Predicting the outcome of patients with subarachnoid hemorrhage using machine learning techniques. de Toledo, P., Rios, P. M., Ledezma, A., Sanchis, A., Alen, J. F., & Lagares, A. IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society, 13(5):794–801, September, 2009. abstract bibtex Outcome prediction for subarachnoid hemorrhage (SAH) helps guide care and compare global management strategies. Logistic regression models for outcome prediction may be cumbersome to apply in clinical practice. To use machine learning techniques to build a model of outcome prediction that makes the knowledge discovered from the data explicit and communicable to domain experts. A derivation cohort (n = 441) of nonselected SAH cases was analyzed using different classification algorithms to generate decision trees and decision rules. Algorithms used were C4.5, fast decision tree learner, partial decision trees, repeated incremental pruning to produce error reduction, nearest neighbor with generalization, and ripple down rule learner. Outcome was dichotomized in favorable [Glasgow outcome scale (GOS) = I-II] and poor (GOS = III-V). An independent cohort (n = 193) was used for validation. An exploratory questionnaire was given to potential users (specialist doctors) to gather their opinion on the classifier and its usability in clinical routine. The best classifier was obtained with the C4.5 algorithm. It uses only two attributes [World Federation of Neurological Surgeons (WFNS) and Fisher's scale] and leads to a simple decision tree. The accuracy of the classifier [area under the ROC curve (AUC) = 0.84; confidence interval (CI) = 0.80-0.88] is similar to that obtained by a logistic regression model (AUC = 0.86; CI = 0.83-0.89) derived from the same data and is considered better fit for clinical use.
@ARTICLE{deToledo-2009,
author = {de Toledo, Paula and Rios, Pablo M. and Ledezma, Agapito and Sanchis,
Araceli and Alen, Jose F. and Lagares, Alfonso},
title = {Predicting the outcome of patients with subarachnoid hemorrhage using
machine learning techniques.},
journal = {IEEE transactions on information technology in biomedicine : a publication
of the IEEE Engineering in Medicine and Biology Society},
year = {2009},
volume = {13},
pages = {794--801},
number = {5},
month = sep,
DI = {10.1109/TITB.2009.2020434},
SN = {1558-0032},
UT = {MEDLINE:19369161},
Z9 = {1},
abstract = {Outcome prediction for subarachnoid hemorrhage (SAH) helps guide care
and compare global management strategies. Logistic regression models
for outcome prediction may be cumbersome to apply in clinical practice.
To use machine learning techniques to build a model of outcome prediction
that makes the knowledge discovered from the data explicit and communicable
to domain experts. A derivation cohort (n = 441) of nonselected SAH
cases was analyzed using different classification algorithms to generate
decision trees and decision rules. Algorithms used were C4.5, fast
decision tree learner, partial decision trees, repeated incremental
pruning to produce error reduction, nearest neighbor with generalization,
and ripple down rule learner. Outcome was dichotomized in favorable
[Glasgow outcome scale (GOS) = I-II] and poor (GOS = III-V). An independent
cohort (n = 193) was used for validation. An exploratory questionnaire
was given to potential users (specialist doctors) to gather their
opinion on the classifier and its usability in clinical routine.
The best classifier was obtained with the C4.5 algorithm. It uses
only two attributes [World Federation of Neurological Surgeons (WFNS)
and Fisher's scale] and leads to a simple decision tree. The accuracy
of the classifier [area under the ROC curve (AUC) = 0.84; confidence
interval (CI) = 0.80-0.88] is similar to that obtained by a logistic
regression model (AUC = 0.86; CI = 0.83-0.89) derived from the same
data and is considered better fit for clinical use.}
}
% This file was created with JabRef 2.4.2.
% Encoding: UTF-8
Downloads: 0
{"_id":{"_str":"51f5c76ba57e92543f000335"},"__v":2,"authorIDs":["54576e722abc8e9f370003c4","545e648a6aaec20d2300081a","5469957ebc7d6a460d00140f","8mdzoMZ27yguKiBHc"],"author_short":["de Toledo, P.","Rios, P. M.","Ledezma, A.","Sanchis, A.","Alen, J. F.","Lagares, A."],"bibbaseid":"detoledo-rios-ledezma-sanchis-alen-lagares-predictingtheoutcomeofpatientswithsubarachnoidhemorrhageusingmachinelearningtechniques-2009","bibdata":{"bibtype":"article","type":"article","author":[{"propositions":["de"],"lastnames":["Toledo"],"firstnames":["Paula"],"suffixes":[]},{"propositions":[],"lastnames":["Rios"],"firstnames":["Pablo","M."],"suffixes":[]},{"propositions":[],"lastnames":["Ledezma"],"firstnames":["Agapito"],"suffixes":[]},{"propositions":[],"lastnames":["Sanchis"],"firstnames":["Araceli"],"suffixes":[]},{"propositions":[],"lastnames":["Alen"],"firstnames":["Jose","F."],"suffixes":[]},{"propositions":[],"lastnames":["Lagares"],"firstnames":["Alfonso"],"suffixes":[]}],"title":"Predicting the outcome of patients with subarachnoid hemorrhage using machine learning techniques.","journal":"IEEE transactions on information technology in biomedicine : a publication of the IEEE Engineering in Medicine and Biology Society","year":"2009","volume":"13","pages":"794–801","number":"5","month":"September","di":"10.1109/TITB.2009.2020434","sn":"1558-0032","ut":"MEDLINE:19369161","z9":"1","abstract":"Outcome prediction for subarachnoid hemorrhage (SAH) helps guide care and compare global management strategies. Logistic regression models for outcome prediction may be cumbersome to apply in clinical practice. To use machine learning techniques to build a model of outcome prediction that makes the knowledge discovered from the data explicit and communicable to domain experts. A derivation cohort (n = 441) of nonselected SAH cases was analyzed using different classification algorithms to generate decision trees and decision rules. Algorithms used were C4.5, fast decision tree learner, partial decision trees, repeated incremental pruning to produce error reduction, nearest neighbor with generalization, and ripple down rule learner. Outcome was dichotomized in favorable [Glasgow outcome scale (GOS) = I-II] and poor (GOS = III-V). An independent cohort (n = 193) was used for validation. An exploratory questionnaire was given to potential users (specialist doctors) to gather their opinion on the classifier and its usability in clinical routine. The best classifier was obtained with the C4.5 algorithm. It uses only two attributes [World Federation of Neurological Surgeons (WFNS) and Fisher's scale] and leads to a simple decision tree. The accuracy of the classifier [area under the ROC curve (AUC) = 0.84; confidence interval (CI) = 0.80-0.88] is similar to that obtained by a logistic regression model (AUC = 0.86; CI = 0.83-0.89) derived from the same data and is considered better fit for clinical use.","bibtex":"@ARTICLE{deToledo-2009,\r\n author = {de Toledo, Paula and Rios, Pablo M. and Ledezma, Agapito and Sanchis,\r\n\tAraceli and Alen, Jose F. and Lagares, Alfonso},\r\n title = {Predicting the outcome of patients with subarachnoid hemorrhage using\r\n\tmachine learning techniques.},\r\n journal = {IEEE transactions on information technology in biomedicine : a publication\r\n\tof the IEEE Engineering in Medicine and Biology Society},\r\n year = {2009},\r\n volume = {13},\r\n pages = {794--801},\r\n number = {5},\r\n month = sep,\r\n DI = {10.1109/TITB.2009.2020434},\r\n SN = {1558-0032},\r\n UT = {MEDLINE:19369161},\r\n Z9 = {1},\r\n abstract = {Outcome prediction for subarachnoid hemorrhage (SAH) helps guide care\r\n\tand compare global management strategies. Logistic regression models\r\n\tfor outcome prediction may be cumbersome to apply in clinical practice.\r\n\tTo use machine learning techniques to build a model of outcome prediction\r\n\tthat makes the knowledge discovered from the data explicit and communicable\r\n\tto domain experts. A derivation cohort (n = 441) of nonselected SAH\r\n\tcases was analyzed using different classification algorithms to generate\r\n\tdecision trees and decision rules. Algorithms used were C4.5, fast\r\n\tdecision tree learner, partial decision trees, repeated incremental\r\n\tpruning to produce error reduction, nearest neighbor with generalization,\r\n\tand ripple down rule learner. Outcome was dichotomized in favorable\r\n\t[Glasgow outcome scale (GOS) = I-II] and poor (GOS = III-V). An independent\r\n\tcohort (n = 193) was used for validation. An exploratory questionnaire\r\n\twas given to potential users (specialist doctors) to gather their\r\n\topinion on the classifier and its usability in clinical routine.\r\n\tThe best classifier was obtained with the C4.5 algorithm. It uses\r\n\tonly two attributes [World Federation of Neurological Surgeons (WFNS)\r\n\tand Fisher's scale] and leads to a simple decision tree. The accuracy\r\n\tof the classifier [area under the ROC curve (AUC) = 0.84; confidence\r\n\tinterval (CI) = 0.80-0.88] is similar to that obtained by a logistic\r\n\tregression model (AUC = 0.86; CI = 0.83-0.89) derived from the same\r\n\tdata and is considered better fit for clinical use.}\r\n}\r\n\r\n% This file was created with JabRef 2.4.2.\r\n% Encoding: UTF-8\r\n\r\n","author_short":["de Toledo, P.","Rios, P. M.","Ledezma, A.","Sanchis, A.","Alen, J. F.","Lagares, A."],"key":"deToledo-2009","id":"deToledo-2009","bibbaseid":"detoledo-rios-ledezma-sanchis-alen-lagares-predictingtheoutcomeofpatientswithsubarachnoidhemorrhageusingmachinelearningtechniques-2009","role":"author","urls":{},"downloads":0,"html":"","metadata":{"authorlinks":{"ledezma, a":"http://www.caos.inf.uc3m.es/ledezma/ca/publicaciones/"}}},"bibtype":"article","biburl":"http://www.caos.inf.uc3m.es/bibs/pubCAOS.bib","downloads":0,"search_terms":["predicting","outcome","patients","subarachnoid","hemorrhage","using","machine","learning","techniques","de toledo","rios","ledezma","sanchis","alen","lagares"],"title":"Predicting the outcome of patients with subarachnoid hemorrhage using machine learning techniques.","title_words":["predicting","outcome","patients","subarachnoid","hemorrhage","using","machine","learning","techniques"],"year":2009,"keywords":[],"dataSources":["Z4T4fewybNpYCWveD"]}