorem
MH  - Case-Control Studies
MH  - *Genome-Wide Association Study
MH  - Humans
MH  - Models, Genetic
MH  - Polymorphism, Single Nucleotide
MH  - Prognosis
MH  - ROC Curve
PMC - PMC3128400
COIS- Competing interests: None.
EDAT- 2011/06/16 06:00
MHDA- 2011/11/04 06:00
PMCR- 2012/07/01
CRDT- 2011/06/16 06:00
PHST- 2011/06/16 06:00 [entrez]
PHST- 2011/06/16 06:00 [pubmed]
PHST- 2011/11/04 06:00 [medline]
PHST- 2012/07/01 00:00 [pmc-release]
AID - amiajnl-2011-000101 [pii]
AID - 10.1136/amiajnl-2011-000101 [doi]
PST - ppublish
SO  - J Am Med Inform Assoc. 2011 Jul-Aug;18(4):370-5. doi: 
      10.1136/amiajnl-2011-000101.