Skip to main content

Advertisement

Table 8 Mean scores on the Agincourt dataset using the WHO categories

From: Automatically determining cause of death from verbal autopsy narratives

  Precision Sensitivity F 1 PCCC CSMFA CCCSMFA
Adult (15–69 years)
Naïve Bayes .433 .448 .431 .432 .876 .662
Random forest .438 .464 .436 .448 .832 .543
SVM .502 .505 .491 .490 .857 .612
Neural network .470 .495 .451 .480 .750 .322
Child (29 days–14 years)
Naïve Bayes .378 .388 .370 .360 .793 .437
Random forest .456 .450 .431 .425 .799 .453
SVM .471 .465 .452 .440 .816 .499
Neural network .388 .428 .374 .402 .667 .095
Neonate (<29 days)
Naïve Bayes .276 .384 .305 .296 .610 -.060
Random forest .292 .369 .314 .279 .673 .111
SVM .391 .405 .373 .320 .733 .274
Neural network .156 .265 .179 .160 .502 -.353
  1. CCCSMFA was calculated using.632 as the mean of random allocation, as suggested in [12]