PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
Synapse
⌘+K
Synapse
November 1, 1994Clinical CardiologyOpen Access

Artificial intelligence versus logistic regression statistical modelling to predict cardiac complications after noncardiac surgery

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Does an artificial intelligence neural network improve the prediction of postoperative cardiac events compared to logistic regression in patients undergoing noncardiac surgery?

Population

360 patients referred for preoperative cardiac risk assessment before major noncardiac surgery.

Comparison

Neural network predictive model using 14 input… vs Backward stepwise logistic regression…

Design

Cohort

Follow-up

postoperative period

Authors

JLJean LetteBCBruce W. CollettiMCMichel Cerino

Discussion

Loading...

Member takes

Overview

May offer a more specific preoperative risk tool; hypothesis-generating and requires prospective validation before practice change.

Structured PICO

Does an artificial intelligence neural network improve the prediction of postoperative cardiac events compared to logistic regression in patients undergoing noncardiac surgery?

P
Population
360 patients referred for preoperative cardiac risk assessment before major noncardiac surgery (200 in training group, 160 in validation group).
I
Intervention
Neural network (NN) predictive model using 14 input, 29 hidden, and 1 output neurons with a back-propagation algorithm.
C
Comparator
Backward stepwise logistic regression (LR) multivariate statistical analysis.
O
Outcome
Prediction of postoperative myocardial infarction and/or cardiac death.hard clinical

Artificial intelligence using neural networks may provide a more specific alternative to conventional logistic regression for preoperative cardiac risk assessment.

Cite This Study

Lette et al. (1994) studied this question.

synapsesocial.com/papers/6a718842b5c1fe5ca9dfdbb0https://doi.org/10.1002/clc.4960171109
View Full Paper
Ask AI
Bookmark
Share