Table 7 Mean scores on the Agincourt dataset
From: Automatically determining cause of death from verbal autopsy narratives
Precision | Sensitivity | F 1 | PCCC | CSMFA | CCCSMFA | |
|---|---|---|---|---|---|---|
Adult (15–69 years) | ||||||
Naïve Bayes | .517 | .517 | .513 | .481 | .932 | .814 |
Random forest | .511 | .517 | .496 | .480 | .844 | .577 |
SVM | .569 | .566 | .561 | .543 | .901 | .730 |
Neural network | .575 | .578 | .570 | .547 | .918 | .777 |
Child (29 days–14 years) | ||||||
Naïve Bayes | .488 | .440 | .435 | .395 | .761 | .351 |
Random forest | .521 | .502 | .487 | .463 | .816 | .501 |
SVM | .535 | .518 | .512 | .479 | .872 | .653 |
Neural network | .572 | .562 | .552 | .527 | .869 | .645 |
Neonate (<29 days) | ||||||
Naïve Bayes | .532 | .526 | .483 | .404 | .702 | .191 |
Random forest | .409 | .496 | .427 | .366 | .710 | .213 |
SVM | .387 | .417 | .371 | .266 | .693 | .165 |
Neural network | .356 | .412 | .354 | .259 | .636 | .012 |