Skip to main content

Table 5 Median neonate cause-specific chance-corrected concordance (%) for InSilicoVA and Tariff 2.0

From: Performance of InSilicoVA for assigning causes of death to verbal autopsies: multisite validation study using clinical diagnostic gold standards

   InSilicoVA (Tariff 2.0 training) Tariff 2.0
   No HCE HCE No HCE HCE
PHMRC cause ICD10 Median 95% UI Median 95% UI Median 95% UI Median 95% UI
Pneumonia J22 5.6 (4.0, 8.0) 3.5 (1.6, 5.8) 31.4 (31.4, 37.1) 37.1 (37.1, 37.1)
Preterm delivery P07 50.5 (49.3, 52.0) 52.0 (50.7, 53.3) 41.5 (40.8, 42.2) 40.5 (40.0, 41.1)
Birth asphyxia P21 38.0 (36.7, 39.5) 38.7 (37.1, 40.0) 22.0 (21.4, 22.6) 25.9 (25.1, 26.6)
Meningitis/sepsis P36 43.8 (41.6, 45.5) 44.3 (42.9, 46.0) 37.9 (36.9, 38.8) 44.3 (43.2, 45.1)
Stillbirth P95 90.9 (90.3, 91.2) 91.0 (90.6, 91.4) 85.7 (85.1, 86.2) 85.6 (85.1, 86.1)
Congenital malformation Q89 −0.9 (−1.6, 0.4) −1.0 (−1.9, 0.3) 34.2 (32.9, 34.2) 34.8 (34.2, 36.1)
  1. Table 5 shows the cause-specific chance-corrected concordance for neonate data for InSilicoVA using an empirical probbase derived from training data mapped to the Tariff 2.0 format. Previously published Tariff 2.0 results are shown for comparison
  2. PHMRC Population Health Metrics Research Consortium, ICD International Classification of Diseases, HCE health care experience, UI uncertainty interval