Catalogo Articoli (Spogli Riviste)
OPAC HELP
Titolo: NEURALNETWORK ASSESSMENT OF PERIOPERATIVE CARDIAC RISK IN VASCULARSURGERY PATIENTS
Autore: LAPUERTA P; LITALIEN GJ; PAUL S; HENDEL RC; LEPPO JA; FLEISHER LA; COHEN MC; EAGLE KA; GIUGLIANO RP;
 Indirizzi:
 BRISTOL MYERS SQUIBB,OUTCOMES RES,POB 4000 PRINCETON NJ 08543 UNIV SO CALIF,SCH MED,DEPT INTERNAL MED LOS ANGELES CA 90033 MASSACHUSETTS GEN HOSP,VASC UNIT BOSTON MA 02114 MASSACHUSETTS GEN HOSP,CARDIAC UNIT BOSTON MA 02114 NORTHWESTERN UNIV,SCH MED,DEPT MED CARDIOL CHICAGO IL 00000 UNIV MASSACHUSETTS,MED CTR,DEPT NUCL MED WORCESTER MA 00000 UNIV MASSACHUSETTS,MED CTR,DEPT MED CARDIOL WORCESTER MA 00000 JOHNS HOPKINS UNIV BALTIMORE MD 00000 BETH ISRAEL DEACONESS MED CTR BOSTON MA 00000 UNIV MICHIGAN,MED CTR,DIV CARDIOL ANN ARBOR MI 48109
 Titolo Testata:
 Medical decision making
fascicolo: 1,
volume: 18,
anno: 1998,
pagine: 70  75
 SICI:
 0272989X(1998)18:1<70:NAOPCR>2.0.ZU;20
 Fonte:
 ISI
 Lingua:
 ENG
 Soggetto:
 MYOCARDIALINFARCTION; MODEL; COMPLICATIONS; PREDICTION; DIAGNOSIS; SURVIVAL;
 Keywords:
 NEURAL NETWORKS; LOGISTIC REGRESSION; LIKELIHOOD RATIO; BAYES THEOREM; CARDIAC RISK;
 Tipo documento:
 Article
 Natura:
 Periodico
 Settore Disciplinare:
 Science Citation Index Expanded
 Science Citation Index Expanded
 Citazioni:
 25
 Recensione:
 Indirizzi per estratti:



 Citazione:
 P. Lapuerta et al., "NEURALNETWORK ASSESSMENT OF PERIOPERATIVE CARDIAC RISK IN VASCULARSURGERY PATIENTS", Medical decision making, 18(1), 1998, pp. 7075
Abstract
Neural networks were developed to predict perioperative cardiac complications with data from 567 vascular surgery patients. Neural network scores were based on cardiac risk factors and dipyridamole thallium results. These scores were converted into likelihood ratios that predicted cardiac risk. The prognostic accuracy of the neural networks was similar to that of logistic regression models (ROC areas 76.0% vs 75.8%), but their calibration was better. Logistic regression overestimated event rates in a group of highrisk patients (predicted event rate, 64%; observed rate 30%; n = 50, p < 0.001). On a validation set of 514 patients, the neural networks still had ROC similar areas to those of logistic regression (68.3% vs 67.5%), but logistic regression again overestimated event rates for a group of highrisk patients. The calibration difference was reflected in the HosmerLemeshow chisquare statistic (18.6 for the neural networks, 45.0 for logistic regression). The neural networks successfully estimated perioperative cardiac risk with better calibration than comparable logistic regression models.
ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 28/11/20 alle ore 09:49:38