Pregled bibliografske jedinice broj: 54471
Detecting predictors of new-born survival by fuzzy sets based machine learning system
Detecting predictors of new-born survival by fuzzy sets based machine learning system // Medical Infobahn for Europe, proceedings of MIE2000 and GDMS2000 / Hasman, A ; Blobel, B. ; Dudeck, J. ; Engelbrecht, R. et al. (ur.).
Amsterdam: IOS Press, 2000. str. 795-798 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
CROSBI ID: 54471 Za ispravke kontaktirajte CROSBI podršku putem web obrasca
Naslov
Detecting predictors of new-born survival by fuzzy sets based machine learning system
Autori
Lukačić, Zoran ; Kern, Josipa ; Težak-Benčić, Marija
Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni
Izvornik
Medical Infobahn for Europe, proceedings of MIE2000 and GDMS2000
/ Hasman, A ; Blobel, B. ; Dudeck, J. ; Engelbrecht, R. et al. - Amsterdam : IOS Press, 2000, 795-798
Skup
Medical Informatics Europe 2000
Mjesto i datum
Hannover, Njemačka, 27.08.2000. - 01.09.2000
Vrsta sudjelovanja
Predavanje
Vrsta recenzije
Međunarodna recenzija
Ključne riječi
fuzzy set; machine learning; prediction
Sažetak
Machine learning system based on fuzzy sets was used for detecting predictors of new-born survival within the first 15 days after birth. The system processed real-life medical data of 566 new-borns; 528 survived and were classified as alive, the remaining 38 did not survive and were classified as died. The state of each new-born was described by values of 112 attributes. The system detected five of the attributes as the best predictors for survival (asphyxia, apnoea, birth weight, reanimation and gestation age). To evaluate, the following procedure was used: 566 new-borns were divided into two groups by random selection; 396 randomly selected formed the learning group, the remaining 170 new-borns formed the test group. The system accquired prediction knowledge by processing data of the learning group. Using the knowledge thus acquired, the system predicted survival for each new-born from the test group several times, each time using another set of attributes: once, using all 112 attributes; once, using attributes detected by the system as the best predictors; once, using remaining attributes without the best predictors. After the predictions for all new-borns from the test group had been finished, classification accuracy, sensitivity (accuracy for alive) and sšpecificity (accuracy for died) were calculated as measures of prediction success with particular sets of attributes. The results have shown that the best prognostic accuracies were achieved when prediction was done using those attributes which the system detected as the best predictors for new-born survival.
Izvorni jezik
Engleski
Znanstvena područja
Temeljne medicinske znanosti
